Compare commits

...

67 Commits

Author SHA1 Message Date
Manfred Riem
f5f8311415 fix: correct PresetError docstring from template to preset 2026-03-10 17:20:54 -05:00
Manfred Riem
6da1375396 fix: address Copilot PR review comments (round 3)
- Fix PS Resolve-Template fallback to skip dot-prefixed dirs (.cache)
- Rename _catalog to _catalog_name for consistency with extension system
- Enforce install_allowed policy in CLI preset add and download_pack()
- Fix shell injection: pass registry path via env var instead of string interpolation
2026-03-10 17:06:34 -05:00
Manfred Riem
1c143e64b1 fix: remove self-test from catalog.json (local-only preset) 2026-03-10 16:39:07 -05:00
Manfred Riem
da6e7d2283 fix: address Copilot PR review comments (round 2)
- Fix init --preset error masking: distinguish "not found" from real errors
- Fix bash resolve_template: skip hidden dirs in extensions (match Python/PS)
- Fix temp dir leaks in tests: use temp_dir fixture instead of mkdtemp
- Fix self-test catalog entry: add note that it's local-only (no download_url)
- Fix Windows path issue in resolve_with_source: use Path.relative_to()
- Fix skill restore path: use project's .specify/templates/commands/ not source tree
- Add encoding="utf-8" to all file read/write in agents.py
- Update test to set up core command templates for skill restoration
2026-03-10 16:35:17 -05:00
Manfred Riem
3ffef55954 fix: narrow empty except blocks and add explanatory comments 2026-03-10 15:16:43 -05:00
Manfred Riem
52f137ce84 fix: address Copilot PR review comments
- Move save_init_options() before preset install so skills propagation
  works during 'specify init --preset --ai-skills'
- Clean up downloaded ZIP after successful preset install during init
- Validate --from URL scheme (require HTTPS, HTTP only for localhost)
- Expose unregister_commands() on extensions.py CommandRegistrar wrapper
  instead of reaching into private _registrar field
- Use _get_merged_packs() for search() and get_pack_info() so all
  active catalogs are searched, not just the highest-priority one
- Fix fetch_catalog() cache to verify cached URL matches current URL
- Fix PresetResolver: script resolution uses .sh extension, consistent
  file extensions throughout resolve(), and resolve_with_source()
  delegates to resolve() to honor template_type parameter
- Fix bash common.sh: fall through to directory scan when python3
  returns empty preset list
- Fix PowerShell Resolve-Template: filter out dot-folders and sort
  extensions deterministically
2026-03-10 15:11:31 -05:00
Manfred Riem
445eefe5ba fix: address PR check failures (ruff F541, CodeQL URL substring)
- Remove extraneous f-prefix from two f-strings without placeholders
- Replace substring URL check in test with startswith/endswith assertions
  to satisfy CodeQL incomplete URL substring sanitization rule
2026-03-10 14:45:16 -05:00
Manfred Riem
35ced30747 feat(presets): propagate command overrides to skills via init-options
- Add save_init_options() / load_init_options() helpers that persist
  CLI flags from 'specify init' to .specify/init-options.json
- PresetManager._register_skills() overwrites SKILL.md files when
  --ai-skills was used during init and corresponding skill dirs exist
- PresetManager._unregister_skills() restores core template content
  on preset removal
- registered_skills stored in preset registry metadata
- 8 new tests covering skill override, skip conditions, and restore
2026-03-10 14:31:17 -05:00
Manfred Riem
914a06a89f Merge remote-tracking branch 'upstream/main' into pr-1787
# Conflicts:
#	CHANGELOG.md
#	src/specify_cli/extensions.py
2026-03-10 14:20:38 -05:00
Manfred Riem
abf4aebdb3 feat(presets): pluggable preset system with template/command overrides, catalog, and resolver
- Rename 'template packs' to 'presets' to avoid naming collision with core templates
- PresetManifest, PresetRegistry, PresetManager, PresetCatalog, PresetResolver in presets.py
- Extract CommandRegistrar to agents.py as shared infrastructure
- CLI: specify preset list/add/remove/search/resolve/info
- CLI: specify preset catalog list/add/remove
- --preset option on specify init
- Priority-based preset stacking (--priority, lower = higher precedence)
- Command overrides registered into all detected agent directories (17+ agents)
- Extension command safety: skip registration if target extension not installed
- Multi-catalog support: env var, project config, user config, built-in defaults
- resolve_template() / Resolve-Template in bash/PowerShell scripts
- Self-test preset: overrides all 6 core templates + 1 command
- Scaffold with 4 examples: core/extension template and command overrides
- Preset catalog (catalog.json, catalog.community.json)
- Documentation: README.md, ARCHITECTURE.md, PUBLISHING.md
- 110 preset tests, 253 total tests passing
2026-03-10 14:17:44 -05:00
Ben Lawson
2632a0f52d feat(extensions): support .extensionignore to exclude files during install (#1781)
* feat(extensions): support .extensionignore to exclude files during install

Add .extensionignore support so extension authors can exclude files and
folders from being copied when users run 'specify extension add'.

The file uses glob-style patterns (one per line), supports comments (#),
blank lines, trailing-slash directory patterns, and relative path matching.
The .extensionignore file itself is always excluded from the copy.

- Add _load_extensionignore() to ExtensionManager
- Integrate ignore function into shutil.copytree in install_from_directory
- Document .extensionignore in EXTENSION-DEVELOPMENT-GUIDE.md
- Add 6 tests covering all pattern matching scenarios
- Bump version to 0.1.14

* fix(extensions): use pathspec for gitignore-compatible .extensionignore matching

Replace fnmatch with pathspec.GitIgnoreSpec to get proper .gitignore
semantics where * does not cross directory boundaries. This addresses
review feedback on #1781.

Changes:
- Switch from fnmatch to pathspec>=0.12.0 (GitIgnoreSpec.from_lines)
- Normalize backslashes in patterns for cross-platform compatibility
- Distinguish directories from files for trailing-slash patterns
- Update docs to accurately describe supported pattern semantics
- Add edge-case tests: .., absolute paths, empty file, backslashes,
  * vs ** boundary behavior, and ! negation
- Move changelog entry to [Unreleased] section
2026-03-10 12:02:04 -05:00
Adrián Luján Muñoz
4ab91fbadf feat: add Codex support for extension command registration (#1767)
* feat: add Codex support for extension command registration

* test: add codex command registrar mapping check

* test: add codex consistency check to test_agent_config_consistency

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-10 09:50:42 -05:00
copilot-swe-agent[bot]
6003a232d8 test(templates): add comprehensive unit tests for template pack system
Co-authored-by: mnriem <15701806+mnriem@users.noreply.github.com>
2026-03-09 21:05:27 +00:00
copilot-swe-agent[bot]
2e8a4d6432 feat(templates): add pluggable template system with packs, catalog, resolver, and CLI commands
Co-authored-by: mnriem <15701806+mnriem@users.noreply.github.com>
2026-03-09 21:02:52 +00:00
copilot-swe-agent[bot]
65ecaa9fe4 Initial plan 2026-03-09 20:53:50 +00:00
Manfred Riem
5c0bedb410 chore: bump version to 0.2.0 (#1786)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2026-03-09 14:54:08 -05:00
Pavel-tabnine
d92798d5b0 fix: sync agent list comments with actual supported agents (#1785)
Several comment and documentation strings were not updated when
Mistral Vibe support was added, leaving them out of sync with the
code. This fixes:
- update-agent-context.sh: add Generic to Supports header comment
- update-agent-context.ps1: add generic to Multi-Agent header comment
- README.md: add Mistral Vibe to CLI tool-check text
2026-03-09 14:34:54 -05:00
Copilot
ee922cbde9 feat(extensions): support multiple active catalogs simultaneously (#1720)
* Initial plan

* feat(extensions): implement multi-catalog stack support

- Add CatalogEntry dataclass to represent catalog entries
- Add get_active_catalogs() reading SPECKIT_CATALOG_URL, project config,
  user config, or built-in default stack (org-approved + community)
- Add _load_catalog_config() to parse .specify/extension-catalogs.yml
- Add _validate_catalog_url() HTTPS validation helper
- Add _fetch_single_catalog() with per-URL caching, backward-compat for DEFAULT_CATALOG_URL
- Add _get_merged_extensions() that merges all catalogs (priority wins on conflict)
- Update search() and get_extension_info() to use merged results
  annotated with _catalog_name and _install_allowed
- Update clear_cache() to also remove per-URL hash cache files
- Add extension_catalogs CLI command to list active catalogs
- Add catalog add/remove sub-commands for .specify/extension-catalogs.yml
- Update extension_add to enforce install_allowed=false policy
- Update extension_search to show source catalog per result
- Update extension_info to show source catalog with install_allowed status
- Add 13 new tests covering catalog stack, merge conflict resolution,
  install_allowed enforcement, and catalog metadata

Co-authored-by: mnriem <15701806+mnriem@users.noreply.github.com>

* docs: update RFC, user guide, and API reference for multi-catalog support

- RFC: replace FUTURE FEATURE section with full implementation docs,
  add catalog stack resolution order, config file examples, merge
  conflict resolution, and install_allowed behavior
- EXTENSION-USER-GUIDE.md: add multi-catalog section with CLI examples
  for catalogs/catalog-add/catalog-remove, update catalog config docs
- EXTENSION-API-REFERENCE.md: add CatalogEntry class docs, update
  ExtensionCatalog docs with new methods and result annotations,
  add catalog CLI commands (catalogs, catalog add, catalog remove)

Also fix extension_catalogs command to correctly show "Using built-in
default catalog stack" when config file exists but has empty catalogs

Co-authored-by: mnriem <15701806+mnriem@users.noreply.github.com>

* Potential fix for pull request finding 'Empty except'

Co-authored-by: Copilot Autofix powered by AI <223894421+github-code-quality[bot]@users.noreply.github.com>

* fix: remove extraneous f-string prefixes (ruff F541)

Remove f-prefix from strings with no placeholders in catalog_remove
and extension_search commands.

Co-authored-by: mnriem <15701806+mnriem@users.noreply.github.com>

* fix: address PR review feedback for multi-catalog support

- Rename 'org-approved' catalog to 'default'
- Move 'catalogs' command to 'catalog list' for consistency
- Add 'description' field to CatalogEntry dataclass
- Add --description option to 'catalog add' CLI command
- Align install_allowed default to False in _load_catalog_config
- Add user-level config detection in catalog list footer
- Fix _load_catalog_config docstring (document ValidationError)
- Fix test isolation for test_search_by_tag, test_search_by_query,
  test_search_verified_only, test_get_extension_info
- Update version to 0.1.14 and CHANGELOG
- Update all docs (RFC, User Guide, API Reference)

* fix: wrap _load_catalog_config() calls in catalog_list with try/except

- Check SPECKIT_CATALOG_URL first (matching get_active_catalogs() resolution order)
- Wrap both _load_catalog_config() calls in try/except ValidationError so a
  malformed config file cannot crash `specify extension catalog list` after
  the active catalogs have already been printed successfully

Co-authored-by: mnriem <15701806+mnriem@users.noreply.github.com>

---------

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: mnriem <15701806+mnriem@users.noreply.github.com>
Co-authored-by: Copilot Autofix powered by AI <223894421+github-code-quality[bot]@users.noreply.github.com>
2026-03-09 14:30:27 -05:00
Pavel-tabnine
1df24f1953 Pavel/add tabnine cli support (#1503)
* feat: add Tabnine CLI agent support

Tabnine CLI is a Gemini fork that uses TOML commands with the
.tabnine/agent/ directory structure and TABNINE.md context files.

Changes:
- Add 'tabnine' to AGENT_CONFIG in __init__.py
- Update release scripts (bash + PowerShell) for TOML command generation
- Update agent context scripts (bash + PowerShell)
- Add to GitHub release packages
- Update README.md and AGENTS.md documentation
- Bump version to 0.1.14
- Add 8 new tests for cross-file consistency

* fix: add missing generic to agent-context script usage string
2026-03-09 14:04:02 -05:00
LADISLAV BIHARI
3033834d64 Add Understanding extension to community catalog (#1778)
* Add Understanding extension to community catalog

31 deterministic requirements quality metrics based on IEEE/ISO standards.
Catches ambiguity, missing testability, and structural issues before implementation.
Includes experimental energy-based ambiguity detection.

Repository: https://github.com/Testimonial/understanding
Commands: scan, validate, energy
Hook: after_tasks validation prompt

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* Sort README table and catalog entries alphabetically

Move Understanding extension entry between Spec Sync and V-Model
to maintain alphabetical ordering in both files.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Ladislav Bihari <ladislav.bihari@statsperform.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-09 10:18:41 -05:00
Ben Lawson
4b00078907 Add ralph extension to community catalog (#1780)
- Extension ID: ralph
- Version: 1.0.0
- Author: Rubiss
- Description: Autonomous implementation loop using AI agent CLI
2026-03-09 10:01:34 -05:00
Lautaro Lubatti
2d72f85790 Update README with project initialization instructions (#1772)
* Update README with project initialization instructions

Added instructions for creating a new project and initializing in an existing project.

* Update README.md with alternative one-time usage command for existing projects

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Added --ai option to prevent interactive AI selection

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2026-03-09 09:56:49 -05:00
Ismael
855ac838b8 feat: add review extension to community catalog (#1775)
Add spec-kit-review to catalog.community.json
and the Available Community Extensions table in extensions/README.md.

Co-authored-by: Ismael <ismael.jimenez-martinez@bmw.de>
2026-03-09 09:10:59 -05:00
Sharath Satish
a8ec87e3c2 Add fleet extension to community catalog (#1771)
- Extension ID: fleet
- Version: 1.0.0
- Author: sharathsatish
- Description: Orchestrate a full feature lifecycle with human-in-the-loop gates across all SpecKit phases
2026-03-09 08:13:36 -05:00
Gaël
9d6c05ad5b Integration of Mistral vibe support into speckit (#1725)
* Add Mistral Vibe support to Spec Kit

This commit adds comprehensive support for Mistral Vibe as an AI agent in the
Spec Kit project. The integration includes:

- Added Mistral Vibe to AGENT_CONFIG with proper CLI tool configuration
- Updated README.md with Mistral Vibe in supported agents table and examples
- Modified release package scripts to generate Mistral Vibe templates
- Updated both bash and PowerShell agent context update scripts
- Added appropriate CLI help text and documentation

Mistral Vibe is now fully supported with the same level of integration as
other CLI-based agents like Claude Code, Gemini CLI, etc.

Generated by Mistral Vibe.
Co-Authored-By: Mistral Vibe <vibe@mistral.ai>

* Add Mistral Vibe support to Spec Kit

- Added Mistral Vibe (vibe) to AGENT_CONFIG with proper TOML format support
- Updated CLI help text to include vibe as a valid AI assistant option
- Added Mistral Vibe to release scripts with correct .vibe/agents/ directory structure
- Updated agent context scripts (bash and PowerShell) with proper TOML file paths
- Added Mistral Vibe to README.md supported agents table with v2.0 slash command notes
- Used correct argument syntax {{args}} for Mistral Vibe TOML configurations

Mistral Vibe is now fully integrated with the same level of support as other
CLI-based agents like Gemini and Qwen. Users can now use specify init --ai vibe
to create projects with Mistral Vibe support.

Generated by Mistral Vibe.
Co-Authored-By: Mistral Vibe <vibe@mistral.ai>

* Add Vibe templates to GitHub release script

creation of Mistral vibe zip

* Add 'vibe' agent to release package script

* Add 'vibe' to the list of agents in create-release-packages.sh

* chore: bump version to v1.0.1 [skip ci]

* Add generic spec kit templates to release script

* chore: bump version to v1.0.2 [skip ci]

* Update project version to 0.1.5

* Add generic spec kit templates to release script

* Add 'generic' and 'qodercli' to agent list to be aligned

* Update supported agents in update-agent-context.sh to be aligned

* Update README with new AI assistant options to be aligned

* Document --ai-commands-dir option in README to be aligned

Added new option for AI commands directory in README.

* Fix formatting in README.md for init arguments to be aligned

* Update README with AI assistant options to be aligned

Added AI options to specify init arguments in README.

* Fix formatting in README.md for project-name argument

* Update expected agent types in update-agent-context.sh to be aligned

* Update agent types and usage in update-agent-context.ps1 to be aligned

* Add support for generic AI assistant configuration to be aligned

* Fix formatting in __init__.py clean space

* Update AI assistant options in init command to be aligned

* Add 'qodercli' to expected agent types to be aligned

* Remove 'vibe' case from release package script

Removed the 'vibe' case from the create-release-packages script.

* Update README.md

ok for this

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update .github/workflows/scripts/create-release-packages.ps1

ok to commit

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Add commands_subdir key to Mistral Vibe configuration

* Rename specify-agents.toml to specify-agents.md

* Update scripts/bash/update-agent-context.sh

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update .github/workflows/scripts/create-release-packages.sh

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update src/specify_cli/__init__.py

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update src/specify_cli/__init__.py

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Fix duplicate 'commands_subdir' in vibe configuration

Removed duplicate 'commands_subdir' entries for 'vibe'.

* Add support for 'vibe' command in release script

add an mkdir and generate command

* Change commands_subdir from 'commands' to 'prompts'

* Update README.md

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update update-agent-context.ps1

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update create-release-packages.sh

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update create-release-packages.ps1

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update agent list in update-agent-context.sh

Kiro

---------

Co-authored-by: Lénaïc Huard <lenaic@lhuard.fr>
Co-authored-by: Mistral Vibe <vibe@mistral.ai>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2026-03-09 08:05:13 -05:00
Ryo Hasegawa
3ef12cae3e fix: Remove duplicate options in specify.md (#1765) 2026-03-09 07:38:10 -05:00
Fabián Silva
8618d0a53e fix: use global branch numbering instead of per-short-name detection (#1757)
* fix: remove per-short-name number detection from specify prompt

The specify.md prompt instructed the AI to search for existing branches
filtered by the exact short-name, causing every new feature to start at
001 since no branches matched the new short-name. The underlying
create-new-feature.sh script already has correct global numbering logic
via check_existing_branches() that searches ALL branches and spec
directories.

The fix removes the AI's flawed number-detection steps and tells it to
NOT pass --number, letting the script auto-detect the next globally
available number.

Closes #1744
Closes #1468

🤖 Generated with [Claude Code](https://claude.com/code)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: clarify --json flag requirement per Copilot review

- Rephrased step 2 to mention both --short-name and --json flags
- Added explicit note to always include the JSON flag for reliable output parsing

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-09 07:37:46 -05:00
Copilot
71e6b4da4a Add Community Walkthroughs section to README (#1766)
* Initial plan

* Add Community Walkthroughs section to README.md

Co-authored-by: mnriem <15701806+mnriem@users.noreply.github.com>

---------

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: mnriem <15701806+mnriem@users.noreply.github.com>
2026-03-05 12:55:29 -06:00
Michal Bachorik
ad74334a85 feat(extensions): add Jira Integration to community catalog (#1764)
* feat(extensions): add Jira Integration to community catalog

Adds the spec-kit-jira extension to the community catalog.

## Extension Details
- **Name**: Jira Integration
- **Version**: 2.1.0
- **Repository**: https://github.com/mbachorik/spec-kit-jira

## Features
- Create Jira Epics, Stories, and Issues from spec-kit artifacts
- 3-level hierarchy (Epic → Stories → Tasks) or 2-level mode
- Configurable custom field support
- Status synchronization between local tasks and Jira

## Commands
- `/speckit.jira.specstoissues` - Create Jira hierarchy from spec and tasks
- `/speckit.jira.discover-fields` - Discover Jira custom fields
- `/speckit.jira.sync-status` - Sync task completion to Jira

---
This PR was prepared with the assistance of Claude (Anthropic).

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* fix: address PR review comments

- Set created_at to catalog submission date (2026-03-05)
- Add Jira Integration to Available Community Extensions table in README

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

---------

Co-authored-by: iamaeroplane <michal.bachorik@gmail.com>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
2026-03-05 07:21:38 -06:00
Pragya Chaurasia
8c3982d65b Add Azure DevOps Integration extension to community catalog (#1734)
* Add Azure DevOps work item synchronization with handoffs system

* Resolving the comments

* Added details of Azure DevOps extention

* t status
t revert --abort
Revert "Add Azure DevOps work item synchronization with handoffs system"

This reverts commit 39ac7e48d6.

* Update extensions/README.md

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update extensions/catalog.community.json

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

---------

Co-authored-by: pragya247 <pragya@microsoft.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2026-03-05 07:11:51 -06:00
layla
13dec1de05 Fix docs: update Antigravity link and add initialization example (#1748)
* Fix docs: update Antigravity link and add initialization example

* Update README.md

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

---------

Co-authored-by: Manfred Riem <15701806+mnriem@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2026-03-04 08:29:52 -06:00
Manfred Riem
d0a112c60f fix: wire after_tasks and after_implement hook events into command templates (#1702)
* fix: wire after_tasks and after_implement hook events into command templates (#1701)

The HookExecutor backend in extensions.py was fully implemented but
check_hooks_for_event() was never called by anything — the core command
templates had no instructions to check .specify/extensions.yml.

Add a final step to templates/commands/tasks.md (step 6, after_tasks) and
templates/commands/implement.md (step 10, after_implement) that instructs
the AI agent to:

- Read .specify/extensions.yml if it exists
- Filter hooks.{event} to enabled: true entries
- Evaluate any condition fields and skip non-matching hooks
- Output the RFC-specified hook message format, including
  EXECUTE_COMMAND: markers for mandatory (optional: false) hooks

Bumps version to 0.1.7.

* fix: clarify hook condition handling and add YAML error guidance in templates

- Replace ambiguous "evaluate any condition value" instruction with explicit
  guidance to skip hooks with non-empty conditions, deferring evaluation to
  HookExecutor
- Add instruction to skip hook checking silently if extensions.yml cannot
  be parsed or is invalid

* Fix/extension hooks not triggered (#1)

* feat(templates): implement before-hooks check as pre-execution phase

* test(hooks): create scenario for LLMs/Agents on hooks

---------

Co-authored-by: Dhilip <s.dhilipkumar@gmail.com>
2026-03-04 08:16:31 -06:00
Dhilip
c84756b7f3 make c ignores consistent with c++ (#1747) 2026-03-04 08:08:04 -06:00
Manfred Riem
524affca79 chore: bump version to 0.1.13 (#1746)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2026-03-03 16:08:40 -06:00
Medhat Galal
32c6e7f40c feat: add kiro-cli and AGENT_CONFIG consistency coverage (#1690)
* feat: add kiro-cli and AGENT_CONFIG consistency coverage

* fix: address PR feedback for kiro-cli migration

* test: assert init invocation result in --here mode test

* test: capture init result in here-mode command test

* chore: save local unapproved work in progress

* fix: resolve remaining PR1690 review threads

* Update src/specify_cli/__init__.py

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* test: reduce brittleness in ai help alias assertion

* fix: resolve PR1690 ruff syntax regression

---------

Co-authored-by: Manfred Riem <15701806+mnriem@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2026-03-03 12:04:46 -06:00
Ismael
9cf33e81cc feat: add verify extension to community catalog (#1726)
* feat: add verify extension to community catalog

* Add verify to extension readme

---------

Co-authored-by: Ismael <ismael.jimenez-martinez@bmw.de>
2026-03-03 11:21:06 -06:00
Emi
254e9bbdf0 Add Retrospective Extension to community catalog README table (#1741)
* Add retrospective extension to community catalog.

Register the new retrospective extension release so users can discover and install it from the community catalog.

Co-authored-by: Cursor <cursoragent@cursor.com>

* Add Retrospective Extension to community catalog

---------

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-03-03 09:59:53 -06:00
Zaheer Uddin
6757c90dbd fix(scripts): add empty description validation and branch checkout error handling (#1559)
* fix(scripts): add empty description validation and branch checkout error handling

Adds two critical improvements to both PowerShell and Bash feature creation scripts:

1. Post-trim validation: Prevents creating features with whitespace-only descriptions
2. Branch checkout error handling: Provides clear error messages when branch
   creation fails (e.g., branch already exists) instead of silently continuing

Co-authored-by: Augment Agent <noreply@augmentcode.com>

* fix(scripts): use consistent stderr redirection for branch checkout

---------

Co-authored-by: Augment Agent <noreply@augmentcode.com>
2026-03-03 09:42:46 -06:00
Ismael
f6264d4ef4 fix: correct Copilot extension command registration (#1724)
* fix: correct Copilot extension command registration (#copilot)

- Use .agent.md extension for commands in .github/agents/
- Generate companion .prompt.md files in .github/prompts/
- Clean up .prompt.md files on extension removal
- Add tests for Copilot-specific registration behavior

Bumps version to 0.1.7.

* fix: test copilot prompt cleanup via ExtensionManager.remove() instead of manual unlink

---------

Co-authored-by: Ismael <ismael.jimenez-martinez@bmw.de>
2026-03-03 09:03:38 -06:00
Zaheer Uddin
dd8dbf6344 fix(implement): remove Makefile from C ignore patterns (#1558)
* fix(implement): remove Makefile from C ignore patterns

Makefile is typically source-controlled and should not be in .gitignore.
Replaced with proper autotools-generated files (autom4te.cache/, config.status).

Co-authored-by: Augment Agent <noreply@augmentcode.com>

* fix(implement): restore config.log in C ignore patterns

---------

Co-authored-by: Augment Agent <noreply@augmentcode.com>
2026-03-03 08:28:40 -06:00
Barry Gervin
bf8fb125ad Add sync extension to community catalog (#1728)
* Add sync extension to community catalog

- Extension ID: sync
- Version: 0.1.0
- Author: bgervin
- Description: Detect and resolve drift between specs and implementation

* fix: use main branch in URLs per Copilot review

* Reorder community extensions table alphabetically

Per Copilot review feedback and EXTENSION-PUBLISHING-GUIDE.md

---------

Co-authored-by: Barry Gervin <bgervin@hotmail.com>
2026-03-03 08:18:18 -06:00
Zaheer Uddin
2b92ab444d fix(checklist): clarify file handling behavior for append vs create (#1556)
* fix(checklist): clarify file handling behavior for append vs create

Resolves contradictory instructions in checklist.md lines 97-99 where the
template stated both 'append to existing file' and 'creates a NEW file'.

Changes:
- Clarified that if file doesn't exist, create new with CHK001
- If file exists, append new items continuing from last CHK ID
- Emphasized preservation of existing content (never delete/replace)

Co-authored-by: Augment Agent <noreply@augmentcode.com>

* fix(checklist): align report language with append behavior

---------

Co-authored-by: Augment Agent <noreply@augmentcode.com>
2026-03-03 07:52:02 -06:00
Zaheer Uddin
abe1b7085c fix(clarify): correct conflicting question limit from 10 to 5 (#1557)
Resolves inconsistency where line 92 stated 'Maximum of 10 total questions'
while all other references (lines 2, 91, 100, 134, 158, 178) consistently
specify a maximum of 5 questions.

Co-authored-by: Augment Agent <noreply@augmentcode.com>
2026-03-03 07:46:31 -06:00
Manfred Riem
bfaca2c449 chore: bump version to 0.1.12 (#1737)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2026-03-02 13:35:43 -06:00
Manfred Riem
78ed453e38 fix: use RELEASE_PAT so tag push triggers release workflow (#1736) 2026-03-02 13:31:18 -06:00
Manfred Riem
658ab2a38c fix: release-trigger uses release branch + PR instead of direct push to main (#1733)
* fix: use release branch + PR instead of direct push to main

Bypass branch protection rules by pushing version bump to a
chore/release-vX.Y.Z branch, tagging that commit, then opening
an auto PR to merge back into main. The release workflow still
triggers immediately from the tag push.

* fix: remove --label automated from gh pr create (label does not exist)
2026-03-02 13:16:13 -06:00
Manfred Riem
2c41d3627e fix: Split release process to sync pyproject.toml version with git tags (#1732)
* fix: split release process to sync pyproject.toml version with git tags (#1721)

- Split release workflow into two: release-trigger.yml and release.yml
- release-trigger.yml: Updates pyproject.toml, generates changelog from commits, creates tag
- release.yml: Triggered by tag push, builds artifacts, creates GitHub release
- Ensures git tags point to commits with correct version in pyproject.toml
- Auto-generates changelog from commit messages since last tag
- Supports manual version input or auto-increment patch version
- Added simulate-release.sh for local testing without pushing
- Added comprehensive RELEASE-PROCESS.md documentation
- Updated pyproject.toml to v0.1.10 to sync with latest release

This fixes the version mismatch issue where tags pointed to commits with
outdated pyproject.toml versions, preventing confusion when installing from source.

* Update .github/workflows/RELEASE-PROCESS.md

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update .github/workflows/scripts/simulate-release.sh

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update .github/workflows/release.yml

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update .github/workflows/release-trigger.yml

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* fix: harden release-trigger against shell injection and fix stale docs

- Pass workflow_dispatch version input via env: instead of direct
  interpolation into shell script, preventing potential injection attacks
- Validate version input against strict semver regex before use
- Fix RELEASE-PROCESS.md Option 2 still referencing [Unreleased] section
  handling that no longer exists in the workflow

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2026-03-02 12:52:13 -06:00
Fabián Silva
b55d00beed fix: prepend YAML frontmatter to Cursor .mdc files (#1699)
* fix: prepend YAML frontmatter to Cursor .mdc files for auto-inclusion

Cursor IDE requires YAML frontmatter with `alwaysApply: true` in .mdc
rule files for them to be automatically loaded. Without this frontmatter,
users must manually configure glob patterns for the rules to take effect.

This fix adds frontmatter generation to both the bash and PowerShell
update-agent-context scripts, handling three scenarios:
- New .mdc file creation (frontmatter prepended after template processing)
- Existing .mdc file update without frontmatter (frontmatter added)
- Existing .mdc file with frontmatter (no duplication)

Closes #669

🤖 Generated with [Claude Code](https://claude.com/code)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* refactor: address Copilot review suggestions

- Handle CRLF line endings in frontmatter detection (grep '^---' instead
  of '^---$')
- Fix double blank line after frontmatter in PowerShell New-AgentFile
- Remove unused tempfile import from tests
- Add encoding="utf-8" to all open() calls for cross-platform safety

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-27 08:20:00 -06:00
dependabot[bot]
525eae7f7e chore(deps): bump astral-sh/setup-uv from 6 to 7 (#1709)
Bumps [astral-sh/setup-uv](https://github.com/astral-sh/setup-uv) from 6 to 7.
- [Release notes](https://github.com/astral-sh/setup-uv/releases)
- [Commits](https://github.com/astral-sh/setup-uv/compare/v6...v7)

---
updated-dependencies:
- dependency-name: astral-sh/setup-uv
  dependency-version: '7'
  dependency-type: direct:production
  update-type: version-update:semver-major
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2026-02-27 08:09:43 -06:00
dependabot[bot]
ce7bed4823 chore(deps): bump actions/setup-python from 5 to 6 (#1710)
Bumps [actions/setup-python](https://github.com/actions/setup-python) from 5 to 6.
- [Release notes](https://github.com/actions/setup-python/releases)
- [Commits](https://github.com/actions/setup-python/compare/v5...v6)

---
updated-dependencies:
- dependency-name: actions/setup-python
  dependency-version: '6'
  dependency-type: direct:production
  update-type: version-update:semver-major
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2026-02-27 08:07:19 -06:00
Manfred Riem
61b0637a6d chore: Update outdated GitHub Actions versions (#1706)
Co-authored-by: Padraic Slattery <pgoslatara@gmail.com>
2026-02-26 14:43:22 -06:00
Manfred Riem
56deda7be3 docs: Document dual-catalog system for extensions (#1689)
* docs: Document dual-catalog system for extensions

- Clarify distinction between catalog.json (curated) and catalog.community.json (reference)
- Update EXTENSION-DEVELOPMENT-GUIDE.md to explain community catalog submission
- Update EXTENSION-PUBLISHING-GUIDE.md with dual-catalog workflow
- Update EXTENSION-USER-GUIDE.md with catalog selection guidance
- Expand README.md with comprehensive catalog explanation
- Update RFC-EXTENSION-SYSTEM.md with dual-catalog design and current implementation
- Change GitHub references from statsperform to github
- Add SPECKIT_CATALOG_URL environment variable documentation

This clarifies how organizations can curate their own catalog while
browsing community-contributed extensions for discovery.

* Update extensions/README.md

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update extensions/README.md

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update extensions/README.md

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2026-02-25 14:38:56 -06:00
Santosh Bhavani
525cdc17ec Fix version command in documentation (#1685)
Co-authored-by: Santosh Bhavani <sb@mac-mini-i7.local>
2026-02-25 08:20:18 -06:00
dsrednicki
607760e72f Add Cleanup Extension to README (#1678) 2026-02-24 15:50:04 -06:00
Emi
c7ecdfb998 Add retrospective extension to community catalog. (#1681)
Register the new retrospective extension release so users can discover and install it from the community catalog.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-02-24 13:56:03 -06:00
dsrednicki
f444ccba3a Add Cleanup Extension to catalog (#1617)
**Repository**: https://github.com/dsrednicki/spec-kit-cleanup
**Version**: 1.0.0
**License**: MIT
**Author**: @dsrednicki

Adds catalog entry for the Cleanup Extension - a post-implementation
quality gate that fixes small issues (scout rule), creates tasks for
medium issues, and generates analysis for large issues.
2026-02-23 13:52:40 -06:00
Manfred Riem
3040d33c31 Fix parameter ordering issues in CLI (#1669)
* chore: bump version to v0.0.6 [skip ci]

* Fix parameter ordering issues in CLI (#1641)

- Add validation to detect when option flags are consumed as values
- Provide clear error messages with helpful hints and examples
- Add 5 comprehensive tests to prevent regressions
- Update CODEOWNERS to @mnriem
- Bump version to 0.1.6 with changelog entry

Fixes: #1641

* Fix ruff linting errors: remove f-string prefix from strings without placeholders

---------

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2026-02-23 13:17:08 -06:00
Leonardo Nascimento
6cc61025cb Update V-Model Extension Pack to v0.4.0 (#1665)
- Version: 0.2.0 → 0.4.0
- Commands: 5 → 9 (new: architecture-design, integration-test, module-design, unit-test)
- Download URL: updated to v0.4.0 tag
2026-02-23 13:14:02 -06:00
Emi
c1034f1d9d docs: Fix doc missing step (#1496)
* docs: Fix doc missing step

* docs: Update steps for generating technical plan and defining tasks
2026-02-23 11:40:41 -06:00
Leonardo Nascimento
cee4f26fac Update V-Model Extension Pack to v0.3.0 (#1661)
- Version: 0.2.0 → 0.3.0
- Commands: 5 → 7 (architecture-design, integration-test)
- Download URL updated to v0.3.0 tag
2026-02-23 09:02:24 -06:00
Manfred Riem
6f523ede22 Fix #1658: Add commands_subdir field to support non-standard agent directory structures (#1660)
- Added commands_subdir field to AGENT_CONFIG for all agents
- Updated install_ai_skills() to use commands_subdir instead of hardcoded 'commands'
- Fixed --ai-skills flag for copilot, opencode, windsurf, codex, kilocode, q, and agy
- Bumped version to 0.1.5
- Updated AGENTS.md documentation with new field

Affected agents now correctly locate their command templates:
- copilot: .github/agents/
- opencode: .opencode/command/ (singular)
- windsurf: .windsurf/workflows/
- codex: .codex/prompts/
- kilocode: .kilocode/workflows/
- q: .amazonq/prompts/
- agy: .agent/workflows/

All 51 tests pass.
2026-02-21 08:05:58 -06:00
Manfred Riem
68d1d3a0fc feat: add GitHub issue templates (#1655)
* feat: add issue templates for agent requests, bug reports, feature requests, extension submissions, and configuration

* Update .github/ISSUE_TEMPLATE/config.yml

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update .github/ISSUE_TEMPLATE/agent_request.yml

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update .github/ISSUE_TEMPLATE/config.yml

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update .github/ISSUE_TEMPLATE/bug_report.yml

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update .github/ISSUE_TEMPLATE/feature_request.yml

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2026-02-20 17:35:48 -06:00
Leonardo Nascimento
07077d0fc2 Update V-Model Extension Pack to v0.2.0 in community catalog (#1656)
- Version: 0.1.0 → 0.2.0
- Download URL updated to v0.2.0 tag
- Commands: 3 → 5 (added system-design, system-test)
2026-02-20 17:29:58 -06:00
Leonardo Nascimento
aeed11f735 Add V-Model Extension Pack to catalog (#1640)
* Add V-Model Extension Pack to catalog

Second community extension: V-Model paired dev-spec and test-spec
generation with regulatory-grade traceability.

- 3 commands: requirements, acceptance, trace
- Deterministic coverage validation (regex-based, not AI)
- Targets: IEC 62304, ISO 26262, DO-178C, FDA 21 CFR Part 820
- Repository: https://github.com/leocamello/spec-kit-v-model
- Release: v0.1.0

* Fix catalog entry: provides as number, add timestamps and statistics

Address review feedback:
- provides.commands: array → number (3), add hooks (1)
- Add created_at and updated_at timestamps
- Add statistics block (downloads: 0, stars: 0)

* Address review: use catalog.community.json and add extensions README

Per maintainer feedback:
- Revert catalog.json to its original empty state (empty by design)
- Rename catalog.example.json → catalog.community.json
- Replace example entries with real V-Model Extension Pack entry
- Add extensions/README.md with community extensions table
2026-02-20 15:11:51 -06:00
Manfred Riem
12405c01e1 refactor: remove OpenAPI/GraphQL bias from templates (#1652)
* chore: bump version to v0.0.5 [skip ci]

* refactor: update documentation for interface contracts and integration patterns

* Update pyproject.toml

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update templates/commands/tasks.md

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update templates/commands/tasks.md

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

---------

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2026-02-20 14:46:56 -06:00
Manfred Riem
fc3b98ea09 fix: rename Qoder AGENT_CONFIG key from 'qoder' to 'qodercli' to match actual CLI executable (#1651)
* fix: rename Qoder CLI to QoderCLI across scripts and documentation

* Apply suggestion from @Copilot

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Apply suggestion from @Copilot

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update .github/workflows/scripts/create-release-packages.ps1

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2026-02-20 13:30:16 -06:00
Manfred Riem
6150f1e317 Add generic agent support with customizable command directories (#1639)
- Add --ai generic option for unsupported AI agents (bring your own agent)
- Require --ai-commands-dir to specify where agent reads commands from
- Generate Markdown commands with $ARGUMENTS format (compatible with most agents)
- Rebuild CHANGELOG from GitHub releases (last 10 releases)
- Align version to 0.1.3

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-02-20 11:05:38 -06:00
79 changed files with 10473 additions and 982 deletions

View File

@@ -50,8 +50,6 @@
"kilocode.Kilo-Code",
// Roo Code
"RooVeterinaryInc.roo-cline",
// Amazon Developer Q
"AmazonWebServices.amazon-q-vscode",
// Claude Code
"anthropic.claude-code"
],

View File

@@ -51,32 +51,33 @@ echo -e "\n🤖 Installing OpenCode CLI..."
run_command "npm install -g opencode-ai@latest"
echo "✅ Done"
echo -e "\n🤖 Installing Amazon Q CLI..."
# 👉🏾 https://docs.aws.amazon.com/amazonq/latest/qdeveloper-ug/command-line-verify-download.html
echo -e "\n🤖 Installing Kiro CLI..."
# https://kiro.dev/docs/cli/
KIRO_INSTALLER_URL="https://cli.kiro.dev/install"
KIRO_INSTALLER_SHA256="7487a65cf310b7fb59b357c4b5e6e3f3259d383f4394ecedb39acf70f307cffb"
KIRO_INSTALLER_PATH="$(mktemp)"
run_command "curl --proto '=https' --tlsv1.2 -sSf 'https://desktop-release.q.us-east-1.amazonaws.com/latest/q-x86_64-linux.zip' -o 'q.zip'"
run_command "curl --proto '=https' --tlsv1.2 -sSf 'https://desktop-release.q.us-east-1.amazonaws.com/latest/q-x86_64-linux.zip.sig' -o 'q.zip.sig'"
cat > amazonq-public-key.asc << 'EOF'
-----BEGIN PGP PUBLIC KEY BLOCK-----
cleanup_kiro_installer() {
rm -f "$KIRO_INSTALLER_PATH"
}
trap cleanup_kiro_installer EXIT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=f8yY
-----END PGP PUBLIC KEY BLOCK-----
EOF
run_command "gpg --batch --import amazonq-public-key.asc"
run_command "gpg --verify q.zip.sig q.zip"
run_command "unzip -q q.zip"
run_command "chmod +x ./q/install.sh"
run_command "./q/install.sh --no-confirm"
run_command "rm -rf ./q q.zip q.zip.sig amazonq-public-key.asc"
run_command "curl -fsSL \"$KIRO_INSTALLER_URL\" -o \"$KIRO_INSTALLER_PATH\""
run_command "echo \"$KIRO_INSTALLER_SHA256 $KIRO_INSTALLER_PATH\" | sha256sum -c -"
run_command "bash \"$KIRO_INSTALLER_PATH\""
kiro_binary=""
if command -v kiro-cli >/dev/null 2>&1; then
kiro_binary="kiro-cli"
elif command -v kiro >/dev/null 2>&1; then
kiro_binary="kiro"
else
echo -e "\033[0;31m[ERROR] Kiro CLI installation did not create 'kiro-cli' or 'kiro' in PATH.\033[0m" >&2
exit 1
fi
run_command "$kiro_binary --help > /dev/null"
echo "✅ Done"
echo -e "\n🤖 Installing CodeBuddy CLI..."

2
.github/CODEOWNERS vendored
View File

@@ -1,3 +1,3 @@
# Global code owner
* @localden
* @mnriem

141
.github/ISSUE_TEMPLATE/agent_request.yml vendored Normal file
View File

@@ -0,0 +1,141 @@
name: Agent Request
description: Request support for a new AI agent/assistant in Spec Kit
title: "[Agent]: Add support for "
labels: ["agent-request", "enhancement", "needs-triage"]
body:
- type: markdown
attributes:
value: |
Thanks for requesting a new agent! Before submitting, please check if the agent is already supported.
**Currently supported agents**: Claude Code, Gemini CLI, GitHub Copilot, Cursor, Qwen Code, opencode, Codex CLI, Windsurf, Kilo Code, Auggie CLI, Roo Code, CodeBuddy, Qoder CLI, Kiro CLI, Amp, SHAI, IBM Bob, Antigravity
- type: input
id: agent-name
attributes:
label: Agent Name
description: What is the name of the AI agent/assistant?
placeholder: "e.g., SuperCoder AI"
validations:
required: true
- type: input
id: website
attributes:
label: Official Website
description: Link to the agent's official website or documentation
placeholder: "https://..."
validations:
required: true
- type: dropdown
id: agent-type
attributes:
label: Agent Type
description: How is the agent accessed?
options:
- CLI tool (command-line interface)
- IDE extension/plugin
- Both CLI and IDE
- Other
validations:
required: true
- type: input
id: cli-command
attributes:
label: CLI Command (if applicable)
description: What command is used to invoke the agent from terminal?
placeholder: "e.g., supercode, ai-assistant"
- type: input
id: install-method
attributes:
label: Installation Method
description: How is the agent installed?
placeholder: "e.g., npm install -g supercode, pip install supercode, IDE marketplace"
validations:
required: true
- type: textarea
id: command-structure
attributes:
label: Command/Workflow Structure
description: How does the agent define custom commands or workflows?
placeholder: |
- Command file format (Markdown, YAML, TOML, etc.)
- Directory location (e.g., .supercode/commands/)
- Example command file structure
validations:
required: true
- type: textarea
id: argument-pattern
attributes:
label: Argument Passing Pattern
description: How does the agent handle arguments in commands?
placeholder: |
e.g., Uses {{args}}, $ARGUMENTS, %ARGS%, or other placeholder format
Example: "Run test suite with {{args}}"
- type: dropdown
id: popularity
attributes:
label: Popularity/Usage
description: How widely is this agent used?
options:
- Widely used (thousands+ of users)
- Growing adoption (hundreds of users)
- New/emerging (less than 100 users)
- Unknown
validations:
required: true
- type: textarea
id: documentation
attributes:
label: Documentation Links
description: Links to relevant documentation for custom commands/workflows
placeholder: |
- Command documentation: https://...
- API/CLI reference: https://...
- Examples: https://...
- type: textarea
id: use-case
attributes:
label: Use Case
description: Why do you want this agent supported in Spec Kit?
placeholder: Explain your workflow and how this agent fits into your development process
validations:
required: true
- type: textarea
id: example-command
attributes:
label: Example Command File
description: If possible, provide an example of a command file for this agent
render: markdown
placeholder: |
```toml
description = "Example command"
prompt = "Do something with {{args}}"
```
- type: checkboxes
id: contribution
attributes:
label: Contribution
description: Are you willing to help implement support for this agent?
options:
- label: I can help test the integration
- label: I can provide example command files
- label: I can help with documentation
- label: I can submit a pull request for the integration
- type: textarea
id: context
attributes:
label: Additional Context
description: Any other relevant information about this agent
placeholder: Screenshots, community links, comparison to existing agents, etc.

118
.github/ISSUE_TEMPLATE/bug_report.yml vendored Normal file
View File

@@ -0,0 +1,118 @@
name: Bug Report
description: Report a bug or unexpected behavior in Specify CLI or Spec Kit
title: "[Bug]: "
labels: ["bug", "needs-triage"]
body:
- type: markdown
attributes:
value: |
Thanks for taking the time to report a bug! Please fill out the sections below to help us diagnose and fix the issue.
- type: textarea
id: description
attributes:
label: Bug Description
description: A clear and concise description of what the bug is.
placeholder: What went wrong?
validations:
required: true
- type: textarea
id: reproduce
attributes:
label: Steps to Reproduce
description: Steps to reproduce the behavior
placeholder: |
1. Run command '...'
2. Execute script '...'
3. See error
validations:
required: true
- type: textarea
id: expected
attributes:
label: Expected Behavior
description: What did you expect to happen?
placeholder: Describe the expected outcome
validations:
required: true
- type: textarea
id: actual
attributes:
label: Actual Behavior
description: What actually happened?
placeholder: Describe what happened instead
validations:
required: true
- type: input
id: version
attributes:
label: Specify CLI Version
description: "Run `specify version` or `pip show spec-kit`"
placeholder: "e.g., 1.3.0"
validations:
required: true
- type: dropdown
id: ai-agent
attributes:
label: AI Agent
description: Which AI agent are you using?
options:
- Claude Code
- Gemini CLI
- GitHub Copilot
- Cursor
- Qwen Code
- opencode
- Codex CLI
- Windsurf
- Kilo Code
- Auggie CLI
- Roo Code
- CodeBuddy
- Qoder CLI
- Kiro CLI
- Amp
- SHAI
- IBM Bob
- Antigravity
- Not applicable
validations:
required: true
- type: input
id: os
attributes:
label: Operating System
description: Your operating system and version
placeholder: "e.g., macOS 14.2, Ubuntu 22.04, Windows 11"
validations:
required: true
- type: input
id: python
attributes:
label: Python Version
description: "Run `python --version` or `python3 --version`"
placeholder: "e.g., Python 3.11.5"
validations:
required: true
- type: textarea
id: logs
attributes:
label: Error Logs
description: Please paste any relevant error messages or logs
render: shell
placeholder: Paste error output here
- type: textarea
id: context
attributes:
label: Additional Context
description: Add any other context about the problem
placeholder: Screenshots, related issues, workarounds attempted, etc.

17
.github/ISSUE_TEMPLATE/config.yml vendored Normal file
View File

@@ -0,0 +1,17 @@
blank_issues_enabled: false
contact_links:
- name: 💬 General Discussion
url: https://github.com/github/spec-kit/discussions
about: Ask questions, share ideas, or discuss Spec-Driven Development
- name: 📖 Documentation
url: https://github.com/github/spec-kit/blob/main/README.md
about: Read the Spec Kit documentation and guides
- name: 🛠️ Extension Development Guide
url: https://github.com/manfredseee/spec-kit/blob/main/extensions/EXTENSION-DEVELOPMENT-GUIDE.md
about: Learn how to develop and publish Spec Kit extensions
- name: 🤝 Contributing Guide
url: https://github.com/github/spec-kit/blob/main/CONTRIBUTING.md
about: Learn how to contribute to Spec Kit
- name: 🔒 Security Issues
url: https://github.com/github/spec-kit/blob/main/SECURITY.md
about: Report security vulnerabilities privately

View File

@@ -0,0 +1,280 @@
name: Extension Submission
description: Submit your extension to the Spec Kit catalog
title: "[Extension]: Add "
labels: ["extension-submission", "enhancement", "needs-triage"]
body:
- type: markdown
attributes:
value: |
Thanks for contributing an extension! This template helps you submit your extension to the community catalog.
**Before submitting:**
- Review the [Extension Publishing Guide](https://github.com/github/spec-kit/blob/main/extensions/EXTENSION-PUBLISHING-GUIDE.md)
- Ensure your extension has a valid `extension.yml` manifest
- Create a GitHub release with a version tag (e.g., v1.0.0)
- Test installation: `specify extension add --from <your-release-url>`
- type: input
id: extension-id
attributes:
label: Extension ID
description: Unique extension identifier (lowercase with hyphens only)
placeholder: "e.g., jira-integration"
validations:
required: true
- type: input
id: extension-name
attributes:
label: Extension Name
description: Human-readable extension name
placeholder: "e.g., Jira Integration"
validations:
required: true
- type: input
id: version
attributes:
label: Version
description: Semantic version number
placeholder: "e.g., 1.0.0"
validations:
required: true
- type: textarea
id: description
attributes:
label: Description
description: Brief description of what your extension does (under 200 characters)
placeholder: Integrates Jira issue tracking with Spec Kit workflows for seamless task management
validations:
required: true
- type: input
id: author
attributes:
label: Author
description: Your name or organization
placeholder: "e.g., John Doe or Acme Corp"
validations:
required: true
- type: input
id: repository
attributes:
label: Repository URL
description: GitHub repository URL for your extension
placeholder: "https://github.com/your-org/spec-kit-your-extension"
validations:
required: true
- type: input
id: download-url
attributes:
label: Download URL
description: URL to the GitHub release archive (e.g., v1.0.0.zip)
placeholder: "https://github.com/your-org/spec-kit-your-extension/archive/refs/tags/v1.0.0.zip"
validations:
required: true
- type: input
id: license
attributes:
label: License
description: Open source license type
placeholder: "e.g., MIT, Apache-2.0"
validations:
required: true
- type: input
id: homepage
attributes:
label: Homepage (optional)
description: Link to extension homepage or documentation site
placeholder: "https://..."
- type: input
id: documentation
attributes:
label: Documentation URL (optional)
description: Link to detailed documentation
placeholder: "https://github.com/your-org/spec-kit-your-extension/blob/main/docs/"
- type: input
id: changelog
attributes:
label: Changelog URL (optional)
description: Link to changelog file
placeholder: "https://github.com/your-org/spec-kit-your-extension/blob/main/CHANGELOG.md"
- type: input
id: speckit-version
attributes:
label: Required Spec Kit Version
description: Minimum Spec Kit version required
placeholder: "e.g., >=0.1.0"
validations:
required: true
- type: textarea
id: required-tools
attributes:
label: Required Tools (optional)
description: List any external tools or dependencies required
placeholder: |
- jira-cli (>=1.0.0) - required
- python (>=3.8) - optional
render: markdown
- type: input
id: commands-count
attributes:
label: Number of Commands
description: How many commands does your extension provide?
placeholder: "e.g., 3"
validations:
required: true
- type: input
id: hooks-count
attributes:
label: Number of Hooks (optional)
description: How many hooks does your extension provide?
placeholder: "e.g., 0"
- type: textarea
id: tags
attributes:
label: Tags
description: 2-5 relevant tags (lowercase, separated by commas)
placeholder: "issue-tracking, jira, atlassian, automation"
validations:
required: true
- type: textarea
id: features
attributes:
label: Key Features
description: List the main features and capabilities of your extension
placeholder: |
- Create Jira issues from specs
- Sync task status with Jira
- Link specs to existing issues
- Generate Jira reports
validations:
required: true
- type: checkboxes
id: testing
attributes:
label: Testing Checklist
description: Confirm that your extension has been tested
options:
- label: Extension installs successfully via download URL
required: true
- label: All commands execute without errors
required: true
- label: Documentation is complete and accurate
required: true
- label: No security vulnerabilities identified
required: true
- label: Tested on at least one real project
required: true
- type: checkboxes
id: requirements
attributes:
label: Submission Requirements
description: Verify your extension meets all requirements
options:
- label: Valid `extension.yml` manifest included
required: true
- label: README.md with installation and usage instructions
required: true
- label: LICENSE file included
required: true
- label: GitHub release created with version tag
required: true
- label: All command files exist and are properly formatted
required: true
- label: Extension ID follows naming conventions (lowercase-with-hyphens)
required: true
- type: textarea
id: testing-details
attributes:
label: Testing Details
description: Describe how you tested your extension
placeholder: |
**Tested on:**
- macOS 14.0 with Spec Kit v0.1.0
- Linux Ubuntu 22.04 with Spec Kit v0.1.0
**Test project:** [Link or description]
**Test scenarios:**
1. Installed extension
2. Configured settings
3. Ran all commands
4. Verified outputs
validations:
required: true
- type: textarea
id: example-usage
attributes:
label: Example Usage
description: Provide a simple example of using your extension
render: markdown
placeholder: |
```bash
# Install extension
specify extension add --from https://github.com/your-org/spec-kit-your-extension/archive/refs/tags/v1.0.0.zip
# Use a command
/speckit.your-extension.command-name arg1 arg2
```
validations:
required: true
- type: textarea
id: catalog-entry
attributes:
label: Proposed Catalog Entry
description: Provide the JSON entry for catalog.json (helps reviewers)
render: json
placeholder: |
{
"your-extension": {
"name": "Your Extension",
"id": "your-extension",
"description": "Brief description",
"author": "Your Name",
"version": "1.0.0",
"download_url": "https://github.com/your-org/spec-kit-your-extension/archive/refs/tags/v1.0.0.zip",
"repository": "https://github.com/your-org/spec-kit-your-extension",
"homepage": "https://github.com/your-org/spec-kit-your-extension",
"license": "MIT",
"requires": {
"speckit_version": ">=0.1.0"
},
"provides": {
"commands": 3
},
"tags": ["category", "tool"],
"verified": false,
"downloads": 0,
"stars": 0,
"created_at": "2026-02-20T00:00:00Z",
"updated_at": "2026-02-20T00:00:00Z"
}
}
validations:
required: true
- type: textarea
id: additional-context
attributes:
label: Additional Context
description: Any other information that would help reviewers
placeholder: Screenshots, demo videos, links to related projects, etc.

View File

@@ -0,0 +1,104 @@
name: Feature Request
description: Suggest a new feature or enhancement for Specify CLI or Spec Kit
title: "[Feature]: "
labels: ["enhancement", "needs-triage"]
body:
- type: markdown
attributes:
value: |
Thanks for suggesting a feature! Please provide details below to help us understand and evaluate your request.
- type: textarea
id: problem
attributes:
label: Problem Statement
description: Is your feature request related to a problem? Please describe.
placeholder: "I'm frustrated when..."
validations:
required: true
- type: textarea
id: solution
attributes:
label: Proposed Solution
description: Describe the solution you'd like
placeholder: What would you like to happen?
validations:
required: true
- type: textarea
id: alternatives
attributes:
label: Alternatives Considered
description: Have you considered any alternative solutions or workarounds?
placeholder: What other approaches might work?
- type: dropdown
id: component
attributes:
label: Component
description: Which component does this feature relate to?
options:
- Specify CLI (initialization, commands)
- Spec templates (BDD, Testing Strategy, etc.)
- Agent integrations (command files, workflows)
- Scripts (Bash/PowerShell utilities)
- Documentation
- CI/CD workflows
- Other
validations:
required: true
- type: dropdown
id: ai-agent
attributes:
label: AI Agent (if applicable)
description: Does this feature relate to a specific AI agent?
options:
- All agents
- Claude Code
- Gemini CLI
- GitHub Copilot
- Cursor
- Qwen Code
- opencode
- Codex CLI
- Windsurf
- Kilo Code
- Auggie CLI
- Roo Code
- CodeBuddy
- Qoder CLI
- Kiro CLI
- Amp
- SHAI
- IBM Bob
- Antigravity
- Not applicable
- type: textarea
id: use-cases
attributes:
label: Use Cases
description: Describe specific use cases where this feature would be valuable
placeholder: |
1. When working on large projects...
2. During spec review...
3. When integrating with CI/CD...
- type: textarea
id: acceptance
attributes:
label: Acceptance Criteria
description: How would you know this feature is complete and working?
placeholder: |
- [ ] Feature does X
- [ ] Documentation is updated
- [ ] Works with all supported agents
- type: textarea
id: context
attributes:
label: Additional Context
description: Add any other context, screenshots, or examples
placeholder: Links to similar features, mockups, related discussions, etc.

191
.github/workflows/RELEASE-PROCESS.md vendored Normal file
View File

@@ -0,0 +1,191 @@
# Release Process
This document describes the automated release process for Spec Kit.
## Overview
The release process is split into two workflows to ensure version consistency:
1. **Release Trigger Workflow** (`release-trigger.yml`) - Manages versioning and triggers release
2. **Release Workflow** (`release.yml`) - Builds and publishes artifacts
This separation ensures that git tags always point to commits with the correct version in `pyproject.toml`.
## Before Creating a Release
**Important**: Write clear, descriptive commit messages!
### How CHANGELOG.md Works
The CHANGELOG is **automatically generated** from your git commit messages:
1. **During Development**: Write clear, descriptive commit messages:
```bash
git commit -m "feat: Add new authentication feature"
git commit -m "fix: Resolve timeout issue in API client (#123)"
git commit -m "docs: Update installation instructions"
```
2. **When Releasing**: The release trigger workflow automatically:
- Finds all commits since the last release tag
- Formats them as changelog entries
- Inserts them into CHANGELOG.md
- Commits the updated changelog before creating the new tag
### Commit Message Best Practices
Good commit messages make good changelogs:
- **Be descriptive**: "Add user authentication" not "Update files"
- **Reference issues/PRs**: Include `(#123)` for automated linking
- **Use conventional commits** (optional): `feat:`, `fix:`, `docs:`, `chore:`
- **Keep it concise**: One line is ideal, details go in commit body
**Example commits that become good changelog entries:**
```
fix: prepend YAML frontmatter to Cursor .mdc files (#1699)
feat: add generic agent support with customizable command directories (#1639)
docs: document dual-catalog system for extensions (#1689)
```
## Creating a Release
### Option 1: Auto-Increment (Recommended for patches)
1. Go to **Actions** → **Release Trigger**
2. Click **Run workflow**
3. Leave the version field **empty**
4. Click **Run workflow**
The workflow will:
- Auto-increment the patch version (e.g., `0.1.10` → `0.1.11`)
- Update `pyproject.toml`
- Update `CHANGELOG.md` by adding a new section for the release based on commits since the last tag
- Commit changes to a `chore/release-vX.Y.Z` branch
- Create and push the git tag from that branch
- Open a PR to merge the version bump into `main`
- Trigger the release workflow automatically via the tag push
### Option 2: Manual Version (For major/minor bumps)
1. Go to **Actions** → **Release Trigger**
2. Click **Run workflow**
3. Enter the desired version (e.g., `0.2.0` or `v0.2.0`)
4. Click **Run workflow**
The workflow will:
- Use your specified version
- Update `pyproject.toml`
- Update `CHANGELOG.md` by adding a new section for the release based on commits since the last tag
- Commit changes to a `chore/release-vX.Y.Z` branch
- Create and push the git tag from that branch
- Open a PR to merge the version bump into `main`
- Trigger the release workflow automatically via the tag push
## What Happens Next
Once the release trigger workflow completes:
1. A `chore/release-vX.Y.Z` branch is pushed with the version bump commit
2. The git tag is pushed, pointing to that commit
3. The **Release Workflow** is automatically triggered by the tag push
4. Release artifacts are built for all supported agents
5. A GitHub Release is created with all assets
6. A PR is opened to merge the version bump branch into `main`
> **Note**: Merge the auto-opened PR after the release is published to keep `main` in sync.
## Workflow Details
### Release Trigger Workflow
**File**: `.github/workflows/release-trigger.yml`
**Trigger**: Manual (`workflow_dispatch`)
**Permissions Required**: `contents: write`
**Steps**:
1. Checkout repository
2. Determine version (manual or auto-increment)
3. Check if tag already exists (prevents duplicates)
4. Create `chore/release-vX.Y.Z` branch
5. Update `pyproject.toml`
6. Update `CHANGELOG.md` from git commits
7. Commit changes
8. Push branch and tag
9. Open PR to merge version bump into `main`
### Release Workflow
**File**: `.github/workflows/release.yml`
**Trigger**: Tag push (`v*`)
**Permissions Required**: `contents: write`
**Steps**:
1. Checkout repository at tag
2. Extract version from tag name
3. Check if release already exists
4. Build release package variants (all agents × shell/powershell)
5. Generate release notes from commits
6. Create GitHub Release with all assets
## Version Constraints
- Tags must follow format: `v{MAJOR}.{MINOR}.{PATCH}`
- Example valid versions: `v0.1.11`, `v0.2.0`, `v1.0.0`
- Auto-increment only bumps patch version
- Cannot create duplicate tags (workflow will fail)
## Benefits of This Approach
✅ **Version Consistency**: Git tags point to commits with matching `pyproject.toml` version
✅ **Single Source of Truth**: Version set once, used everywhere
✅ **Prevents Drift**: No more manual version synchronization needed
✅ **Clean Separation**: Versioning logic separate from artifact building
✅ **Flexibility**: Supports both auto-increment and manual versioning
## Troubleshooting
### No Commits Since Last Release
If you run the release trigger workflow when there are no new commits since the last tag:
- The workflow will still succeed
- The CHANGELOG will show "- Initial release" if it's the first release
- Or it will be empty if there are no commits
- Consider adding meaningful commits before releasing
**Best Practice**: Use descriptive commit messages - they become your changelog!
### Tag Already Exists
If you see "Error: Tag vX.Y.Z already exists!", you need to:
- Choose a different version number, or
- Delete the existing tag if it was created in error
### Release Workflow Didn't Trigger
Check that:
- The release trigger workflow completed successfully
- The tag was pushed (check repository tags)
- The release workflow is enabled in Actions settings
### Version Mismatch
If `pyproject.toml` doesn't match the latest tag:
- Run the release trigger workflow to sync versions
- Or manually update `pyproject.toml` and push changes before running the release trigger
## Legacy Behavior (Pre-v0.1.10)
Before this change, the release workflow:
- Created tags automatically on main branch pushes
- Updated `pyproject.toml` AFTER creating the tag
- Resulted in tags pointing to commits with outdated versions
This has been fixed in v0.1.10+.

View File

@@ -29,7 +29,7 @@ jobs:
runs-on: ubuntu-latest
steps:
- name: Checkout
uses: actions/checkout@v4
uses: actions/checkout@v6
with:
fetch-depth: 0 # Fetch all history for git info

View File

@@ -12,7 +12,7 @@ jobs:
runs-on: ubuntu-latest
steps:
- name: Checkout
uses: actions/checkout@v4
uses: actions/checkout@v6
- name: Run markdownlint-cli2
uses: DavidAnson/markdownlint-cli2-action@v19

161
.github/workflows/release-trigger.yml vendored Normal file
View File

@@ -0,0 +1,161 @@
name: Release Trigger
on:
workflow_dispatch:
inputs:
version:
description: 'Version to release (e.g., 0.1.11). Leave empty to auto-increment patch version.'
required: false
type: string
jobs:
bump-version:
runs-on: ubuntu-latest
permissions:
contents: write
pull-requests: write
steps:
- name: Checkout repository
uses: actions/checkout@v6
with:
fetch-depth: 0
token: ${{ secrets.RELEASE_PAT }}
- name: Configure Git
run: |
git config user.name "github-actions[bot]"
git config user.email "41898282+github-actions[bot]@users.noreply.github.com"
- name: Determine version
id: version
env:
INPUT_VERSION: ${{ github.event.inputs.version }}
run: |
if [[ -n "$INPUT_VERSION" ]]; then
# Manual version specified - strip optional v prefix
VERSION="${INPUT_VERSION#v}"
# Validate strict semver format to prevent injection
if [[ ! "$VERSION" =~ ^[0-9]+\.[0-9]+\.[0-9]+$ ]]; then
echo "Error: Invalid version format '$VERSION'. Must be X.Y.Z (e.g. 1.2.3 or v1.2.3)"
exit 1
fi
echo "version=$VERSION" >> $GITHUB_OUTPUT
echo "tag=v$VERSION" >> $GITHUB_OUTPUT
echo "Using manual version: $VERSION"
else
# Auto-increment patch version
LATEST_TAG=$(git describe --tags --abbrev=0 2>/dev/null || echo "v0.0.0")
echo "Latest tag: $LATEST_TAG"
# Extract version number and increment
VERSION=$(echo $LATEST_TAG | sed 's/v//')
IFS='.' read -ra VERSION_PARTS <<< "$VERSION"
MAJOR=${VERSION_PARTS[0]:-0}
MINOR=${VERSION_PARTS[1]:-0}
PATCH=${VERSION_PARTS[2]:-0}
# Increment patch version
PATCH=$((PATCH + 1))
NEW_VERSION="$MAJOR.$MINOR.$PATCH"
echo "version=$NEW_VERSION" >> $GITHUB_OUTPUT
echo "tag=v$NEW_VERSION" >> $GITHUB_OUTPUT
echo "Auto-incremented version: $NEW_VERSION"
fi
- name: Check if tag already exists
run: |
if git rev-parse "${{ steps.version.outputs.tag }}" >/dev/null 2>&1; then
echo "Error: Tag ${{ steps.version.outputs.tag }} already exists!"
exit 1
fi
- name: Create release branch
run: |
BRANCH="chore/release-${{ steps.version.outputs.tag }}"
git checkout -b "$BRANCH"
echo "branch=$BRANCH" >> $GITHUB_ENV
- name: Update pyproject.toml
run: |
sed -i "s/version = \".*\"/version = \"${{ steps.version.outputs.version }}\"/" pyproject.toml
echo "Updated pyproject.toml to version ${{ steps.version.outputs.version }}"
- name: Update CHANGELOG.md
run: |
if [ -f "CHANGELOG.md" ]; then
DATE=$(date +%Y-%m-%d)
# Get the previous tag to compare commits
PREVIOUS_TAG=$(git describe --tags --abbrev=0 2>/dev/null || echo "")
echo "Generating changelog from commits..."
if [[ -n "$PREVIOUS_TAG" ]]; then
echo "Changes since $PREVIOUS_TAG"
COMMITS=$(git log --oneline "$PREVIOUS_TAG"..HEAD --no-merges --pretty=format:"- %s" 2>/dev/null || echo "- Initial release")
else
echo "No previous tag found - this is the first release"
COMMITS="- Initial release"
fi
# Create new changelog entry
{
head -n 8 CHANGELOG.md
echo ""
echo "## [${{ steps.version.outputs.version }}] - $DATE"
echo ""
echo "### Changed"
echo ""
echo "$COMMITS"
echo ""
tail -n +9 CHANGELOG.md
} > CHANGELOG.md.tmp
mv CHANGELOG.md.tmp CHANGELOG.md
echo "✅ Updated CHANGELOG.md with commits since $PREVIOUS_TAG"
else
echo "No CHANGELOG.md found"
fi
- name: Commit version bump
run: |
if [ -f "CHANGELOG.md" ]; then
git add pyproject.toml CHANGELOG.md
else
git add pyproject.toml
fi
if git diff --cached --quiet; then
echo "No changes to commit"
else
git commit -m "chore: bump version to ${{ steps.version.outputs.version }}"
echo "Changes committed"
fi
- name: Create and push tag
run: |
git tag -a "${{ steps.version.outputs.tag }}" -m "Release ${{ steps.version.outputs.tag }}"
git push origin "${{ env.branch }}"
git push origin "${{ steps.version.outputs.tag }}"
echo "Branch ${{ env.branch }} and tag ${{ steps.version.outputs.tag }} pushed"
- name: Open pull request
env:
GITHUB_TOKEN: ${{ secrets.RELEASE_PAT }}
run: |
gh pr create \
--base main \
--head "${{ env.branch }}" \
--title "chore: bump version to ${{ steps.version.outputs.version }}" \
--body "Automated version bump to ${{ steps.version.outputs.version }}.
This PR was created by the Release Trigger workflow. The git tag \`${{ steps.version.outputs.tag }}\` has already been pushed and the release artifacts are being built.
Merge this PR to record the version bump and changelog update on \`main\`."
- name: Summary
run: |
echo "✅ Version bumped to ${{ steps.version.outputs.version }}"
echo "✅ Tag ${{ steps.version.outputs.tag }} created and pushed"
echo "✅ PR opened to merge version bump into main"
echo "🚀 Release workflow is building artifacts from the tag"

View File

@@ -2,60 +2,60 @@ name: Create Release
on:
push:
branches: [ main ]
paths:
- 'memory/**'
- 'scripts/**'
- 'src/**'
- 'templates/**'
- '.github/workflows/**'
workflow_dispatch:
tags:
- 'v*'
jobs:
release:
runs-on: ubuntu-latest
permissions:
contents: write
pull-requests: write
steps:
- name: Checkout repository
uses: actions/checkout@v4
uses: actions/checkout@v6
with:
fetch-depth: 0
token: ${{ secrets.GITHUB_TOKEN }}
- name: Get latest tag
id: get_tag
- name: Extract version from tag
id: version
run: |
chmod +x .github/workflows/scripts/get-next-version.sh
.github/workflows/scripts/get-next-version.sh
VERSION=${GITHUB_REF#refs/tags/}
echo "tag=$VERSION" >> $GITHUB_OUTPUT
echo "Building release for $VERSION"
- name: Check if release already exists
id: check_release
run: |
chmod +x .github/workflows/scripts/check-release-exists.sh
.github/workflows/scripts/check-release-exists.sh ${{ steps.get_tag.outputs.new_version }}
.github/workflows/scripts/check-release-exists.sh ${{ steps.version.outputs.tag }}
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
- name: Create release package variants
if: steps.check_release.outputs.exists == 'false'
run: |
chmod +x .github/workflows/scripts/create-release-packages.sh
.github/workflows/scripts/create-release-packages.sh ${{ steps.get_tag.outputs.new_version }}
.github/workflows/scripts/create-release-packages.sh ${{ steps.version.outputs.tag }}
- name: Generate release notes
if: steps.check_release.outputs.exists == 'false'
id: release_notes
run: |
chmod +x .github/workflows/scripts/generate-release-notes.sh
.github/workflows/scripts/generate-release-notes.sh ${{ steps.get_tag.outputs.new_version }} ${{ steps.get_tag.outputs.latest_tag }}
# Get the previous tag for changelog generation
PREVIOUS_TAG=$(git describe --tags --abbrev=0 ${{ steps.version.outputs.tag }}^ 2>/dev/null || echo "")
# Default to v0.0.0 if no previous tag is found (e.g., first release)
if [ -z "$PREVIOUS_TAG" ]; then
PREVIOUS_TAG="v0.0.0"
fi
.github/workflows/scripts/generate-release-notes.sh ${{ steps.version.outputs.tag }} "$PREVIOUS_TAG"
- name: Create GitHub Release
if: steps.check_release.outputs.exists == 'false'
run: |
chmod +x .github/workflows/scripts/create-github-release.sh
.github/workflows/scripts/create-github-release.sh ${{ steps.get_tag.outputs.new_version }}
.github/workflows/scripts/create-github-release.sh ${{ steps.version.outputs.tag }}
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
- name: Update version in pyproject.toml (for release artifacts only)
if: steps.check_release.outputs.exists == 'false'
run: |
chmod +x .github/workflows/scripts/update-version.sh
.github/workflows/scripts/update-version.sh ${{ steps.get_tag.outputs.new_version }}

View File

@@ -40,17 +40,23 @@ gh release create "$VERSION" \
.genreleases/spec-kit-template-roo-ps-"$VERSION".zip \
.genreleases/spec-kit-template-codebuddy-sh-"$VERSION".zip \
.genreleases/spec-kit-template-codebuddy-ps-"$VERSION".zip \
.genreleases/spec-kit-template-qoder-sh-"$VERSION".zip \
.genreleases/spec-kit-template-qoder-ps-"$VERSION".zip \
.genreleases/spec-kit-template-qodercli-sh-"$VERSION".zip \
.genreleases/spec-kit-template-qodercli-ps-"$VERSION".zip \
.genreleases/spec-kit-template-amp-sh-"$VERSION".zip \
.genreleases/spec-kit-template-amp-ps-"$VERSION".zip \
.genreleases/spec-kit-template-shai-sh-"$VERSION".zip \
.genreleases/spec-kit-template-shai-ps-"$VERSION".zip \
.genreleases/spec-kit-template-q-sh-"$VERSION".zip \
.genreleases/spec-kit-template-q-ps-"$VERSION".zip \
.genreleases/spec-kit-template-tabnine-sh-"$VERSION".zip \
.genreleases/spec-kit-template-tabnine-ps-"$VERSION".zip \
.genreleases/spec-kit-template-kiro-cli-sh-"$VERSION".zip \
.genreleases/spec-kit-template-kiro-cli-ps-"$VERSION".zip \
.genreleases/spec-kit-template-agy-sh-"$VERSION".zip \
.genreleases/spec-kit-template-agy-ps-"$VERSION".zip \
.genreleases/spec-kit-template-bob-sh-"$VERSION".zip \
.genreleases/spec-kit-template-bob-ps-"$VERSION".zip \
.genreleases/spec-kit-template-vibe-sh-"$VERSION".zip \
.genreleases/spec-kit-template-vibe-ps-"$VERSION".zip \
.genreleases/spec-kit-template-generic-sh-"$VERSION".zip \
.genreleases/spec-kit-template-generic-ps-"$VERSION".zip \
--title "Spec Kit Templates - $VERSION_NO_V" \
--notes-file release_notes.md

View File

@@ -14,7 +14,7 @@
.PARAMETER Agents
Comma or space separated subset of agents to build (default: all)
Valid agents: claude, gemini, copilot, cursor-agent, qwen, opencode, windsurf, codex, kilocode, auggie, roo, codebuddy, amp, q, bob, qoder
Valid agents: claude, gemini, copilot, cursor-agent, qwen, opencode, windsurf, codex, kilocode, auggie, roo, codebuddy, amp, kiro-cli, bob, qodercli, shai, tabnine, agy, vibe, generic
.PARAMETER Scripts
Comma or space separated subset of script types to build (default: both)
@@ -335,17 +335,42 @@ function Build-Variant {
$cmdDir = Join-Path $baseDir ".agents/commands"
Generate-Commands -Agent 'amp' -Extension 'md' -ArgFormat '$ARGUMENTS' -OutputDir $cmdDir -ScriptVariant $Script
}
'q' {
$cmdDir = Join-Path $baseDir ".amazonq/prompts"
Generate-Commands -Agent 'q' -Extension 'md' -ArgFormat '$ARGUMENTS' -OutputDir $cmdDir -ScriptVariant $Script
'kiro-cli' {
$cmdDir = Join-Path $baseDir ".kiro/prompts"
Generate-Commands -Agent 'kiro-cli' -Extension 'md' -ArgFormat '$ARGUMENTS' -OutputDir $cmdDir -ScriptVariant $Script
}
'bob' {
$cmdDir = Join-Path $baseDir ".bob/commands"
Generate-Commands -Agent 'bob' -Extension 'md' -ArgFormat '$ARGUMENTS' -OutputDir $cmdDir -ScriptVariant $Script
}
'qoder' {
'qodercli' {
$cmdDir = Join-Path $baseDir ".qoder/commands"
Generate-Commands -Agent 'qoder' -Extension 'md' -ArgFormat '$ARGUMENTS' -OutputDir $cmdDir -ScriptVariant $Script
Generate-Commands -Agent 'qodercli' -Extension 'md' -ArgFormat '$ARGUMENTS' -OutputDir $cmdDir -ScriptVariant $Script
}
'shai' {
$cmdDir = Join-Path $baseDir ".shai/commands"
Generate-Commands -Agent 'shai' -Extension 'md' -ArgFormat '$ARGUMENTS' -OutputDir $cmdDir -ScriptVariant $Script
}
'tabnine' {
$cmdDir = Join-Path $baseDir ".tabnine/agent/commands"
Generate-Commands -Agent 'tabnine' -Extension 'toml' -ArgFormat '{{args}}' -OutputDir $cmdDir -ScriptVariant $Script
$tabnineTemplate = Join-Path 'agent_templates' 'tabnine/TABNINE.md'
if (Test-Path $tabnineTemplate) { Copy-Item $tabnineTemplate (Join-Path $baseDir 'TABNINE.md') }
}
'agy' {
$cmdDir = Join-Path $baseDir ".agent/workflows"
Generate-Commands -Agent 'agy' -Extension 'md' -ArgFormat '$ARGUMENTS' -OutputDir $cmdDir -ScriptVariant $Script
}
'generic' {
$cmdDir = Join-Path $baseDir ".speckit/commands"
Generate-Commands -Agent 'generic' -Extension 'md' -ArgFormat '$ARGUMENTS' -OutputDir $cmdDir -ScriptVariant $Script
}
'vibe' {
$cmdDir = Join-Path $baseDir ".vibe/prompts"
Generate-Commands -Agent 'vibe' -Extension 'md' -ArgFormat '$ARGUMENTS' -OutputDir $cmdDir -ScriptVariant $Script
}
default {
throw "Unsupported agent '$Agent'."
}
}
@@ -356,7 +381,7 @@ function Build-Variant {
}
# Define all agents and scripts
$AllAgents = @('claude', 'gemini', 'copilot', 'cursor-agent', 'qwen', 'opencode', 'windsurf', 'codex', 'kilocode', 'auggie', 'roo', 'codebuddy', 'amp', 'q', 'bob', 'qoder')
$AllAgents = @('claude', 'gemini', 'copilot', 'cursor-agent', 'qwen', 'opencode', 'windsurf', 'codex', 'kilocode', 'auggie', 'roo', 'codebuddy', 'amp', 'kiro-cli', 'bob', 'qodercli', 'shai', 'tabnine', 'agy', 'vibe', 'generic')
$AllScripts = @('sh', 'ps')
function Normalize-List {
@@ -421,4 +446,4 @@ foreach ($agent in $AgentList) {
Write-Host "`nArchives in ${GenReleasesDir}:"
Get-ChildItem -Path $GenReleasesDir -Filter "spec-kit-template-*-${Version}.zip" | ForEach-Object {
Write-Host " $($_.Name)"
}
}

View File

@@ -6,7 +6,7 @@ set -euo pipefail
# Usage: .github/workflows/scripts/create-release-packages.sh <version>
# Version argument should include leading 'v'.
# Optionally set AGENTS and/or SCRIPTS env vars to limit what gets built.
# AGENTS : space or comma separated subset of: claude gemini copilot cursor-agent qwen opencode windsurf codex amp shai bob (default: all)
# AGENTS : space or comma separated subset of: claude gemini copilot cursor-agent qwen opencode windsurf codex kilocode auggie roo codebuddy amp shai tabnine kiro-cli agy bob vibe qodercli generic (default: all)
# SCRIPTS : space or comma separated subset of: sh ps (default: both)
# Examples:
# AGENTS=claude SCRIPTS=sh $0 v0.2.0
@@ -155,7 +155,7 @@ build_variant() {
# NOTE: We substitute {ARGS} internally. Outward tokens differ intentionally:
# * Markdown/prompt (claude, copilot, cursor-agent, opencode): $ARGUMENTS
# * TOML (gemini, qwen): {{args}}
# * TOML (gemini, qwen, tabnine): {{args}}
# This keeps formats readable without extra abstraction.
case $agent in
@@ -203,31 +203,41 @@ build_variant() {
codebuddy)
mkdir -p "$base_dir/.codebuddy/commands"
generate_commands codebuddy md "\$ARGUMENTS" "$base_dir/.codebuddy/commands" "$script" ;;
qoder)
qodercli)
mkdir -p "$base_dir/.qoder/commands"
generate_commands qoder md "\$ARGUMENTS" "$base_dir/.qoder/commands" "$script" ;;
generate_commands qodercli md "\$ARGUMENTS" "$base_dir/.qoder/commands" "$script" ;;
amp)
mkdir -p "$base_dir/.agents/commands"
generate_commands amp md "\$ARGUMENTS" "$base_dir/.agents/commands" "$script" ;;
shai)
mkdir -p "$base_dir/.shai/commands"
generate_commands shai md "\$ARGUMENTS" "$base_dir/.shai/commands" "$script" ;;
q)
mkdir -p "$base_dir/.amazonq/prompts"
generate_commands q md "\$ARGUMENTS" "$base_dir/.amazonq/prompts" "$script" ;;
tabnine)
mkdir -p "$base_dir/.tabnine/agent/commands"
generate_commands tabnine toml "{{args}}" "$base_dir/.tabnine/agent/commands" "$script"
[[ -f agent_templates/tabnine/TABNINE.md ]] && cp agent_templates/tabnine/TABNINE.md "$base_dir/TABNINE.md" ;;
kiro-cli)
mkdir -p "$base_dir/.kiro/prompts"
generate_commands kiro-cli md "\$ARGUMENTS" "$base_dir/.kiro/prompts" "$script" ;;
agy)
mkdir -p "$base_dir/.agent/workflows"
generate_commands agy md "\$ARGUMENTS" "$base_dir/.agent/workflows" "$script" ;;
bob)
mkdir -p "$base_dir/.bob/commands"
generate_commands bob md "\$ARGUMENTS" "$base_dir/.bob/commands" "$script" ;;
vibe)
mkdir -p "$base_dir/.vibe/prompts"
generate_commands vibe md "\$ARGUMENTS" "$base_dir/.vibe/prompts" "$script" ;;
generic)
mkdir -p "$base_dir/.speckit/commands"
generate_commands generic md "\$ARGUMENTS" "$base_dir/.speckit/commands" "$script" ;;
esac
( cd "$base_dir" && zip -r "../spec-kit-template-${agent}-${script}-${NEW_VERSION}.zip" . )
echo "Created $GENRELEASES_DIR/spec-kit-template-${agent}-${script}-${NEW_VERSION}.zip"
}
# Determine agent list
ALL_AGENTS=(claude gemini copilot cursor-agent qwen opencode windsurf codex kilocode auggie roo codebuddy amp shai q agy bob qoder)
ALL_AGENTS=(claude gemini copilot cursor-agent qwen opencode windsurf codex kilocode auggie roo codebuddy amp shai tabnine kiro-cli agy bob vibe qodercli generic)
ALL_SCRIPTS=(sh ps)
norm_list() {
@@ -274,4 +284,3 @@ done
echo "Archives in $GENRELEASES_DIR:"
ls -1 "$GENRELEASES_DIR"/spec-kit-template-*-"${NEW_VERSION}".zip

161
.github/workflows/scripts/simulate-release.sh vendored Executable file
View File

@@ -0,0 +1,161 @@
#!/usr/bin/env bash
set -euo pipefail
# simulate-release.sh
# Simulate the release process locally without pushing to GitHub
# Usage: simulate-release.sh [version]
# If version is omitted, auto-increments patch version
# Colors for output
GREEN='\033[0;32m'
BLUE='\033[0;34m'
YELLOW='\033[1;33m'
RED='\033[0;31m'
NC='\033[0m' # No Color
echo -e "${BLUE}🧪 Simulating Release Process Locally${NC}"
echo "======================================"
echo ""
# Step 1: Determine version
if [[ -n "${1:-}" ]]; then
VERSION="${1#v}"
TAG="v$VERSION"
echo -e "${GREEN}📝 Using manual version: $VERSION${NC}"
else
LATEST_TAG=$(git describe --tags --abbrev=0 2>/dev/null || echo "v0.0.0")
echo -e "${BLUE}Latest tag: $LATEST_TAG${NC}"
VERSION=$(echo $LATEST_TAG | sed 's/v//')
IFS='.' read -ra VERSION_PARTS <<< "$VERSION"
MAJOR=${VERSION_PARTS[0]:-0}
MINOR=${VERSION_PARTS[1]:-0}
PATCH=${VERSION_PARTS[2]:-0}
PATCH=$((PATCH + 1))
VERSION="$MAJOR.$MINOR.$PATCH"
TAG="v$VERSION"
echo -e "${GREEN}📝 Auto-incremented to: $VERSION${NC}"
fi
echo ""
# Step 2: Check if tag exists
if git rev-parse "$TAG" >/dev/null 2>&1; then
echo -e "${RED}❌ Error: Tag $TAG already exists!${NC}"
echo " Please use a different version or delete the tag first."
exit 1
fi
echo -e "${GREEN}✓ Tag $TAG is available${NC}"
# Step 3: Backup current state
echo ""
echo -e "${YELLOW}💾 Creating backup of current state...${NC}"
BACKUP_DIR=$(mktemp -d)
cp pyproject.toml "$BACKUP_DIR/pyproject.toml.bak"
cp CHANGELOG.md "$BACKUP_DIR/CHANGELOG.md.bak"
echo -e "${GREEN}✓ Backup created at: $BACKUP_DIR${NC}"
# Step 4: Update pyproject.toml
echo ""
echo -e "${YELLOW}📝 Updating pyproject.toml...${NC}"
sed -i.tmp "s/version = \".*\"/version = \"$VERSION\"/" pyproject.toml
rm -f pyproject.toml.tmp
echo -e "${GREEN}✓ Updated pyproject.toml to version $VERSION${NC}"
# Step 5: Update CHANGELOG.md
echo ""
echo -e "${YELLOW}📝 Updating CHANGELOG.md...${NC}"
DATE=$(date +%Y-%m-%d)
# Get the previous tag to compare commits
PREVIOUS_TAG=$(git describe --tags --abbrev=0 2>/dev/null || echo "")
if [[ -n "$PREVIOUS_TAG" ]]; then
echo " Generating changelog from commits since $PREVIOUS_TAG"
# Get commits since last tag, format as bullet points
COMMITS=$(git log --oneline "$PREVIOUS_TAG"..HEAD --no-merges --pretty=format:"- %s" 2>/dev/null || echo "- Initial release")
else
echo " No previous tag found - this is the first release"
COMMITS="- Initial release"
fi
# Create temp file with new entry
{
head -n 8 CHANGELOG.md
echo ""
echo "## [$VERSION] - $DATE"
echo ""
echo "### Changed"
echo ""
echo "$COMMITS"
echo ""
tail -n +9 CHANGELOG.md
} > CHANGELOG.md.tmp
mv CHANGELOG.md.tmp CHANGELOG.md
echo -e "${GREEN}✓ Updated CHANGELOG.md with commits since $PREVIOUS_TAG${NC}"
# Step 6: Show what would be committed
echo ""
echo -e "${YELLOW}📋 Changes that would be committed:${NC}"
git diff pyproject.toml CHANGELOG.md
# Step 7: Create temporary tag (no push)
echo ""
echo -e "${YELLOW}🏷️ Creating temporary local tag...${NC}"
git tag -a "$TAG" -m "Simulated release $TAG" 2>/dev/null || true
echo -e "${GREEN}✓ Tag $TAG created locally${NC}"
# Step 8: Simulate release artifact creation
echo ""
echo -e "${YELLOW}📦 Simulating release package creation...${NC}"
echo " (High-level simulation only; packaging script is not executed)"
echo ""
# Check if script exists and is executable
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
if [[ -x "$SCRIPT_DIR/create-release-packages.sh" ]]; then
echo -e "${BLUE}In a real release, the following command would be run to create packages:${NC}"
echo " $SCRIPT_DIR/create-release-packages.sh \"$TAG\""
echo ""
echo "This simulation does not enumerate individual package files to avoid"
echo "drifting from the actual behavior of create-release-packages.sh."
else
echo -e "${RED}⚠️ create-release-packages.sh not found or not executable${NC}"
fi
# Step 9: Simulate release notes generation
echo ""
echo -e "${YELLOW}📄 Simulating release notes generation...${NC}"
echo ""
PREVIOUS_TAG=$(git describe --tags --abbrev=0 $TAG^ 2>/dev/null || echo "")
if [[ -n "$PREVIOUS_TAG" ]]; then
echo -e "${BLUE}Changes since $PREVIOUS_TAG:${NC}"
git log --oneline "$PREVIOUS_TAG".."$TAG" | head -n 10
echo ""
else
echo -e "${BLUE}No previous tag found - this would be the first release${NC}"
fi
# Step 10: Summary
echo ""
echo -e "${GREEN}🎉 Simulation Complete!${NC}"
echo "======================================"
echo ""
echo -e "${BLUE}Summary:${NC}"
echo " Version: $VERSION"
echo " Tag: $TAG"
echo " Backup: $BACKUP_DIR"
echo ""
echo -e "${YELLOW}⚠️ SIMULATION ONLY - NO CHANGES PUSHED${NC}"
echo ""
echo -e "${BLUE}Next steps:${NC}"
echo " 1. Review the changes above"
echo " 2. To keep changes: git add pyproject.toml CHANGELOG.md && git commit"
echo " 3. To discard changes: git checkout pyproject.toml CHANGELOG.md && git tag -d $TAG"
echo " 4. To restore from backup: cp $BACKUP_DIR/* ."
echo ""
echo -e "${BLUE}To run the actual release:${NC}"
echo " Go to: https://github.com/github/spec-kit/actions/workflows/release-trigger.yml"
echo " Click 'Run workflow' and enter version: $VERSION"
echo ""

View File

@@ -16,10 +16,10 @@ jobs:
uses: actions/checkout@v4
- name: Install uv
uses: astral-sh/setup-uv@v6
uses: astral-sh/setup-uv@v7
- name: Set up Python
uses: actions/setup-python@v5
uses: actions/setup-python@v6
with:
python-version: "3.13"
@@ -36,10 +36,10 @@ jobs:
uses: actions/checkout@v4
- name: Install uv
uses: astral-sh/setup-uv@v6
uses: astral-sh/setup-uv@v7
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v5
uses: actions/setup-python@v6
with:
python-version: ${{ matrix.python-version }}

View File

@@ -43,11 +43,13 @@ Specify supports multiple AI agents by generating agent-specific command files a
| **Auggie CLI** | `.augment/rules/` | Markdown | `auggie` | Auggie CLI |
| **Roo Code** | `.roo/rules/` | Markdown | N/A (IDE-based) | Roo Code IDE |
| **CodeBuddy CLI** | `.codebuddy/commands/` | Markdown | `codebuddy` | CodeBuddy CLI |
| **Qoder CLI** | `.qoder/commands/` | Markdown | `qoder` | Qoder CLI |
| **Amazon Q Developer CLI** | `.amazonq/prompts/` | Markdown | `q` | Amazon Q Developer CLI |
| **Qoder CLI** | `.qoder/commands/` | Markdown | `qodercli` | Qoder CLI |
| **Kiro CLI** | `.kiro/prompts/` | Markdown | `kiro-cli` | Kiro CLI |
| **Amp** | `.agents/commands/` | Markdown | `amp` | Amp CLI |
| **SHAI** | `.shai/commands/` | Markdown | `shai` | SHAI CLI |
| **Tabnine CLI** | `.tabnine/agent/commands/` | TOML | `tabnine` | Tabnine CLI |
| **IBM Bob** | `.bob/commands/` | Markdown | N/A (IDE-based) | IBM Bob IDE |
| **Generic** | User-specified via `--ai-commands-dir` | Markdown | N/A | Bring your own agent |
### Step-by-Step Integration Guide
@@ -65,6 +67,7 @@ AGENT_CONFIG = {
"new-agent-cli": { # Use the ACTUAL CLI tool name (what users type in terminal)
"name": "New Agent Display Name",
"folder": ".newagent/", # Directory for agent files
"commands_subdir": "commands", # Subdirectory name for command files (default: "commands")
"install_url": "https://example.com/install", # URL for installation docs (or None if IDE-based)
"requires_cli": True, # True if CLI tool required, False for IDE-based agents
},
@@ -82,6 +85,10 @@ This eliminates the need for special-case mappings throughout the codebase.
- `name`: Human-readable display name shown to users
- `folder`: Directory where agent-specific files are stored (relative to project root)
- `commands_subdir`: Subdirectory name within the agent folder where command/prompt files are stored (default: `"commands"`)
- Most agents use `"commands"` (e.g., `.claude/commands/`)
- Some agents use alternative names: `"agents"` (copilot), `"workflows"` (windsurf, kilocode, agy), `"prompts"` (codex, kiro-cli), `"command"` (opencode - singular)
- This field enables `--ai-skills` to locate command templates correctly for skill generation
- `install_url`: Installation documentation URL (set to `None` for IDE-based agents)
- `requires_cli`: Whether the agent requires a CLI tool check during initialization
@@ -90,7 +97,7 @@ This eliminates the need for special-case mappings throughout the codebase.
Update the `--ai` parameter help text in the `init()` command to include the new agent:
```python
ai_assistant: str = typer.Option(None, "--ai", help="AI assistant to use: claude, gemini, copilot, cursor-agent, qwen, opencode, codex, windsurf, kilocode, auggie, codebuddy, new-agent-cli, or q"),
ai_assistant: str = typer.Option(None, "--ai", help="AI assistant to use: claude, gemini, copilot, cursor-agent, qwen, opencode, codex, windsurf, kilocode, auggie, codebuddy, new-agent-cli, or kiro-cli"),
```
Also update any function docstrings, examples, and error messages that list available agents.
@@ -111,7 +118,7 @@ Modify `.github/workflows/scripts/create-release-packages.sh`:
##### Add to ALL_AGENTS array
```bash
ALL_AGENTS=(claude gemini copilot cursor-agent qwen opencode windsurf q)
ALL_AGENTS=(claude gemini copilot cursor-agent qwen opencode windsurf kiro-cli)
```
##### Add case statement for directory structure
@@ -311,11 +318,12 @@ Require a command-line tool to be installed:
- **Cursor**: `cursor-agent` CLI
- **Qwen Code**: `qwen` CLI
- **opencode**: `opencode` CLI
- **Amazon Q Developer CLI**: `q` CLI
- **Kiro CLI**: `kiro-cli` CLI
- **CodeBuddy CLI**: `codebuddy` CLI
- **Qoder CLI**: `qoder` CLI
- **Qoder CLI**: `qodercli` CLI
- **Amp**: `amp` CLI
- **SHAI**: `shai` CLI
- **Tabnine CLI**: `tabnine` CLI
### IDE-Based Agents
@@ -329,7 +337,7 @@ Work within integrated development environments:
### Markdown Format
Used by: Claude, Cursor, opencode, Windsurf, Amazon Q Developer, Amp, SHAI, IBM Bob
Used by: Claude, Cursor, opencode, Windsurf, Kiro CLI, Amp, SHAI, IBM Bob
**Standard format:**
@@ -354,7 +362,7 @@ Command content with {SCRIPT} and $ARGUMENTS placeholders.
### TOML Format
Used by: Gemini, Qwen
Used by: Gemini, Qwen, Tabnine
```toml
description = "Command description"

View File

@@ -2,318 +2,234 @@
<!-- markdownlint-disable MD024 -->
All notable changes to the Specify CLI and templates are documented here.
Recent changes to the Specify CLI and templates are documented here.
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
## [0.1.2] - 2026-02-20
## [0.2.1] - 2026-03-10
### Added
- feat(presets): Pluggable preset system with preset catalog and template resolver
- Preset manifest (`preset.yml`) with validation for artifact, command, and script types
- `PresetManifest`, `PresetRegistry`, `PresetManager`, `PresetCatalog`, `PresetResolver` classes in `src/specify_cli/presets.py`
- CLI commands: `specify preset search`, `specify preset add`, `specify preset list`, `specify preset remove`, `specify preset resolve`, `specify preset info`
- CLI commands: `specify preset catalog list`, `specify preset catalog add`, `specify preset catalog remove` for multi-catalog management
- `PresetCatalogEntry` dataclass and multi-catalog support mirroring the extension catalog system
- `--preset` option for `specify init` to install presets during initialization
- Priority-based preset resolution: presets with lower priority number win (`--priority` flag)
- `resolve_template()` / `Resolve-Template` helpers in bash and PowerShell common scripts
- Template resolution priority stack: overrides → presets → extensions → core
- Preset catalog files (`presets/catalog.json`, `presets/catalog.community.json`)
- Preset scaffold directory (`presets/scaffold/`)
- Scripts updated to use template resolution instead of hardcoded paths
- feat(presets): Preset command overrides now propagate to agent skills when `--ai-skills` was used during init
- feat: `specify init` persists CLI options to `.specify/init-options.json` for downstream operations
- feat(extensions): support `.extensionignore` to exclude files/folders during `specify extension add` (#1781)
## [0.2.0] - 2026-03-09
### Changed
- fix: sync agent list comments with actual supported agents (#1785)
- feat(extensions): support multiple active catalogs simultaneously (#1720)
- Pavel/add tabnine cli support (#1503)
- Add Understanding extension to community catalog (#1778)
- Add ralph extension to community catalog (#1780)
- Update README with project initialization instructions (#1772)
- feat: add review extension to community catalog (#1775)
- Add fleet extension to community catalog (#1771)
- Integration of Mistral vibe support into speckit (#1725)
- fix: Remove duplicate options in specify.md (#1765)
- fix: use global branch numbering instead of per-short-name detection (#1757)
- Add Community Walkthroughs section to README (#1766)
- feat(extensions): add Jira Integration to community catalog (#1764)
- Add Azure DevOps Integration extension to community catalog (#1734)
- Fix docs: update Antigravity link and add initialization example (#1748)
- fix: wire after_tasks and after_implement hook events into command templates (#1702)
- make c ignores consistent with c++ (#1747)
- chore: bump version to 0.1.13 (#1746)
- feat: add kiro-cli and AGENT_CONFIG consistency coverage (#1690)
- feat: add verify extension to community catalog (#1726)
- Add Retrospective Extension to community catalog README table (#1741)
- fix(scripts): add empty description validation and branch checkout error handling (#1559)
- fix: correct Copilot extension command registration (#1724)
- fix(implement): remove Makefile from C ignore patterns (#1558)
- Add sync extension to community catalog (#1728)
- fix(checklist): clarify file handling behavior for append vs create (#1556)
- fix(clarify): correct conflicting question limit from 10 to 5 (#1557)
- chore: bump version to 0.1.12 (#1737)
- fix: use RELEASE_PAT so tag push triggers release workflow (#1736)
- fix: release-trigger uses release branch + PR instead of direct push to main (#1733)
- fix: Split release process to sync pyproject.toml version with git tags (#1732)
## [0.1.14] - 2026-03-09
### Added
- feat: add Tabnine CLI agent support
- **Multi-Catalog Support (#1707)**: Extension catalog system now supports multiple active catalogs simultaneously via a catalog stack
- New `specify extension catalog list` command lists all active catalogs with name, URL, priority, and `install_allowed` status
- New `specify extension catalog add` and `specify extension catalog remove` commands for project-scoped catalog management
- Default built-in stack includes `catalog.json` (default, installable) and `catalog.community.json` (community, discovery only) — community extensions are now surfaced in search results out of the box
- `specify extension search` aggregates results across all active catalogs, annotating each result with source catalog
- `specify extension add` enforces `install_allowed` policy — extensions from discovery-only catalogs cannot be installed directly
- Project-level `.specify/extension-catalogs.yml` and user-level `~/.specify/extension-catalogs.yml` config files supported, with project-level taking precedence
- `SPECKIT_CATALOG_URL` environment variable still works for backward compatibility (replaces full stack with single catalog)
- All catalog URLs require HTTPS (HTTP allowed for localhost development)
- New `CatalogEntry` dataclass in `extensions.py` for catalog stack representation
- Per-URL hash-based caching for non-default catalogs; legacy cache preserved for default catalog
- Higher-priority catalogs win on merge conflicts (same extension id in multiple catalogs)
- 13 new tests covering catalog stack resolution, merge conflicts, URL validation, and `install_allowed` enforcement
- Updated RFC, Extension User Guide, and Extension API Reference documentation
## [0.1.13] - 2026-03-03
### Changed
- feat: add kiro-cli and AGENT_CONFIG consistency coverage (#1690)
- feat: add verify extension to community catalog (#1726)
- Add Retrospective Extension to community catalog README table (#1741)
- fix(scripts): add empty description validation and branch checkout error handling (#1559)
- fix: correct Copilot extension command registration (#1724)
- fix(implement): remove Makefile from C ignore patterns (#1558)
- Add sync extension to community catalog (#1728)
- fix(checklist): clarify file handling behavior for append vs create (#1556)
- fix(clarify): correct conflicting question limit from 10 to 5 (#1557)
- chore: bump version to 0.1.12 (#1737)
- fix: use RELEASE_PAT so tag push triggers release workflow (#1736)
- fix: release-trigger uses release branch + PR instead of direct push to main (#1733)
- fix: Split release process to sync pyproject.toml version with git tags (#1732)
## [0.1.13] - 2026-03-03
### Fixed
- **Python 3.14 / Homebrew compatibility**: Added explicit `click>=8.1` dependency so the resolver always selects a Click version compatible with Python 3.14 and avoids errors such as `TypeError: ParamType.get_metavar() got an unexpected keyword argument 'ctx'` when an older Click would otherwise be used. Note that broader uv/Homebrew environment isolation or `sys.path` bleed issues (see [#1631](https://github.com/github/spec-kit/issues/1631)) may still require environment-level workarounds.
## [0.1.1] - 2026-02-13
### Added
- **Agent Skills Installation**: New `--ai-skills` CLI option to install Prompt.MD templates as agent skills following [agentskills.io specification](https://agentskills.io/specification)
- Skills are installed to agent-specific directories (e.g., `.claude/skills/`, `.gemini/skills/`, `.github/skills/`)
- Codex uses `.agents/skills/` following Codex agent directory conventions
- Default fallback directory is `.agents/skills/` for agents without a specific mapping
- Requires `--ai` flag to be specified
- Converts all 9 spec-kit command templates (specify, plan, tasks, implement, analyze, clarify, constitution, checklist, taskstoissues) to properly formatted SKILL.md files
- **New projects**: command files are not installed when `--ai-skills` is used (skills replace commands)
- **Existing repos** (`--here`): pre-existing command files are preserved — no breaking changes
- `pyyaml` dependency (already present) used for YAML frontmatter parsing
- **Unit tests** for `install_ai_skills`, `_get_skills_dir`, and `--ai-skills` CLI validation (51 test cases covering all 18 supported agents)
## [0.1.0] - 2026-01-28
### Added
- **Extension System**: Introduced modular extension architecture for Spec Kit
- Extensions are self-contained packages that add commands and functionality without bloating core
- Extension manifest schema (`extension.yml`) with validation
- Extension registry (`.specify/extensions/.registry`) for tracking installed extensions
- Extension manager module (`src/specify_cli/extensions.py`) for installation/removal
- New CLI commands:
- `specify extension list` - List installed extensions
- `specify extension add` - Install extension from local directory or URL
- `specify extension remove` - Uninstall extension
- `specify extension search` - Search extension catalog
- `specify extension info` - Show detailed extension information
- Semantic versioning compatibility checks
- Support for extension configuration files
- Command registration system for AI agents (Claude support initially)
- Added dependencies: `pyyaml>=6.0`, `packaging>=23.0`
- **Extension Catalog**: Extension discovery and distribution system
- Central catalog (`extensions/catalog.json`) for published extensions
- Extension catalog manager (`ExtensionCatalog` class) with:
- Catalog fetching from GitHub
- 1-hour local caching for performance
- Search by query, tag, author, or verification status
- Extension info retrieval
- Catalog cache stored in `.specify/extensions/.cache/`
- Search and info commands with rich console output
- Added 9 catalog-specific unit tests (100% pass rate)
- **Jira Extension**: First official extension for Jira integration
- Extension ID: `jira`
- Version: 1.0.0
- Commands:
- `/speckit.jira.specstoissues` - Create Jira hierarchy from spec and tasks
- `/speckit.jira.discover-fields` - Discover Jira custom fields
- `/speckit.jira.sync-status` - Sync task completion status
- Comprehensive documentation (README, usage guide, examples)
- MIT licensed
- **Hook System**: Extension lifecycle hooks for automation
- `HookExecutor` class for managing extension hooks
- Hooks registered in `.specify/extensions.yml`
- Hook registration during extension installation
- Hook unregistration during extension removal
- Support for optional and mandatory hooks
- Hook execution messages for AI agent integration
- Condition support for conditional hook execution (placeholder)
- **Extension Management**: Advanced extension management commands
- `specify extension update` - Check and update extensions to latest version
- `specify extension enable` - Enable a disabled extension
- `specify extension disable` - Disable extension without removing it
- Version comparison with catalog
- Update notifications
- Preserve configuration during updates
- **Multi-Agent Support**: Extensions now work with all supported AI agents (Phase 6)
- Automatic detection and registration for all agents in project
- Support for 16+ AI agents (Claude, Gemini, Copilot, Cursor, Qwen, and more)
- Agent-specific command formats (Markdown and TOML)
- Automatic argument placeholder conversion ($ARGUMENTS → {{args}})
- Commands registered for all detected agents during installation
- Multi-agent command unregistration on extension removal
- `CommandRegistrar.register_commands_for_agent()` method
- `CommandRegistrar.register_commands_for_all_agents()` method
- **Configuration Layers**: Full configuration cascade system (Phase 6)
- **Layer 1**: Defaults from extension manifest (`extension.yml`)
- **Layer 2**: Project config (`.specify/extensions/{ext-id}/{ext-id}-config.yml`)
- **Layer 3**: Local config (`.specify/extensions/{ext-id}/local-config.yml`, gitignored)
- **Layer 4**: Environment variables (`SPECKIT_{EXT_ID}_{KEY}` pattern)
- Recursive config merging with proper precedence
- `ConfigManager` class for programmatic config access
- `get_config()`, `get_value()`, `has_value()` methods
- Support for nested configuration paths with dot-notation
- **Hook Condition Evaluation**: Smart hook execution based on runtime conditions (Phase 6)
- Config conditions: `config.key.path is set`, `config.key == 'value'`, `config.key != 'value'`
- Environment conditions: `env.VAR is set`, `env.VAR == 'value'`, `env.VAR != 'value'`
- Automatic filtering of hooks based on condition evaluation
- Safe fallback behavior on evaluation errors
- Case-insensitive pattern matching
- **Hook Integration**: Agent-level hook checking and execution (Phase 6)
- `check_hooks_for_event()` method for AI agents to query hooks after core commands
- Condition-aware hook filtering before execution
- `enable_hooks()` and `disable_hooks()` methods per extension
- Formatted hook messages for agent display
- `execute_hook()` method for hook execution information
- **Documentation Suite**: Comprehensive documentation for users and developers
- **EXTENSION-USER-GUIDE.md**: Complete user guide with installation, usage, configuration, and troubleshooting
- **EXTENSION-API-REFERENCE.md**: Technical API reference with manifest schema, Python API, and CLI commands
- **EXTENSION-PUBLISHING-GUIDE.md**: Publishing guide for extension authors
- **RFC-EXTENSION-SYSTEM.md**: Extension architecture design document
- **Extension Template**: Starter template in `extensions/template/` for creating new extensions
- Fully commented `extension.yml` manifest template
- Example command file with detailed explanations
- Configuration template with all options
- Complete project structure (README, LICENSE, CHANGELOG, .gitignore)
- EXAMPLE-README.md showing final documentation format
- **Unit Tests**: Comprehensive test suite with 39 tests covering all extension system components
- Test coverage: 83% of extension module code
- Test dependencies: `pytest>=7.0`, `pytest-cov>=4.0`
- Configured pytest in `pyproject.toml`
- **Copilot Extension Commands Not Visible**: Fixed extension commands not appearing in GitHub Copilot when installed via `specify extension add --dev`
- Changed Copilot file extension from `.md` to `.agent.md` in `CommandRegistrar.AGENT_CONFIGS` so Copilot recognizes agent files
- Added generation of companion `.prompt.md` files in `.github/prompts/` during extension command registration, matching the release packaging behavior
- Added cleanup of `.prompt.md` companion files when removing extensions via `specify extension remove`
- Fixed a syntax regression in `src/specify_cli/__init__.py` in `_build_ai_assistant_help()` that broke `ruff` and `pytest` collection in CI.
## [0.1.12] - 2026-03-02
### Changed
- Version bumped to 0.1.0 (minor release for new feature)
- fix: use RELEASE_PAT so tag push triggers release workflow (#1736)
- fix: release-trigger uses release branch + PR instead of direct push to main (#1733)
- fix: Split release process to sync pyproject.toml version with git tags (#1732)
## [0.0.22] - 2025-11-07
- Support for VS Code/Copilot agents, and moving away from prompts to proper agents with hand-offs.
- Move to use `AGENTS.md` for Copilot workloads, since it's already supported out-of-the-box.
- Adds support for the version command. ([#486](https://github.com/github/spec-kit/issues/486))
- Fixes potential bug with the `create-new-feature.ps1` script that ignores existing feature branches when determining next feature number ([#975](https://github.com/github/spec-kit/issues/975))
- Add graceful fallback and logging for GitHub API rate-limiting during template fetch ([#970](https://github.com/github/spec-kit/issues/970))
## [0.0.21] - 2025-10-21
- Fixes [#975](https://github.com/github/spec-kit/issues/975) (thank you [@fgalarraga](https://github.com/fgalarraga)).
- Adds support for Amp CLI.
- Adds support for VS Code hand-offs and moves prompts to be full-fledged chat modes.
- Adds support for `version` command (addresses [#811](https://github.com/github/spec-kit/issues/811) and [#486](https://github.com/github/spec-kit/issues/486), thank you [@mcasalaina](https://github.com/mcasalaina) and [@dentity007](https://github.com/dentity007)).
- Adds support for rendering the rate limit errors from the CLI when encountered ([#970](https://github.com/github/spec-kit/issues/970), thank you [@psmman](https://github.com/psmman)).
## [0.0.20] - 2025-10-14
### Added
- **Intelligent Branch Naming**: `create-new-feature` scripts now support `--short-name` parameter for custom branch names
- When `--short-name` provided: Uses the custom name directly (cleaned and formatted)
- When omitted: Automatically generates meaningful names using stop word filtering and length-based filtering
- Filters out common stop words (I, want, to, the, for, etc.)
- Removes words shorter than 3 characters (unless they're uppercase acronyms)
- Takes 3-4 most meaningful words from the description
- **Enforces GitHub's 244-byte branch name limit** with automatic truncation and warnings
- Examples:
- "I want to create user authentication" → `001-create-user-authentication`
- "Implement OAuth2 integration for API" → `001-implement-oauth2-integration-api`
- "Fix payment processing bug" → `001-fix-payment-processing`
- Very long descriptions are automatically truncated at word boundaries to stay within limits
- Designed for AI agents to provide semantic short names while maintaining standalone usability
### Changed
- Enhanced help documentation for `create-new-feature.sh` and `create-new-feature.ps1` scripts with examples
- Branch names now validated against GitHub's 244-byte limit with automatic truncation if needed
## [0.0.19] - 2025-10-10
### Added
- Support for CodeBuddy (thank you to [@lispking](https://github.com/lispking) for the contribution).
- You can now see Git-sourced errors in the Specify CLI.
### Changed
- Fixed the path to the constitution in `plan.md` (thank you to [@lyzno1](https://github.com/lyzno1) for spotting).
- Fixed backslash escapes in generated TOML files for Gemini (thank you to [@hsin19](https://github.com/hsin19) for the contribution).
- Implementation command now ensures that the correct ignore files are added (thank you to [@sigent-amazon](https://github.com/sigent-amazon) for the contribution).
## [0.0.18] - 2025-10-06
### Added
- Support for using `.` as a shorthand for current directory in `specify init .` command, equivalent to `--here` flag but more intuitive for users.
- Use the `/speckit.` command prefix to easily discover Spec Kit-related commands.
- Refactor the prompts and templates to simplify their capabilities and how they are tracked. No more polluting things with tests when they are not needed.
- Ensure that tasks are created per user story (simplifies testing and validation).
- Add support for Visual Studio Code prompt shortcuts and automatic script execution.
### Changed
- All command files now prefixed with `speckit.` (e.g., `speckit.specify.md`, `speckit.plan.md`) for better discoverability and differentiation in IDE/CLI command palettes and file explorers
## [0.0.17] - 2025-09-22
### Added
- New `/clarify` command template to surface up to 5 targeted clarification questions for an existing spec and persist answers into a Clarifications section in the spec.
- New `/analyze` command template providing a non-destructive cross-artifact discrepancy and alignment report (spec, clarifications, plan, tasks, constitution) inserted after `/tasks` and before `/implement`.
- Note: Constitution rules are explicitly treated as non-negotiable; any conflict is a CRITICAL finding requiring artifact remediation, not weakening of principles.
## [0.0.16] - 2025-09-22
### Added
- `--force` flag for `init` command to bypass confirmation when using `--here` in a non-empty directory and proceed with merging/overwriting files.
## [0.0.15] - 2025-09-21
### Added
- Support for Roo Code.
## [0.0.14] - 2025-09-21
### Changed
- Error messages are now shown consistently.
## [0.0.13] - 2025-09-21
### Added
- Support for Kilo Code. Thank you [@shahrukhkhan489](https://github.com/shahrukhkhan489) with [#394](https://github.com/github/spec-kit/pull/394).
- Support for Auggie CLI. Thank you [@hungthai1401](https://github.com/hungthai1401) with [#137](https://github.com/github/spec-kit/pull/137).
- Agent folder security notice displayed after project provisioning completion, warning users that some agents may store credentials or auth tokens in their agent folders and recommending adding relevant folders to `.gitignore` to prevent accidental credential leakage.
### Changed
- Warning displayed to ensure that folks are aware that they might need to add their agent folder to `.gitignore`.
- Cleaned up the `check` command output.
## [0.0.12] - 2025-09-21
### Changed
- Added additional context for OpenAI Codex users - they need to set an additional environment variable, as described in [#417](https://github.com/github/spec-kit/issues/417).
## [0.0.11] - 2025-09-20
### Added
- Codex CLI support (thank you [@honjo-hiroaki-gtt](https://github.com/honjo-hiroaki-gtt) for the contribution in [#14](https://github.com/github/spec-kit/pull/14))
- Codex-aware context update tooling (Bash and PowerShell) so feature plans refresh `AGENTS.md` alongside existing assistants without manual edits.
## [0.0.10] - 2025-09-20
## [0.1.10] - 2026-03-02
### Fixed
- Addressed [#378](https://github.com/github/spec-kit/issues/378) where a GitHub token may be attached to the request when it was empty.
- **Version Sync Issue (#1721)**: Fixed version mismatch between `pyproject.toml` and git release tags
- Split release process into two workflows: `release-trigger.yml` for version management and `release.yml` for artifact building
- Version bump now happens BEFORE tag creation, ensuring tags point to commits with correct version
- Supports both manual version specification and auto-increment (patch version)
- Git tags now accurately reflect the version in `pyproject.toml` at that commit
- Prevents confusion when installing from source
## [0.0.9] - 2025-09-19
## [0.1.9] - 2026-02-28
### Changed
- Improved agent selector UI with cyan highlighting for agent keys and gray parentheses for full names
- Updated dependency: bumped astral-sh/setup-uv from 6 to 7
## [0.0.8] - 2025-09-19
### Added
- Windsurf IDE support as additional AI assistant option (thank you [@raedkit](https://github.com/raedkit) for the work in [#151](https://github.com/github/spec-kit/pull/151))
- GitHub token support for API requests to handle corporate environments and rate limiting (contributed by [@zryfish](https://github.com/@zryfish) in [#243](https://github.com/github/spec-kit/pull/243))
## [0.1.8] - 2026-02-28
### Changed
- Updated README with Windsurf examples and GitHub token usage
- Enhanced release workflow to include Windsurf templates
- Updated dependency: bumped actions/setup-python from 5 to 6
## [0.0.7] - 2025-09-18
## [0.1.7] - 2026-02-27
### Changed
- Updated command instructions in the CLI.
- Cleaned up the code to not render agent-specific information when it's generic.
## [0.0.6] - 2025-09-17
### Added
- opencode support as additional AI assistant option
## [0.0.5] - 2025-09-17
### Added
- Qwen Code support as additional AI assistant option
## [0.0.4] - 2025-09-14
### Added
- SOCKS proxy support for corporate environments via `httpx[socks]` dependency
- Updated outdated GitHub Actions versions
- Documented dual-catalog system for extensions
### Fixed
N/A
- Fixed version command in documentation
### Changed
### Added
N/A
- Added Cleanup Extension to README
- Added retrospective extension to community catalog
## [0.1.6] - 2026-02-23
### Fixed
- **Parameter Ordering Issues (#1641)**: Fixed CLI parameter parsing issue where option flags were incorrectly consumed as values for preceding options
- Added validation to detect when `--ai` or `--ai-commands-dir` incorrectly consume following flags like `--here` or `--ai-skills`
- Now provides clear error messages: "Invalid value for --ai: '--here'"
- Includes helpful hints suggesting proper usage and listing available agents
- Commands like `specify init --ai-skills --ai --here` now fail with actionable feedback instead of confusing "Must specify project name" errors
- Added comprehensive test suite (5 new tests) to prevent regressions
## [0.1.5] - 2026-02-21
### Fixed
- **AI Skills Installation Bug (#1658)**: Fixed `--ai-skills` flag not generating skill files for GitHub Copilot and other agents with non-standard command directory structures
- Added `commands_subdir` field to `AGENT_CONFIG` to explicitly specify the subdirectory name for each agent
- Affected agents now work correctly: copilot (`.github/agents/`), opencode (`.opencode/command/`), windsurf (`.windsurf/workflows/`), codex (`.codex/prompts/`), kilocode (`.kilocode/workflows/`), q (`.amazonq/prompts/`), and agy (`.agent/workflows/`)
- The `install_ai_skills()` function now uses the correct path for all agents instead of assuming `commands/` for everyone
## [0.1.4] - 2026-02-20
### Fixed
- **Qoder CLI detection**: Renamed `AGENT_CONFIG` key from `"qoder"` to `"qodercli"` to match the actual executable name, fixing `specify check` and `specify init --ai` detection failures
## [0.1.3] - 2026-02-20
### Added
- **Generic Agent Support**: Added `--ai generic` option for unsupported AI agents ("bring your own agent")
- Requires `--ai-commands-dir <path>` to specify where the agent reads commands from
- Generates Markdown commands with `$ARGUMENTS` format (compatible with most agents)
- Example: `specify init my-project --ai generic --ai-commands-dir .myagent/commands/`
- Enables users to start with Spec Kit immediately while their agent awaits formal support
## [0.0.102] - 2026-02-20
- fix: include 'src/**' path in release workflow triggers (#1646)
## [0.0.101] - 2026-02-19
- chore(deps): bump github/codeql-action from 3 to 4 (#1635)
## [0.0.100] - 2026-02-19
- Add pytest and Python linting (ruff) to CI (#1637)
- feat: add pull request template for better contribution guidelines (#1634)
## [0.0.99] - 2026-02-19
- Feat/ai skills (#1632)
## [0.0.98] - 2026-02-19
- chore(deps): bump actions/stale from 9 to 10 (#1623)
- feat: add dependabot configuration for pip and GitHub Actions updates (#1622)
## [0.0.97] - 2026-02-18
- Remove Maintainers section from README.md (#1618)
## [0.0.96] - 2026-02-17
- fix: typo in plan-template.md (#1446)
## [0.0.95] - 2026-02-12
- Feat: add a new agent: Google Anti Gravity (#1220)
## [0.0.94] - 2026-02-11
- Add stale workflow for 180-day inactive issues and PRs (#1594)

View File

@@ -22,6 +22,7 @@
- [🤔 What is Spec-Driven Development?](#-what-is-spec-driven-development)
- [⚡ Get Started](#-get-started)
- [📽️ Video Overview](#-video-overview)
- [🚶 Community Walkthroughs](#-community-walkthroughs)
- [🤖 Supported AI Agents](#-supported-ai-agents)
- [🔧 Specify CLI Reference](#-specify-cli-reference)
- [📚 Core Philosophy](#-core-philosophy)
@@ -79,7 +80,13 @@ uv tool install specify-cli --force --from git+https://github.com/github/spec-ki
Run directly without installing:
```bash
# Create new project
uvx --from git+https://github.com/github/spec-kit.git specify init <PROJECT_NAME>
# Or initialize in existing project
uvx --from git+https://github.com/github/spec-kit.git specify init . --ai claude
# or
uvx --from git+https://github.com/github/spec-kit.git specify init --here --ai claude
```
**Benefits of persistent installation:**
@@ -139,12 +146,22 @@ Want to see Spec Kit in action? Watch our [video overview](https://www.youtube.c
[![Spec Kit video header](/media/spec-kit-video-header.jpg)](https://www.youtube.com/watch?v=a9eR1xsfvHg&pp=0gcJCckJAYcqIYzv)
## 🚶 Community Walkthroughs
See Spec-Driven Development in action across different scenarios with these community-contributed walkthroughs:
- **[Greenfield .NET CLI tool](https://github.com/mnriem/spec-kit-dotnet-cli-demo)** — Builds a Timezone Utility as a .NET single-binary CLI tool from a blank directory, covering the full spec-kit workflow: constitution, specify, plan, tasks, and multi-pass implement using GitHub Copilot agents.
- **[Greenfield Spring Boot + React platform](https://github.com/mnriem/spec-kit-spring-react-demo)** — Builds an LLM performance analytics platform (REST API, graphs, iteration tracking) from scratch using Spring Boot, embedded React, PostgreSQL, and Docker Compose, with a clarify step and a cross-artifact consistency analysis pass included.
- **[Brownfield ASP.NET CMS extension](https://github.com/mnriem/spec-kit-aspnet-brownfield-demo)** — Extends an existing open-source .NET CMS (CarrotCakeCMS-Core) with two new features — cross-platform Docker Compose infrastructure and a token-authenticated headless REST API — demonstrating how spec-kit fits into existing codebases without prior specs or a constitution.
## 🤖 Supported AI Agents
| Agent | Support | Notes |
| ------------------------------------------------------------------------------------ | ------- | ----------------------------------------------------------------------------------------------------------------------------------------- |
| [Qoder CLI](https://qoder.com/cli) | ✅ | |
| [Amazon Q Developer CLI](https://aws.amazon.com/developer/learning/q-developer-cli/) | ⚠️ | Amazon Q Developer CLI [does not support](https://github.com/aws/amazon-q-developer-cli/issues/3064) custom arguments for slash commands. |
| [Kiro CLI](https://kiro.dev/docs/cli/) | ✅ | Use `--ai kiro-cli` (alias: `--ai kiro`) |
| [Amp](https://ampcode.com/) | ✅ | |
| [Auggie CLI](https://docs.augmentcode.com/cli/overview) | ✅ | |
| [Claude Code](https://www.anthropic.com/claude-code) | ✅ | |
@@ -160,8 +177,11 @@ Want to see Spec Kit in action? Watch our [video overview](https://www.youtube.c
| [Qwen Code](https://github.com/QwenLM/qwen-code) | ✅ | |
| [Roo Code](https://roocode.com/) | ✅ | |
| [SHAI (OVHcloud)](https://github.com/ovh/shai) | ✅ | |
| [Tabnine CLI](https://docs.tabnine.com/main/getting-started/tabnine-cli) | ✅ | |
| [Mistral Vibe](https://github.com/mistralai/mistral-vibe) | ✅ | |
| [Windsurf](https://windsurf.com/) | ✅ | |
| [Antigravity (agy)](https://agy.ai/) | ✅ | |
| [Antigravity (agy)](https://antigravity.google/) | ✅ | |
| Generic | ✅ | Bring your own agent — use `--ai generic --ai-commands-dir <path>` for unsupported agents |
## 🔧 Specify CLI Reference
@@ -172,14 +192,15 @@ The `specify` command supports the following options:
| Command | Description |
| ------- | ------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `init` | Initialize a new Specify project from the latest template |
| `check` | Check for installed tools (`git`, `claude`, `gemini`, `code`/`code-insiders`, `cursor-agent`, `windsurf`, `qwen`, `opencode`, `codex`, `shai`, `qoder`) |
| `check` | Check for installed tools (`git`, `claude`, `gemini`, `code`/`code-insiders`, `cursor-agent`, `windsurf`, `qwen`, `opencode`, `codex`, `kiro-cli`, `shai`, `qodercli`, `vibe`) |
### `specify init` Arguments & Options
| Argument/Option | Type | Description |
| ---------------------- | -------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `<project-name>` | Argument | Name for your new project directory (optional if using `--here`, or use `.` for current directory) |
| `--ai` | Option | AI assistant to use: `claude`, `gemini`, `copilot`, `cursor-agent`, `qwen`, `opencode`, `codex`, `windsurf`, `kilocode`, `auggie`, `roo`, `codebuddy`, `amp`, `shai`, `q`, `agy`, `bob`, or `qoder` |
| `--ai` | Option | AI assistant to use: `claude`, `gemini`, `copilot`, `cursor-agent`, `qwen`, `opencode`, `codex`, `windsurf`, `kilocode`, `auggie`, `roo`, `codebuddy`, `amp`, `shai`, `kiro-cli` (`kiro` alias), `agy`, `bob`, `qodercli`, `vibe`, or `generic` (requires `--ai-commands-dir`) |
| `--ai-commands-dir` | Option | Directory for agent command files (required with `--ai generic`, e.g. `.myagent/commands/`) |
| `--script` | Option | Script variant to use: `sh` (bash/zsh) or `ps` (PowerShell) |
| `--ignore-agent-tools` | Flag | Skip checks for AI agent tools like Claude Code |
| `--no-git` | Flag | Skip git repository initialization |
@@ -203,20 +224,32 @@ specify init my-project --ai claude
specify init my-project --ai cursor-agent
# Initialize with Qoder support
specify init my-project --ai qoder
specify init my-project --ai qodercli
# Initialize with Windsurf support
specify init my-project --ai windsurf
# Initialize with Kiro CLI support
specify init my-project --ai kiro-cli
# Initialize with Amp support
specify init my-project --ai amp
# Initialize with SHAI support
specify init my-project --ai shai
# Initialize with Mistral Vibe support
specify init my-project --ai vibe
# Initialize with IBM Bob support
specify init my-project --ai bob
# Initialize with Antigravity support
specify init my-project --ai agy
# Initialize with an unsupported agent (generic / bring your own agent)
specify init my-project --ai generic --ai-commands-dir .myagent/commands/
# Initialize with PowerShell scripts (Windows/cross-platform)
specify init my-project --ai copilot --script ps
@@ -388,7 +421,7 @@ specify init . --force --ai claude
specify init --here --force --ai claude
```
The CLI will check if you have Claude Code, Gemini CLI, Cursor CLI, Qwen CLI, opencode, Codex CLI, Qoder CLI, or Amazon Q Developer CLI installed. If you do not, or you prefer to get the templates without checking for the right tools, use `--ignore-agent-tools` with your command:
The CLI will check if you have Claude Code, Gemini CLI, Cursor CLI, Qwen CLI, opencode, Codex CLI, Qoder CLI, Tabnine CLI, Kiro CLI, or Mistral Vibe installed. If you do not, or you prefer to get the templates without checking for the right tools, use `--ignore-agent-tools` with your command:
```bash
specify init <project_name> --ai claude --ignore-agent-tools

View File

@@ -81,6 +81,9 @@ Then, use the `/speckit.implement` slash command to execute the plan.
/speckit.implement
```
> [!TIP]
> **Phased Implementation**: For complex projects, implement in phases to avoid overwhelming the agent's context. Start with core functionality, validate it works, then add features incrementally.
## Detailed Example: Building Taskify
Here's a complete example of building a team productivity platform:
@@ -135,7 +138,15 @@ Be specific about your tech stack and technical requirements:
/speckit.plan We are going to generate this using .NET Aspire, using Postgres as the database. The frontend should use Blazor server with drag-and-drop task boards, real-time updates. There should be a REST API created with a projects API, tasks API, and a notifications API.
```
### Step 6: Validate and Implement
### Step 6: Define Tasks
Generate an actionable task list using the `/speckit.tasks` command:
```bash
/speckit.tasks
```
### Step 7: Validate and Implement
Have your AI agent audit the implementation plan using `/speckit.analyze`:
@@ -149,6 +160,9 @@ Finally, implement the solution:
/speckit.implement
```
> [!TIP]
> **Phased Implementation**: For large projects like Taskify, consider implementing in phases (e.g., Phase 1: Basic project/task structure, Phase 2: Kanban functionality, Phase 3: Comments and assignments). This prevents context saturation and allows for validation at each stage.
## Key Principles
- **Be explicit** about what you're building and why

View File

@@ -243,6 +243,34 @@ manager.check_compatibility(
) # Raises: CompatibilityError if incompatible
```
### CatalogEntry
**Module**: `specify_cli.extensions`
Represents a single catalog in the active catalog stack.
```python
from specify_cli.extensions import CatalogEntry
entry = CatalogEntry(
url="https://example.com/catalog.json",
name="default",
priority=1,
install_allowed=True,
description="Built-in catalog of installable extensions",
)
```
**Fields**:
| Field | Type | Description |
|-------|------|-------------|
| `url` | `str` | Catalog URL (must use HTTPS, or HTTP for localhost) |
| `name` | `str` | Human-readable catalog name |
| `priority` | `int` | Sort order (lower = higher priority, wins on conflicts) |
| `install_allowed` | `bool` | Whether extensions from this catalog can be installed |
| `description` | `str` | Optional human-readable description of the catalog (default: empty) |
### ExtensionCatalog
**Module**: `specify_cli.extensions`
@@ -253,30 +281,67 @@ from specify_cli.extensions import ExtensionCatalog
catalog = ExtensionCatalog(project_root)
```
**Class attributes**:
```python
ExtensionCatalog.DEFAULT_CATALOG_URL # default catalog URL
ExtensionCatalog.COMMUNITY_CATALOG_URL # community catalog URL
```
**Methods**:
```python
# Fetch catalog
# Get the ordered list of active catalogs
entries = catalog.get_active_catalogs() # List[CatalogEntry]
# Fetch catalog (primary catalog, backward compat)
catalog_data = catalog.fetch_catalog(force_refresh: bool = False) # Dict
# Search extensions
# Search extensions across all active catalogs
# Each result includes _catalog_name and _install_allowed
results = catalog.search(
query: Optional[str] = None,
tag: Optional[str] = None,
author: Optional[str] = None,
verified_only: bool = False
) # Returns: List[Dict]
) # Returns: List[Dict] — each dict includes _catalog_name, _install_allowed
# Get extension info
# Get extension info (searches all active catalogs)
# Returns None if not found; includes _catalog_name and _install_allowed
ext_info = catalog.get_extension_info(extension_id: str) # Optional[Dict]
# Check cache validity
# Check cache validity (primary catalog)
is_valid = catalog.is_cache_valid() # bool
# Clear cache
# Clear all catalog caches
catalog.clear_cache()
```
**Result annotation fields**:
Each extension dict returned by `search()` and `get_extension_info()` includes:
| Field | Type | Description |
|-------|------|-------------|
| `_catalog_name` | `str` | Name of the source catalog |
| `_install_allowed` | `bool` | Whether installation is allowed from this catalog |
**Catalog config file** (`.specify/extension-catalogs.yml`):
```yaml
catalogs:
- name: "default"
url: "https://raw.githubusercontent.com/github/spec-kit/main/extensions/catalog.json"
priority: 1
install_allowed: true
description: "Built-in catalog of installable extensions"
- name: "community"
url: "https://raw.githubusercontent.com/github/spec-kit/main/extensions/catalog.community.json"
priority: 2
install_allowed: false
description: "Community-contributed extensions (discovery only)"
```
### HookExecutor
**Module**: `specify_cli.extensions`
@@ -543,6 +608,39 @@ EXECUTE_COMMAND: {command}
**Output**: List of installed extensions with metadata
### extension catalog list
**Usage**: `specify extension catalog list`
Lists all active catalogs in the current catalog stack, showing name, description, URL, priority, and `install_allowed` status.
### extension catalog add
**Usage**: `specify extension catalog add URL [OPTIONS]`
**Options**:
- `--name NAME` - Catalog name (required)
- `--priority INT` - Priority (lower = higher priority, default: 10)
- `--install-allowed / --no-install-allowed` - Allow installs from this catalog (default: false)
- `--description TEXT` - Optional description of the catalog
**Arguments**:
- `URL` - Catalog URL (must use HTTPS)
Adds a catalog entry to `.specify/extension-catalogs.yml`.
### extension catalog remove
**Usage**: `specify extension catalog remove NAME`
**Arguments**:
- `NAME` - Catalog name to remove
Removes a catalog entry from `.specify/extension-catalogs.yml`.
### extension add
**Usage**: `specify extension add EXTENSION [OPTIONS]`
@@ -551,13 +649,13 @@ EXECUTE_COMMAND: {command}
- `--from URL` - Install from custom URL
- `--dev PATH` - Install from local directory
- `--version VERSION` - Install specific version
- `--no-register` - Skip command registration
**Arguments**:
- `EXTENSION` - Extension name or URL
**Note**: Extensions from catalogs with `install_allowed: false` cannot be installed via this command.
### extension remove
**Usage**: `specify extension remove EXTENSION [OPTIONS]`
@@ -575,6 +673,8 @@ EXECUTE_COMMAND: {command}
**Usage**: `specify extension search [QUERY] [OPTIONS]`
Searches all active catalogs simultaneously. Results include source catalog name and install_allowed status.
**Options**:
- `--tag TAG` - Filter by tag
@@ -589,6 +689,8 @@ EXECUTE_COMMAND: {command}
**Usage**: `specify extension info EXTENSION`
Shows source catalog and install_allowed status.
**Arguments**:
- `EXTENSION` - Extension ID

View File

@@ -332,6 +332,67 @@ echo "$config"
---
## Excluding Files with `.extensionignore`
Extension authors can create a `.extensionignore` file in the extension root to exclude files and folders from being copied when a user installs the extension with `specify extension add`. This is useful for keeping development-only files (tests, CI configs, docs source, etc.) out of the installed copy.
### Format
The file uses `.gitignore`-compatible patterns (one per line), powered by the [`pathspec`](https://pypi.org/project/pathspec/) library:
- Blank lines are ignored
- Lines starting with `#` are comments
- `*` matches anything **except** `/` (does not cross directory boundaries)
- `**` matches zero or more directories (e.g., `docs/**/*.draft.md`)
- `?` matches any single character except `/`
- A trailing `/` restricts a pattern to directories only
- Patterns containing `/` (other than a trailing slash) are anchored to the extension root
- Patterns without `/` match at any depth in the tree
- `!` negates a previously excluded pattern (re-includes a file)
- Backslashes in patterns are normalised to forward slashes for cross-platform compatibility
- The `.extensionignore` file itself is always excluded automatically
### Example
```gitignore
# .extensionignore
# Development files
tests/
.github/
.gitignore
# Build artifacts
__pycache__/
*.pyc
dist/
# Documentation source (keep only the built README)
docs/
CONTRIBUTING.md
```
### Pattern Matching
| Pattern | Matches | Does NOT match |
|---------|---------|----------------|
| `*.pyc` | Any `.pyc` file in any directory | — |
| `tests/` | The `tests` directory (and all its contents) | A file named `tests` |
| `docs/*.draft.md` | `docs/api.draft.md` (directly inside `docs/`) | `docs/sub/api.draft.md` (nested) |
| `.env` | The `.env` file at any level | — |
| `!README.md` | Re-includes `README.md` even if matched by an earlier pattern | — |
| `docs/**/*.draft.md` | `docs/api.draft.md`, `docs/sub/api.draft.md` | — |
### Unsupported Features
The following `.gitignore` features are **not applicable** in this context:
- **Multiple `.extensionignore` files**: Only a single file at the extension root is supported (`.gitignore` supports files in subdirectories)
- **`$GIT_DIR/info/exclude` and `core.excludesFile`**: These are Git-specific and have no equivalent here
- **Negation inside excluded directories**: Because file copying uses `shutil.copytree`, excluding a directory prevents recursion into it entirely. A negation pattern cannot re-include a file inside a directory that was itself excluded. For example, the combination `tests/` followed by `!tests/important.py` will **not** preserve `tests/important.py` — the `tests/` directory is skipped at the root level and its contents are never evaluated. To work around this, exclude the directory's contents individually instead of the directory itself (e.g., `tests/*.pyc` and `tests/.cache/` rather than `tests/`).
---
## Validation Rules
### Extension ID
@@ -456,18 +517,20 @@ Users install with:
specify extension add --from https://github.com/.../spec-kit-my-ext-1.0.0.zip
```
### Option 3: Extension Catalog (Future)
### Option 3: Community Reference Catalog
Submit to official catalog:
Submit to the community catalog for public discovery:
1. **Fork** spec-kit repository
2. **Add entry** to `extensions/catalog.json`
3. **Create PR**
4. **After merge**, users can install with:
2. **Add entry** to `extensions/catalog.community.json`
3. **Update** `extensions/README.md` with your extension
4. **Create PR** following the [Extension Publishing Guide](EXTENSION-PUBLISHING-GUIDE.md)
5. **After merge**, your extension becomes available:
- Users can browse `catalog.community.json` to discover your extension
- Users copy the entry to their own `catalog.json`
- Users install with: `specify extension add my-ext` (from their catalog)
```bash
specify extension add my-ext # No URL needed!
```
See the [Extension Publishing Guide](EXTENSION-PUBLISHING-GUIDE.md) for detailed submission instructions.
---

View File

@@ -129,26 +129,32 @@ specify extension add --from https://github.com/your-org/spec-kit-your-extension
## Submit to Catalog
### Understanding the Catalogs
Spec Kit uses a dual-catalog system. For details about how catalogs work, see the main [Extensions README](README.md#extension-catalogs).
**For extension publishing**: All community extensions should be added to `catalog.community.json`. Users browse this catalog and copy extensions they trust into their own `catalog.json`.
### 1. Fork the spec-kit Repository
```bash
# Fork on GitHub
# https://github.com/statsperform/spec-kit/fork
# https://github.com/github/spec-kit/fork
# Clone your fork
git clone https://github.com/YOUR-USERNAME/spec-kit.git
cd spec-kit
```
### 2. Add Extension to Catalog
### 2. Add Extension to Community Catalog
Edit `extensions/catalog.json` and add your extension:
Edit `extensions/catalog.community.json` and add your extension:
```json
{
"schema_version": "1.0",
"updated_at": "2026-01-28T15:54:00Z",
"catalog_url": "https://raw.githubusercontent.com/statsperform/spec-kit/main/extensions/catalog.json",
"catalog_url": "https://raw.githubusercontent.com/github/spec-kit/main/extensions/catalog.community.json",
"extensions": {
"your-extension": {
"name": "Your Extension Name",
@@ -198,15 +204,25 @@ Edit `extensions/catalog.json` and add your extension:
- Use current timestamp for `created_at` and `updated_at`
- Update the top-level `updated_at` to current time
### 3. Submit Pull Request
### 3. Update Extensions README
Add your extension to the Available Extensions table in `extensions/README.md`:
```markdown
| Your Extension Name | Brief description of what it does | [repo-name](https://github.com/your-org/spec-kit-your-extension) |
```
Insert your extension in alphabetical order in the table.
### 4. Submit Pull Request
```bash
# Create a branch
git checkout -b add-your-extension
# Commit your changes
git add extensions/catalog.json
git commit -m "Add your-extension to catalog
git add extensions/catalog.community.json extensions/README.md
git commit -m "Add your-extension to community catalog
- Extension ID: your-extension
- Version: 1.0.0
@@ -218,7 +234,7 @@ git commit -m "Add your-extension to catalog
git push origin add-your-extension
# Create Pull Request on GitHub
# https://github.com/statsperform/spec-kit/compare
# https://github.com/github/spec-kit/compare
```
**Pull Request Template**:
@@ -243,6 +259,8 @@ Brief description of what your extension does.
- [x] Extension tested on real project
- [x] All commands working
- [x] No security vulnerabilities
- [x] Added to extensions/catalog.community.json
- [x] Added to extensions/README.md Available Extensions table
### Testing
Tested on:

View File

@@ -46,7 +46,7 @@ Extensions are modular packages that add new commands and functionality to Spec
### Check Your Version
```bash
specify --version
specify version
# Should show 0.1.0 or higher
```
@@ -76,13 +76,15 @@ vim .specify/extensions/jira/jira-config.yml
## Finding Extensions
`specify extension search` searches **all active catalogs** simultaneously, including the community catalog by default. Results are annotated with their source catalog and install status.
### Browse All Extensions
```bash
specify extension search
```
Shows all available extensions in the catalog.
Shows all extensions across all active catalogs (default and community by default).
### Search by Keyword
@@ -400,13 +402,13 @@ In addition to extension-specific environment variables (`SPECKIT_{EXT_ID}_*`),
| Variable | Description | Default |
|----------|-------------|---------|
| `SPECKIT_CATALOG_URL` | Override the extension catalog URL | GitHub-hosted catalog |
| `SPECKIT_CATALOG_URL` | Override the full catalog stack with a single URL (backward compat) | Built-in default stack |
| `GH_TOKEN` / `GITHUB_TOKEN` | GitHub API token for downloads | None |
#### Example: Using a custom catalog for testing
```bash
# Point to a local or alternative catalog
# Point to a local or alternative catalog (replaces the full stack)
export SPECKIT_CATALOG_URL="http://localhost:8000/catalog.json"
# Or use a staging catalog
@@ -415,11 +417,78 @@ export SPECKIT_CATALOG_URL="https://example.com/staging/catalog.json"
---
## Extension Catalogs
Spec Kit uses a **catalog stack** — an ordered list of catalogs searched simultaneously. By default, two catalogs are active:
| Priority | Catalog | Install Allowed | Purpose |
|----------|---------|-----------------|---------|
| 1 | `catalog.json` (default) | ✅ Yes | Curated extensions available for installation |
| 2 | `catalog.community.json` (community) | ❌ No (discovery only) | Browse community extensions |
### Listing Active Catalogs
```bash
specify extension catalog list
```
### Adding a Catalog (Project-scoped)
```bash
# Add an internal catalog that allows installs
specify extension catalog add \
--name "internal" \
--priority 2 \
--install-allowed \
https://internal.company.com/spec-kit/catalog.json
# Add a discovery-only catalog
specify extension catalog add \
--name "partner" \
--priority 5 \
https://partner.example.com/spec-kit/catalog.json
```
This creates or updates `.specify/extension-catalogs.yml`.
### Removing a Catalog
```bash
specify extension catalog remove internal
```
### Manual Config File
You can also edit `.specify/extension-catalogs.yml` directly:
```yaml
catalogs:
- name: "default"
url: "https://raw.githubusercontent.com/github/spec-kit/main/extensions/catalog.json"
priority: 1
install_allowed: true
description: "Built-in catalog of installable extensions"
- name: "internal"
url: "https://internal.company.com/spec-kit/catalog.json"
priority: 2
install_allowed: true
description: "Internal company extensions"
- name: "community"
url: "https://raw.githubusercontent.com/github/spec-kit/main/extensions/catalog.community.json"
priority: 3
install_allowed: false
description: "Community-contributed extensions (discovery only)"
```
A user-level equivalent lives at `~/.specify/extension-catalogs.yml`. Project-level config takes full precedence when it contains one or more catalog entries. An empty `catalogs: []` list falls back to built-in defaults.
## Organization Catalog Customization
### Why the Default Catalog is Empty
### Why Customize Your Catalog
The default spec-kit catalog ships empty by design. This allows organizations to:
Organizations customize their catalogs to:
- **Control available extensions** - Curate which extensions your team can install
- **Host private extensions** - Internal tools that shouldn't be public
@@ -497,24 +566,40 @@ Options for hosting your catalog:
#### 3. Configure Your Environment
##### Option A: Environment variable (recommended for CI/CD)
##### Option A: Catalog stack config file (recommended)
Add to `.specify/extension-catalogs.yml` in your project:
```yaml
catalogs:
- name: "my-org"
url: "https://your-org.com/spec-kit/catalog.json"
priority: 1
install_allowed: true
```
Or use the CLI:
```bash
specify extension catalog add \
--name "my-org" \
--install-allowed \
https://your-org.com/spec-kit/catalog.json
```
##### Option B: Environment variable (recommended for CI/CD, single-catalog)
```bash
# In ~/.bashrc, ~/.zshrc, or CI pipeline
export SPECKIT_CATALOG_URL="https://your-org.com/spec-kit/catalog.json"
```
##### Option B: Per-project configuration
Create `.env` or set in your shell before running spec-kit commands:
```bash
SPECKIT_CATALOG_URL="https://your-org.com/spec-kit/catalog.json" specify extension search
```
#### 4. Verify Configuration
```bash
# List active catalogs
specify extension catalog list
# Search should now show your catalog's extensions
specify extension search

129
extensions/README.md Normal file
View File

@@ -0,0 +1,129 @@
# Spec Kit Extensions
Extension system for [Spec Kit](https://github.com/github/spec-kit) - add new functionality without bloating the core framework.
## Extension Catalogs
Spec Kit provides two catalog files with different purposes:
### Your Catalog (`catalog.json`)
- **Purpose**: Default upstream catalog of extensions used by the Spec Kit CLI
- **Default State**: Empty by design in the upstream project - you or your organization populate a fork/copy with extensions you trust
- **Location (upstream)**: `extensions/catalog.json` in the GitHub-hosted spec-kit repo
- **CLI Default**: The `specify extension` commands use the upstream catalog URL by default, unless overridden
- **Org Catalog**: Point `SPECKIT_CATALOG_URL` at your organization's fork or hosted catalog JSON to use it instead of the upstream default
- **Customization**: Copy entries from the community catalog into your org catalog, or add your own extensions directly
**Example override:**
```bash
# Override the default upstream catalog with your organization's catalog
export SPECKIT_CATALOG_URL="https://your-org.com/spec-kit/catalog.json"
specify extension search # Now uses your organization's catalog instead of the upstream default
```
### Community Reference Catalog (`catalog.community.json`)
- **Purpose**: Browse available community-contributed extensions
- **Status**: Active - contains extensions submitted by the community
- **Location**: `extensions/catalog.community.json`
- **Usage**: Reference catalog for discovering available extensions
- **Submission**: Open to community contributions via Pull Request
**How It Works:**
## Making Extensions Available
You control which extensions your team can discover and install:
### Option 1: Curated Catalog (Recommended for Organizations)
Populate your `catalog.json` with approved extensions:
1. **Discover** extensions from various sources:
- Browse `catalog.community.json` for community extensions
- Find private/internal extensions in your organization's repos
- Discover extensions from trusted third parties
2. **Review** extensions and choose which ones you want to make available
3. **Add** those extension entries to your own `catalog.json`
4. **Team members** can now discover and install them:
- `specify extension search` shows your curated catalog
- `specify extension add <name>` installs from your catalog
**Benefits**: Full control over available extensions, team consistency, organizational approval workflow
**Example**: Copy an entry from `catalog.community.json` to your `catalog.json`, then your team can discover and install it by name.
### Option 2: Direct URLs (For Ad-hoc Use)
Skip catalog curation - team members install directly using URLs:
```bash
specify extension add --from https://github.com/org/spec-kit-ext/archive/refs/tags/v1.0.0.zip
```
**Benefits**: Quick for one-off testing or private extensions
**Tradeoff**: Extensions installed this way won't appear in `specify extension search` for other team members unless you also add them to your `catalog.json`.
## Available Community Extensions
The following community-contributed extensions are available in [`catalog.community.json`](catalog.community.json):
| Extension | Purpose | URL |
|-----------|---------|-----|
| Azure DevOps Integration | Sync user stories and tasks to Azure DevOps work items using OAuth authentication | [spec-kit-azure-devops](https://github.com/pragya247/spec-kit-azure-devops) |
| Cleanup Extension | Post-implementation quality gate that reviews changes, fixes small issues (scout rule), creates tasks for medium issues, and generates analysis for large issues | [spec-kit-cleanup](https://github.com/dsrednicki/spec-kit-cleanup) |
| Fleet Orchestrator | Orchestrate a full feature lifecycle with human-in-the-loop gates across all SpecKit phases | [spec-kit-fleet](https://github.com/sharathsatish/spec-kit-fleet) |
| Jira Integration | Create Jira Epics, Stories, and Issues from spec-kit specifications and task breakdowns with configurable hierarchy and custom field support | [spec-kit-jira](https://github.com/mbachorik/spec-kit-jira) |
| Ralph Loop | Autonomous implementation loop using AI agent CLI | [spec-kit-ralph](https://github.com/Rubiss/spec-kit-ralph) |
| Retrospective Extension | Post-implementation retrospective with spec adherence scoring, drift analysis, and human-gated spec updates | [spec-kit-retrospective](https://github.com/emi-dm/spec-kit-retrospective) |
| Review Extension | Post-implementation comprehensive code review with specialized agents for code quality, comments, tests, error handling, type design, and simplification | [spec-kit-review](https://github.com/ismaelJimenez/spec-kit-review) |
| Spec Sync | Detect and resolve drift between specs and implementation. AI-assisted resolution with human approval | [spec-kit-sync](https://github.com/bgervin/spec-kit-sync) |
| Understanding | Automated requirements quality analysis — 31 deterministic metrics against IEEE/ISO standards with experimental energy-based ambiguity detection | [understanding](https://github.com/Testimonial/understanding) |
| V-Model Extension Pack | Enforces V-Model paired generation of development specs and test specs with full traceability | [spec-kit-v-model](https://github.com/leocamello/spec-kit-v-model) |
| Verify Extension | Post-implementation quality gate that validates implemented code against specification artifacts | [spec-kit-verify](https://github.com/ismaelJimenez/spec-kit-verify) |
## Adding Your Extension
### Submission Process
To add your extension to the community catalog:
1. **Prepare your extension** following the [Extension Development Guide](EXTENSION-DEVELOPMENT-GUIDE.md)
2. **Create a GitHub release** for your extension
3. **Submit a Pull Request** that:
- Adds your extension to `extensions/catalog.community.json`
- Updates this README with your extension in the Available Extensions table
4. **Wait for review** - maintainers will review and merge if criteria are met
See the [Extension Publishing Guide](EXTENSION-PUBLISHING-GUIDE.md) for detailed step-by-step instructions.
### Submission Checklist
Before submitting, ensure:
- ✅ Valid `extension.yml` manifest
- ✅ Complete README with installation and usage instructions
- ✅ LICENSE file included
- ✅ GitHub release created with semantic version (e.g., v1.0.0)
- ✅ Extension tested on a real project
- ✅ All commands working as documented
## Installing Extensions
Once extensions are available (either in your catalog or via direct URL), install them:
```bash
# From your curated catalog (by name)
specify extension search # See what's in your catalog
specify extension add <extension-name> # Install by name
# Direct from URL (bypasses catalog)
specify extension add --from https://github.com/<org>/<repo>/archive/refs/tags/<version>.zip
# List installed extensions
specify extension list
```
For more information, see the [Extension User Guide](EXTENSION-USER-GUIDE.md).

View File

@@ -858,11 +858,41 @@ def should_execute_hook(hook: dict, config: dict) -> bool:
## Extension Discovery & Catalog
### Central Catalog
### Dual Catalog System
Spec Kit uses two catalog files with different purposes:
#### User Catalog (`catalog.json`)
**URL**: `https://raw.githubusercontent.com/github/spec-kit/main/extensions/catalog.json`
**Format**:
- **Purpose**: Organization's curated catalog of approved extensions
- **Default State**: Empty by design - users populate with extensions they trust
- **Usage**: Primary catalog (priority 1, `install_allowed: true`) in the default stack
- **Control**: Organizations maintain their own fork/version for their teams
#### Community Reference Catalog (`catalog.community.json`)
**URL**: `https://raw.githubusercontent.com/github/spec-kit/main/extensions/catalog.community.json`
- **Purpose**: Reference catalog of available community-contributed extensions
- **Verification**: Community extensions may have `verified: false` initially
- **Status**: Active - open for community contributions
- **Submission**: Via Pull Request following the Extension Publishing Guide
- **Usage**: Secondary catalog (priority 2, `install_allowed: false`) in the default stack — discovery only
**How It Works (default stack):**
1. **Discover**: `specify extension search` searches both catalogs — community extensions appear automatically
2. **Review**: Evaluate community extensions for security, quality, and organizational fit
3. **Curate**: Copy approved entries from community catalog to your `catalog.json`, or add to `.specify/extension-catalogs.yml` with `install_allowed: true`
4. **Install**: Use `specify extension add <name>` — only allowed from `install_allowed: true` catalogs
This approach gives organizations full control over which extensions can be installed while still providing community discoverability out of the box.
### Catalog Format
**Format** (same for both catalogs):
```json
{
@@ -931,24 +961,113 @@ specify extension info jira
### Custom Catalogs
Organizations can host private catalogs:
Spec Kit supports a **catalog stack** — an ordered list of catalogs that the CLI merges and searches across. This allows organizations to maintain their own org-approved extensions alongside an internal catalog and community discovery, all at once.
```bash
# Add custom catalog
specify extension add-catalog https://internal.company.com/spec-kit/catalog.json
#### Catalog Stack Resolution
# Set as default
specify extension set-catalog --default https://internal.company.com/spec-kit/catalog.json
The active catalog stack is resolved in this order (first match wins):
# List catalogs
specify extension catalogs
1. **`SPECKIT_CATALOG_URL` environment variable** — single catalog replacing all defaults (backward compat)
2. **Project-level `.specify/extension-catalogs.yml`** — full control for the project
3. **User-level `~/.specify/extension-catalogs.yml`** — personal defaults
4. **Built-in default stack** — `catalog.json` (install_allowed: true) + `catalog.community.json` (install_allowed: false)
#### Default Built-in Stack
When no config file exists, the CLI uses:
| Priority | Catalog | install_allowed | Purpose |
|----------|---------|-----------------|---------|
| 1 | `catalog.json` (default) | `true` | Curated extensions available for installation |
| 2 | `catalog.community.json` (community) | `false` | Discovery only — browse but not install |
This means `specify extension search` surfaces community extensions out of the box, while `specify extension add` is still restricted to entries from catalogs with `install_allowed: true`.
#### `.specify/extension-catalogs.yml` Config File
```yaml
catalogs:
- name: "default"
url: "https://raw.githubusercontent.com/github/spec-kit/main/extensions/catalog.json"
priority: 1 # Highest — only approved entries can be installed
install_allowed: true
description: "Built-in catalog of installable extensions"
- name: "internal"
url: "https://internal.company.com/spec-kit/catalog.json"
priority: 2
install_allowed: true
description: "Internal company extensions"
- name: "community"
url: "https://raw.githubusercontent.com/github/spec-kit/main/extensions/catalog.community.json"
priority: 3 # Lowest — discovery only, not installable
install_allowed: false
description: "Community-contributed extensions (discovery only)"
```
**Catalog priority**:
A user-level equivalent lives at `~/.specify/extension-catalogs.yml`. When a project-level config is present with one or more catalog entries, it takes full control and the built-in defaults are not applied. An empty `catalogs: []` list is treated the same as no config file, falling back to defaults.
1. Project-specific catalog (`.specify/extension-catalogs.yml`)
2. User-level catalog (`~/.specify/extension-catalogs.yml`)
3. Default GitHub catalog
#### Catalog CLI Commands
```bash
# List active catalogs with name, URL, priority, and install_allowed
specify extension catalog list
# Add a catalog (project-scoped)
specify extension catalog add --name "internal" --install-allowed \
https://internal.company.com/spec-kit/catalog.json
# Add a discovery-only catalog
specify extension catalog add --name "community" \
https://raw.githubusercontent.com/github/spec-kit/main/extensions/catalog.community.json
# Remove a catalog
specify extension catalog remove internal
# Show which catalog an extension came from
specify extension info jira
# → Source catalog: default
```
#### Merge Conflict Resolution
When the same extension `id` appears in multiple catalogs, the higher-priority (lower priority number) catalog wins. Extensions from lower-priority catalogs with the same `id` are ignored.
#### `install_allowed: false` Behavior
Extensions from discovery-only catalogs are shown in `specify extension search` results but cannot be installed directly:
```
⚠ 'linear' is available in the 'community' catalog but installation is not allowed from that catalog.
To enable installation, add 'linear' to an approved catalog (install_allowed: true) in .specify/extension-catalogs.yml.
```
#### `SPECKIT_CATALOG_URL` (Backward Compatibility)
The `SPECKIT_CATALOG_URL` environment variable still works — it is treated as a single `install_allowed: true` catalog, **replacing both defaults** for full backward compatibility:
```bash
# Point to your organization's catalog
export SPECKIT_CATALOG_URL="https://internal.company.com/spec-kit/catalog.json"
# All extension commands now use your custom catalog
specify extension search # Uses custom catalog
specify extension add jira # Installs from custom catalog
```
**Requirements:**
- URL must use HTTPS (HTTP only allowed for localhost testing)
- Catalog must follow the standard catalog.json schema
- Must be publicly accessible or accessible within your network
**Example for testing:**
```bash
# Test with localhost during development
export SPECKIT_CATALOG_URL="http://localhost:8000/catalog.json"
specify extension search
```
---

View File

@@ -0,0 +1,366 @@
{
"schema_version": "1.0",
"updated_at": "2026-03-09T00:00:00Z",
"catalog_url": "https://raw.githubusercontent.com/github/spec-kit/main/extensions/catalog.community.json",
"extensions": {
"azure-devops": {
"name": "Azure DevOps Integration",
"id": "azure-devops",
"description": "Sync user stories and tasks to Azure DevOps work items using OAuth authentication.",
"author": "pragya247",
"version": "1.0.0",
"download_url": "https://github.com/pragya247/spec-kit-azure-devops/archive/refs/tags/v1.0.0.zip",
"repository": "https://github.com/pragya247/spec-kit-azure-devops",
"homepage": "https://github.com/pragya247/spec-kit-azure-devops",
"documentation": "https://github.com/pragya247/spec-kit-azure-devops/blob/main/README.md",
"changelog": "https://github.com/pragya247/spec-kit-azure-devops/blob/main/CHANGELOG.md",
"license": "MIT",
"requires": {
"speckit_version": ">=0.1.0",
"tools": [
{
"name": "az",
"version": ">=2.0.0",
"required": true
}
]
},
"provides": {
"commands": 1,
"hooks": 1
},
"tags": [
"azure",
"devops",
"project-management",
"work-items",
"issue-tracking"
],
"verified": false,
"downloads": 0,
"stars": 0,
"created_at": "2026-03-03T00:00:00Z",
"updated_at": "2026-03-03T00:00:00Z"
},
"cleanup": {
"name": "Cleanup Extension",
"id": "cleanup",
"description": "Post-implementation quality gate that reviews changes, fixes small issues (scout rule), creates tasks for medium issues, and generates analysis for large issues.",
"author": "dsrednicki",
"version": "1.0.0",
"download_url": "https://github.com/dsrednicki/spec-kit-cleanup/archive/refs/tags/v1.0.0.zip",
"repository": "https://github.com/dsrednicki/spec-kit-cleanup",
"homepage": "https://github.com/dsrednicki/spec-kit-cleanup",
"documentation": "https://github.com/dsrednicki/spec-kit-cleanup/blob/main/README.md",
"changelog": "https://github.com/dsrednicki/spec-kit-cleanup/blob/main/CHANGELOG.md",
"license": "MIT",
"requires": {
"speckit_version": ">=0.1.0"
},
"provides": {
"commands": 1,
"hooks": 1
},
"tags": [
"quality",
"tech-debt",
"review",
"cleanup",
"scout-rule"
],
"verified": false,
"downloads": 0,
"stars": 0,
"created_at": "2026-02-22T00:00:00Z",
"updated_at": "2026-02-22T00:00:00Z"
},
"fleet": {
"name": "Fleet Orchestrator",
"id": "fleet",
"description": "Orchestrate a full feature lifecycle with human-in-the-loop gates across all SpecKit phases.",
"author": "sharathsatish",
"version": "1.0.0",
"download_url": "https://github.com/sharathsatish/spec-kit-fleet/archive/refs/tags/v1.0.0.zip",
"repository": "https://github.com/sharathsatish/spec-kit-fleet",
"homepage": "https://github.com/sharathsatish/spec-kit-fleet",
"documentation": "https://github.com/sharathsatish/spec-kit-fleet/blob/main/README.md",
"changelog": "https://github.com/sharathsatish/spec-kit-fleet/blob/main/CHANGELOG.md",
"license": "MIT",
"requires": {
"speckit_version": ">=0.1.0"
},
"provides": {
"commands": 2,
"hooks": 1
},
"tags": ["orchestration", "workflow", "human-in-the-loop", "parallel"],
"verified": false,
"downloads": 0,
"stars": 0,
"created_at": "2026-03-06T00:00:00Z",
"updated_at": "2026-03-06T00:00:00Z"
},
"jira": {
"name": "Jira Integration",
"id": "jira",
"description": "Create Jira Epics, Stories, and Issues from spec-kit specifications and task breakdowns with configurable hierarchy and custom field support.",
"author": "mbachorik",
"version": "2.1.0",
"download_url": "https://github.com/mbachorik/spec-kit-jira/archive/refs/tags/v2.1.0.zip",
"repository": "https://github.com/mbachorik/spec-kit-jira",
"homepage": "https://github.com/mbachorik/spec-kit-jira",
"documentation": "https://github.com/mbachorik/spec-kit-jira/blob/main/README.md",
"changelog": "https://github.com/mbachorik/spec-kit-jira/blob/main/CHANGELOG.md",
"license": "MIT",
"requires": {
"speckit_version": ">=0.1.0"
},
"provides": {
"commands": 3,
"hooks": 1
},
"tags": [
"issue-tracking",
"jira",
"atlassian",
"project-management"
],
"verified": false,
"downloads": 0,
"stars": 0,
"created_at": "2026-03-05T00:00:00Z",
"updated_at": "2026-03-05T00:00:00Z"
},
"ralph": {
"name": "Ralph Loop",
"id": "ralph",
"description": "Autonomous implementation loop using AI agent CLI.",
"author": "Rubiss",
"version": "1.0.0",
"download_url": "https://github.com/Rubiss/spec-kit-ralph/archive/refs/tags/v1.0.0.zip",
"repository": "https://github.com/Rubiss/spec-kit-ralph",
"homepage": "https://github.com/Rubiss/spec-kit-ralph",
"documentation": "https://github.com/Rubiss/spec-kit-ralph/blob/main/README.md",
"changelog": "https://github.com/Rubiss/spec-kit-ralph/blob/main/CHANGELOG.md",
"license": "MIT",
"requires": {
"speckit_version": ">=0.1.0",
"tools": [
{
"name": "copilot",
"required": true
},
{
"name": "git",
"required": true
}
]
},
"provides": {
"commands": 2,
"hooks": 1
},
"tags": ["implementation", "automation", "loop", "copilot"],
"verified": false,
"downloads": 0,
"stars": 0,
"created_at": "2026-03-09T00:00:00Z",
"updated_at": "2026-03-09T00:00:00Z"
},
"retrospective": {
"name": "Retrospective Extension",
"id": "retrospective",
"description": "Post-implementation retrospective with spec adherence scoring, drift analysis, and human-gated spec updates.",
"author": "emi-dm",
"version": "1.0.0",
"download_url": "https://github.com/emi-dm/spec-kit-retrospective/archive/refs/tags/v1.0.0.zip",
"repository": "https://github.com/emi-dm/spec-kit-retrospective",
"homepage": "https://github.com/emi-dm/spec-kit-retrospective",
"documentation": "https://github.com/emi-dm/spec-kit-retrospective/blob/main/README.md",
"changelog": "https://github.com/emi-dm/spec-kit-retrospective/blob/main/CHANGELOG.md",
"license": "MIT",
"requires": {
"speckit_version": ">=0.1.0"
},
"provides": {
"commands": 1,
"hooks": 1
},
"tags": [
"retrospective",
"spec-drift",
"quality",
"analysis",
"governance"
],
"verified": false,
"downloads": 0,
"stars": 0,
"created_at": "2026-02-24T00:00:00Z",
"updated_at": "2026-02-24T00:00:00Z"
},
"review": {
"name": "Review Extension",
"id": "review",
"description": "Post-implementation comprehensive code review with specialized agents for code quality, comments, tests, error handling, type design, and simplification.",
"author": "ismaelJimenez",
"version": "1.0.0",
"download_url": "https://github.com/ismaelJimenez/spec-kit-review/archive/refs/tags/v1.0.0.zip",
"repository": "https://github.com/ismaelJimenez/spec-kit-review",
"homepage": "https://github.com/ismaelJimenez/spec-kit-review",
"documentation": "https://github.com/ismaelJimenez/spec-kit-review/blob/main/README.md",
"changelog": "https://github.com/ismaelJimenez/spec-kit-review/blob/main/CHANGELOG.md",
"license": "MIT",
"requires": {
"speckit_version": ">=0.1.0"
},
"provides": {
"commands": 7,
"hooks": 1
},
"tags": ["code-review", "quality", "review", "testing", "error-handling", "type-design", "simplification"],
"verified": false,
"downloads": 0,
"stars": 0,
"created_at": "2026-03-06T00:00:00Z",
"updated_at": "2026-03-06T00:00:00Z"
},
"sync": {
"name": "Spec Sync",
"id": "sync",
"description": "Detect and resolve drift between specs and implementation. AI-assisted resolution with human approval.",
"author": "bgervin",
"version": "0.1.0",
"download_url": "https://github.com/bgervin/spec-kit-sync/archive/refs/tags/v0.1.0.zip",
"repository": "https://github.com/bgervin/spec-kit-sync",
"homepage": "https://github.com/bgervin/spec-kit-sync",
"documentation": "https://github.com/bgervin/spec-kit-sync/blob/main/README.md",
"changelog": "https://github.com/bgervin/spec-kit-sync/blob/main/CHANGELOG.md",
"license": "MIT",
"requires": {
"speckit_version": ">=0.1.0"
},
"provides": {
"commands": 5,
"hooks": 1
},
"tags": [
"sync",
"drift",
"validation",
"bidirectional",
"backfill"
],
"verified": false,
"downloads": 0,
"stars": 0,
"created_at": "2026-03-02T00:00:00Z",
"updated_at": "2026-03-02T00:00:00Z"
},
"understanding": {
"name": "Understanding",
"id": "understanding",
"description": "Automated requirements quality analysis — validates specs against IEEE/ISO standards using 31 deterministic metrics. Catches ambiguity, missing testability, and structural issues before they reach implementation. Includes experimental energy-based ambiguity detection using local LM token perplexity.",
"author": "Ladislav Bihari",
"version": "3.4.0",
"download_url": "https://github.com/Testimonial/understanding/archive/refs/tags/v3.4.0.zip",
"repository": "https://github.com/Testimonial/understanding",
"homepage": "https://github.com/Testimonial/understanding",
"documentation": "https://github.com/Testimonial/understanding/blob/main/extension/README.md",
"changelog": "https://github.com/Testimonial/understanding/blob/main/extension/CHANGELOG.md",
"license": "MIT",
"requires": {
"speckit_version": ">=0.1.0",
"tools": [
{
"name": "understanding",
"version": ">=3.4.0",
"required": true
}
]
},
"provides": {
"commands": 3,
"hooks": 1
},
"tags": [
"quality",
"metrics",
"requirements",
"validation",
"readability",
"IEEE-830",
"ISO-29148"
],
"verified": false,
"downloads": 0,
"stars": 0,
"created_at": "2026-03-07T00:00:00Z",
"updated_at": "2026-03-07T00:00:00Z"
},
"v-model": {
"name": "V-Model Extension Pack",
"id": "v-model",
"description": "Enforces V-Model paired generation of development specs and test specs with full traceability.",
"author": "leocamello",
"version": "0.4.0",
"download_url": "https://github.com/leocamello/spec-kit-v-model/archive/refs/tags/v0.4.0.zip",
"repository": "https://github.com/leocamello/spec-kit-v-model",
"homepage": "https://github.com/leocamello/spec-kit-v-model",
"documentation": "https://github.com/leocamello/spec-kit-v-model/blob/main/README.md",
"changelog": "https://github.com/leocamello/spec-kit-v-model/blob/main/CHANGELOG.md",
"license": "MIT",
"requires": {
"speckit_version": ">=0.1.0"
},
"provides": {
"commands": 9,
"hooks": 1
},
"tags": [
"v-model",
"traceability",
"testing",
"compliance",
"safety-critical"
],
"verified": false,
"downloads": 0,
"stars": 0,
"created_at": "2026-02-20T00:00:00Z",
"updated_at": "2026-02-22T00:00:00Z"
},
"verify": {
"name": "Verify Extension",
"id": "verify",
"description": "Post-implementation quality gate that validates implemented code against specification artifacts.",
"author": "ismaelJimenez",
"version": "1.0.0",
"download_url": "https://github.com/ismaelJimenez/spec-kit-verify/archive/refs/tags/v1.0.0.zip",
"repository": "https://github.com/ismaelJimenez/spec-kit-verify",
"homepage": "https://github.com/ismaelJimenez/spec-kit-verify",
"documentation": "https://github.com/ismaelJimenez/spec-kit-verify/blob/main/README.md",
"changelog": "https://github.com/ismaelJimenez/spec-kit-verify/blob/main/CHANGELOG.md",
"license": "MIT",
"requires": {
"speckit_version": ">=0.1.0"
},
"provides": {
"commands": 1,
"hooks": 1
},
"tags": [
"verification",
"quality-gate",
"implementation",
"spec-adherence",
"compliance"
],
"verified": false,
"downloads": 0,
"stars": 0,
"created_at": "2026-03-03T00:00:00Z",
"updated_at": "2026-03-03T00:00:00Z"
}
}
}

View File

@@ -1,60 +0,0 @@
{
"schema_version": "1.0",
"updated_at": "2026-02-03T00:00:00Z",
"catalog_url": "https://your-org.example.com/speckit/catalog.json",
"extensions": {
"jira": {
"name": "Jira Integration",
"id": "jira",
"description": "Create Jira Epics, Stories, and Issues from spec-kit artifacts",
"author": "Your Organization",
"version": "2.1.0",
"download_url": "https://github.com/your-org/spec-kit-jira/archive/refs/tags/v2.1.0.zip",
"repository": "https://github.com/your-org/spec-kit-jira",
"homepage": "https://github.com/your-org/spec-kit-jira",
"documentation": "https://github.com/your-org/spec-kit-jira/blob/main/README.md",
"changelog": "https://github.com/your-org/spec-kit-jira/blob/main/CHANGELOG.md",
"license": "MIT",
"requires": {
"speckit_version": ">=0.1.0",
"tools": [
{
"name": "atlassian",
"version": ">=1.0.0",
"required": true
}
]
},
"provides": {
"commands": 3,
"hooks": 1
},
"tags": ["jira", "atlassian", "issue-tracking"],
"verified": true,
"downloads": 0,
"stars": 0,
"created_at": "2026-01-28T00:00:00Z",
"updated_at": "2026-02-03T00:00:00Z"
},
"linear": {
"name": "Linear Integration",
"id": "linear",
"description": "Sync specs and tasks with Linear issues",
"author": "Your Organization",
"version": "1.0.0",
"download_url": "https://github.com/your-org/spec-kit-linear/archive/refs/tags/v1.0.0.zip",
"repository": "https://github.com/your-org/spec-kit-linear",
"license": "MIT",
"requires": {
"speckit_version": ">=0.1.0"
},
"provides": {
"commands": 2
},
"tags": ["linear", "issue-tracking"],
"verified": false,
"created_at": "2026-01-30T00:00:00Z",
"updated_at": "2026-01-30T00:00:00Z"
}
}
}

157
presets/ARCHITECTURE.md Normal file
View File

@@ -0,0 +1,157 @@
# Preset System Architecture
This document describes the internal architecture of the preset system — how template resolution, command registration, and catalog management work under the hood.
For usage instructions, see [README.md](README.md).
## Template Resolution
When Spec Kit needs a template (e.g. `spec-template`), the `PresetResolver` walks a priority stack and returns the first match:
```mermaid
flowchart TD
A["resolve_template('spec-template')"] --> B{Override exists?}
B -- Yes --> C[".specify/templates/overrides/spec-template.md"]
B -- No --> D{Preset provides it?}
D -- Yes --> E[".specify/presets/preset-id/templates/spec-template.md"]
D -- No --> F{Extension provides it?}
F -- Yes --> G[".specify/extensions/ext-id/templates/spec-template.md"]
F -- No --> H[".specify/templates/spec-template.md"]
E -- "multiple presets?" --> I["lowest priority number wins"]
I --> E
style C fill:#4caf50,color:#fff
style E fill:#2196f3,color:#fff
style G fill:#ff9800,color:#fff
style H fill:#9e9e9e,color:#fff
```
| Priority | Source | Path | Use case |
|----------|--------|------|----------|
| 1 (highest) | Override | `.specify/templates/overrides/` | One-off project-local tweaks |
| 2 | Preset | `.specify/presets/<id>/templates/` | Shareable, stackable customizations |
| 3 | Extension | `.specify/extensions/<id>/templates/` | Extension-provided templates |
| 4 (lowest) | Core | `.specify/templates/` | Shipped defaults |
When multiple presets are installed, they're sorted by their `priority` field (lower number = higher precedence). This is set via `--priority` on `specify preset add`.
The resolution is implemented three times to ensure consistency:
- **Python**: `PresetResolver` in `src/specify_cli/presets.py`
- **Bash**: `resolve_template()` in `scripts/bash/common.sh`
- **PowerShell**: `Resolve-Template` in `scripts/powershell/common.ps1`
## Command Registration
When a preset is installed with `type: "command"` entries, the `PresetManager` registers them into all detected agent directories using the shared `CommandRegistrar` from `src/specify_cli/agents.py`.
```mermaid
flowchart TD
A["specify preset add my-preset"] --> B{Preset has type: command?}
B -- No --> Z["done (templates only)"]
B -- Yes --> C{Extension command?}
C -- "speckit.myext.cmd\n(3+ dot segments)" --> D{Extension installed?}
D -- No --> E["skip (extension not active)"]
D -- Yes --> F["register command"]
C -- "speckit.specify\n(core command)" --> F
F --> G["detect agent directories"]
G --> H[".claude/commands/"]
G --> I[".gemini/commands/"]
G --> J[".github/agents/"]
G --> K["... (17+ agents)"]
H --> L["write .md (Markdown format)"]
I --> M["write .toml (TOML format)"]
J --> N["write .agent.md + .prompt.md"]
style E fill:#ff5722,color:#fff
style L fill:#4caf50,color:#fff
style M fill:#4caf50,color:#fff
style N fill:#4caf50,color:#fff
```
### Extension safety check
Command names follow the pattern `speckit.<ext-id>.<cmd-name>`. When a command has 3+ dot segments, the system extracts the extension ID and checks if `.specify/extensions/<ext-id>/` exists. If the extension isn't installed, the command is skipped — preventing orphan files referencing non-existent extensions.
Core commands (e.g. `speckit.specify`, with only 2 segments) are always registered.
### Agent format rendering
The `CommandRegistrar` renders commands differently per agent:
| Agent | Format | Extension | Arg placeholder |
|-------|--------|-----------|-----------------|
| Claude, Cursor, opencode, Windsurf, etc. | Markdown | `.md` | `$ARGUMENTS` |
| Copilot | Markdown | `.agent.md` + `.prompt.md` | `$ARGUMENTS` |
| Gemini, Qwen, Tabnine | TOML | `.toml` | `{{args}}` |
### Cleanup on removal
When `specify preset remove` is called, the registered commands are read from the registry metadata and the corresponding files are deleted from each agent directory, including Copilot companion `.prompt.md` files.
## Catalog System
```mermaid
flowchart TD
A["specify preset search"] --> B["PresetCatalog.get_active_catalogs()"]
B --> C{SPECKIT_PRESET_CATALOG_URL set?}
C -- Yes --> D["single custom catalog"]
C -- No --> E{.specify/preset-catalogs.yml exists?}
E -- Yes --> F["project-level catalog stack"]
E -- No --> G{"~/.specify/preset-catalogs.yml exists?"}
G -- Yes --> H["user-level catalog stack"]
G -- No --> I["built-in defaults"]
I --> J["default (install allowed)"]
I --> K["community (discovery only)"]
style D fill:#ff9800,color:#fff
style F fill:#2196f3,color:#fff
style H fill:#2196f3,color:#fff
style J fill:#4caf50,color:#fff
style K fill:#9e9e9e,color:#fff
```
Catalogs are fetched with a 1-hour cache (per-URL, SHA256-hashed cache files). Each catalog entry has a `priority` (for merge ordering) and `install_allowed` flag.
## Repository Layout
```
presets/
├── ARCHITECTURE.md # This file
├── PUBLISHING.md # Guide for submitting presets to the catalog
├── README.md # User guide
├── catalog.json # Official preset catalog
├── catalog.community.json # Community preset catalog
├── scaffold/ # Scaffold for creating new presets
│ ├── preset.yml # Example manifest
│ ├── README.md # Guide for customizing the scaffold
│ ├── commands/
│ │ ├── speckit.specify.md # Core command override example
│ │ └── speckit.myext.myextcmd.md # Extension command override example
│ └── templates/
│ ├── spec-template.md # Core template override example
│ └── myext-template.md # Extension template override example
└── self-test/ # Self-test preset (overrides all core templates)
├── preset.yml
├── commands/
│ └── speckit.specify.md
└── templates/
├── spec-template.md
├── plan-template.md
├── tasks-template.md
├── checklist-template.md
├── constitution-template.md
└── agent-file-template.md
```
## Module Structure
```
src/specify_cli/
├── agents.py # CommandRegistrar — shared infrastructure for writing
│ # command files to agent directories
├── presets.py # PresetManifest, PresetRegistry, PresetManager,
│ # PresetCatalog, PresetCatalogEntry, PresetResolver
└── __init__.py # CLI commands: specify preset list/add/remove/search/
# resolve/info, specify preset catalog list/add/remove
```

295
presets/PUBLISHING.md Normal file
View File

@@ -0,0 +1,295 @@
# Preset Publishing Guide
This guide explains how to publish your preset to the Spec Kit preset catalog, making it discoverable by `specify preset search`.
## Table of Contents
1. [Prerequisites](#prerequisites)
2. [Prepare Your Preset](#prepare-your-preset)
3. [Submit to Catalog](#submit-to-catalog)
4. [Verification Process](#verification-process)
5. [Release Workflow](#release-workflow)
6. [Best Practices](#best-practices)
---
## Prerequisites
Before publishing a preset, ensure you have:
1. **Valid Preset**: A working preset with a valid `preset.yml` manifest
2. **Git Repository**: Preset hosted on GitHub (or other public git hosting)
3. **Documentation**: README.md with description and usage instructions
4. **License**: Open source license file (MIT, Apache 2.0, etc.)
5. **Versioning**: Semantic versioning (e.g., 1.0.0)
6. **Testing**: Preset tested on real projects with `specify preset add --dev`
---
## Prepare Your Preset
### 1. Preset Structure
Ensure your preset follows the standard structure:
```text
your-preset/
├── preset.yml # Required: Preset manifest
├── README.md # Required: Documentation
├── LICENSE # Required: License file
├── CHANGELOG.md # Recommended: Version history
├── templates/ # Template overrides
│ ├── spec-template.md
│ ├── plan-template.md
│ └── ...
└── commands/ # Command overrides (optional)
└── speckit.specify.md
```
Start from the [scaffold](scaffold/) if you're creating a new preset.
### 2. preset.yml Validation
Verify your manifest is valid:
```yaml
schema_version: "1.0"
preset:
id: "your-preset" # Unique lowercase-hyphenated ID
name: "Your Preset Name" # Human-readable name
version: "1.0.0" # Semantic version
description: "Brief description (one sentence)"
author: "Your Name or Organization"
repository: "https://github.com/your-org/spec-kit-preset-your-preset"
license: "MIT"
requires:
speckit_version: ">=0.1.0" # Required spec-kit version
provides:
templates:
- type: "template"
name: "spec-template"
file: "templates/spec-template.md"
description: "Custom spec template"
replaces: "spec-template"
tags: # 2-5 relevant tags
- "category"
- "workflow"
```
**Validation Checklist**:
-`id` is lowercase with hyphens only (no underscores, spaces, or special characters)
-`version` follows semantic versioning (X.Y.Z)
-`description` is concise (under 200 characters)
-`repository` URL is valid and public
- ✅ All template and command files exist in the preset directory
- ✅ Template names are lowercase with hyphens only
- ✅ Command names use dot notation (e.g. `speckit.specify`)
- ✅ Tags are lowercase and descriptive
### 3. Test Locally
```bash
# Install from local directory
specify preset add --dev /path/to/your-preset
# Verify templates resolve from your preset
specify preset resolve spec-template
# Verify preset info
specify preset info your-preset
# List installed presets
specify preset list
# Remove when done testing
specify preset remove your-preset
```
If your preset includes command overrides, verify they appear in the agent directories:
```bash
# Check Claude commands (if using Claude)
ls .claude/commands/speckit.*.md
# Check Copilot commands (if using Copilot)
ls .github/agents/speckit.*.agent.md
# Check Gemini commands (if using Gemini)
ls .gemini/commands/speckit.*.toml
```
### 4. Create GitHub Release
Create a GitHub release for your preset version:
```bash
# Tag the release
git tag v1.0.0
git push origin v1.0.0
```
The release archive URL will be:
```text
https://github.com/your-org/spec-kit-preset-your-preset/archive/refs/tags/v1.0.0.zip
```
### 5. Test Installation from Archive
```bash
specify preset add --from https://github.com/your-org/spec-kit-preset-your-preset/archive/refs/tags/v1.0.0.zip
```
---
## Submit to Catalog
### Understanding the Catalogs
Spec Kit uses a dual-catalog system:
- **`catalog.json`** — Official, verified presets (install allowed by default)
- **`catalog.community.json`** — Community-contributed presets (discovery only by default)
All community presets should be submitted to `catalog.community.json`.
### 1. Fork the spec-kit Repository
```bash
git clone https://github.com/YOUR-USERNAME/spec-kit.git
cd spec-kit
```
### 2. Add Preset to Community Catalog
Edit `presets/catalog.community.json` and add your preset.
> **⚠️ Entries must be sorted alphabetically by preset ID.** Insert your preset in the correct position within the `"presets"` object.
```json
{
"schema_version": "1.0",
"updated_at": "2026-03-10T00:00:00Z",
"catalog_url": "https://raw.githubusercontent.com/github/spec-kit/main/presets/catalog.community.json",
"presets": {
"your-preset": {
"name": "Your Preset Name",
"description": "Brief description of what your preset provides",
"author": "Your Name",
"version": "1.0.0",
"download_url": "https://github.com/your-org/spec-kit-preset-your-preset/archive/refs/tags/v1.0.0.zip",
"repository": "https://github.com/your-org/spec-kit-preset-your-preset",
"license": "MIT",
"requires": {
"speckit_version": ">=0.1.0"
},
"provides": {
"templates": 3,
"commands": 1
},
"tags": [
"category",
"workflow"
],
"created_at": "2026-03-10T00:00:00Z",
"updated_at": "2026-03-10T00:00:00Z"
}
}
}
```
### 3. Submit Pull Request
```bash
git checkout -b add-your-preset
git add presets/catalog.community.json
git commit -m "Add your-preset to community catalog
- Preset ID: your-preset
- Version: 1.0.0
- Author: Your Name
- Description: Brief description
"
git push origin add-your-preset
```
**Pull Request Checklist**:
```markdown
## Preset Submission
**Preset Name**: Your Preset Name
**Preset ID**: your-preset
**Version**: 1.0.0
**Repository**: https://github.com/your-org/spec-kit-preset-your-preset
### Checklist
- [ ] Valid preset.yml manifest
- [ ] README.md with description and usage
- [ ] LICENSE file included
- [ ] GitHub release created
- [ ] Preset tested with `specify preset add --dev`
- [ ] Templates resolve correctly (`specify preset resolve`)
- [ ] Commands register to agent directories (if applicable)
- [ ] Commands match template sections (command + template are coherent)
- [ ] Added to presets/catalog.community.json
```
---
## Verification Process
After submission, maintainers will review:
1. **Manifest validation** — valid `preset.yml`, all files exist
2. **Template quality** — templates are useful and well-structured
3. **Command coherence** — commands reference sections that exist in templates
4. **Security** — no malicious content, safe file operations
5. **Documentation** — clear README explaining what the preset does
Once verified, `verified: true` is set and the preset appears in `specify preset search`.
---
## Release Workflow
When releasing a new version:
1. Update `version` in `preset.yml`
2. Update CHANGELOG.md
3. Tag and push: `git tag v1.1.0 && git push origin v1.1.0`
4. Submit PR to update `version` and `download_url` in `presets/catalog.community.json`
---
## Best Practices
### Template Design
- **Keep sections clear** — use headings and placeholder text the LLM can replace
- **Match commands to templates** — if your preset overrides a command, make sure it references the sections in your template
- **Document customization points** — use HTML comments to guide users on what to change
### Naming
- Preset IDs should be descriptive: `healthcare-compliance`, `enterprise-safe`, `startup-lean`
- Avoid generic names: `my-preset`, `custom`, `test`
### Stacking
- Design presets to work well when stacked with others
- Only override templates you need to change
- Document which templates and commands your preset modifies
### Command Overrides
- Only override commands when the workflow needs to change, not just the output format
- If you only need different template sections, a template override is sufficient
- Test command overrides with multiple agents (Claude, Gemini, Copilot)

115
presets/README.md Normal file
View File

@@ -0,0 +1,115 @@
# Presets
Presets are stackable, priority-ordered collections of template and command overrides for Spec Kit. They let you customize both the artifacts produced by the Spec-Driven Development workflow (specs, plans, tasks, checklists, constitutions) and the commands that guide the LLM in creating them — without forking or modifying core files.
## How It Works
When Spec Kit needs a template (e.g. `spec-template`), it walks a resolution stack:
1. `.specify/templates/overrides/` — project-local one-off overrides
2. `.specify/presets/<preset-id>/templates/` — installed presets (sorted by priority)
3. `.specify/extensions/<ext-id>/templates/` — extension-provided templates
4. `.specify/templates/` — core templates shipped with Spec Kit
If no preset is installed, core templates are used — exactly the same behavior as before presets existed.
For detailed resolution and command registration flows, see [ARCHITECTURE.md](ARCHITECTURE.md).
## Command Overrides
Presets can also override the commands that guide the SDD workflow. Templates define *what* gets produced (specs, plans, constitutions); commands define *how* the LLM produces them (the step-by-step instructions).
When a preset includes `type: "command"` entries, the commands are automatically registered into all detected agent directories (`.claude/commands/`, `.gemini/commands/`, etc.) in the correct format (Markdown or TOML with appropriate argument placeholders). When the preset is removed, the registered commands are cleaned up.
## Quick Start
```bash
# Search available presets
specify preset search
# Install a preset from the catalog
specify preset add healthcare-compliance
# Install from a local directory (for development)
specify preset add --dev ./my-preset
# Install with a specific priority (lower = higher precedence)
specify preset add healthcare-compliance --priority 5
# List installed presets
specify preset list
# See which template a name resolves to
specify preset resolve spec-template
# Get detailed info about a preset
specify preset info healthcare-compliance
# Remove a preset
specify preset remove healthcare-compliance
```
## Stacking Presets
Multiple presets can be installed simultaneously. The `--priority` flag controls which one wins when two presets provide the same template (lower number = higher precedence):
```bash
specify preset add enterprise-safe --priority 10 # base layer
specify preset add healthcare-compliance --priority 5 # overrides enterprise-safe
specify preset add pm-workflow --priority 1 # overrides everything
```
Presets **override**, they don't merge. If two presets both provide `spec-template`, the one with the lowest priority number wins entirely.
## Catalog Management
Presets are discovered through catalogs. By default, Spec Kit uses the official and community catalogs:
```bash
# List active catalogs
specify preset catalog list
# Add a custom catalog
specify preset catalog add https://example.com/catalog.json --name my-org --install-allowed
# Remove a catalog
specify preset catalog remove my-org
```
## Creating a Preset
See [scaffold/](scaffold/) for a scaffold you can copy to create your own preset.
1. Copy `scaffold/` to a new directory
2. Edit `preset.yml` with your preset's metadata
3. Add or replace templates in `templates/`
4. Test locally with `specify preset add --dev .`
5. Verify with `specify preset resolve spec-template`
## Environment Variables
| Variable | Description |
|----------|-------------|
| `SPECKIT_PRESET_CATALOG_URL` | Override the catalog URL (replaces all defaults) |
## Configuration Files
| File | Scope | Description |
|------|-------|-------------|
| `.specify/preset-catalogs.yml` | Project | Custom catalog stack for this project |
| `~/.specify/preset-catalogs.yml` | User | Custom catalog stack for all projects |
## Future Considerations
The following enhancements are under consideration for future releases:
- **Composition strategies** — Allow presets to declare a `strategy` per template instead of the default `replace`:
| Type | `replace` | `prepend` | `append` | `wrap` |
|------|-----------|-----------|----------|--------|
| **template** | ✓ (default) | ✓ | ✓ | ✓ |
| **command** | ✓ (default) | ✓ | ✓ | ✓ |
| **script** | ✓ (default) | — | — | ✓ |
For artifacts and commands (which are LLM directives), `wrap` would inject preset content before and after the core template using a `{CORE_TEMPLATE}` placeholder. For scripts, `wrap` would run custom logic before/after the core script via a `$CORE_SCRIPT` variable.
- **Script overrides** — Enable presets to provide alternative versions of core scripts (e.g. `create-new-feature.sh`) for workflow customization. A `strategy: "wrap"` option could allow presets to run custom logic before/after the core script without fully replacing it.

View File

@@ -0,0 +1,6 @@
{
"schema_version": "1.0",
"updated_at": "2026-03-09T00:00:00Z",
"catalog_url": "https://raw.githubusercontent.com/github/spec-kit/main/presets/catalog.community.json",
"presets": {}
}

6
presets/catalog.json Normal file
View File

@@ -0,0 +1,6 @@
{
"schema_version": "1.0",
"updated_at": "2026-03-10T00:00:00Z",
"catalog_url": "https://raw.githubusercontent.com/github/spec-kit/main/presets/catalog.json",
"presets": {}
}

View File

@@ -0,0 +1,46 @@
# My Preset
A custom preset for Spec Kit. Copy this directory and customize it to create your own.
## Templates Included
| Template | Type | Description |
|----------|------|-------------|
| `spec-template` | template | Custom feature specification template (overrides core and extensions) |
| `myext-template` | template | Override of the myext extension's report template |
| `speckit.specify` | command | Custom specification command (overrides core) |
| `speckit.myext.myextcmd` | command | Override of the myext extension's myextcmd command |
## Development
1. Copy this directory: `cp -r presets/scaffold my-preset`
2. Edit `preset.yml` — set your preset's ID, name, description, and templates
3. Add or modify templates in `templates/`
4. Test locally: `specify preset add --dev ./my-preset`
5. Verify resolution: `specify preset resolve spec-template`
6. Remove when done testing: `specify preset remove my-preset`
## Manifest Reference (`preset.yml`)
Required fields:
- `schema_version` — always `"1.0"`
- `preset.id` — lowercase alphanumeric with hyphens
- `preset.name` — human-readable name
- `preset.version` — semantic version (e.g. `1.0.0`)
- `preset.description` — brief description
- `requires.speckit_version` — version constraint (e.g. `>=0.1.0`)
- `provides.templates` — list of templates with `type`, `name`, and `file`
## Template Types
- **template** — Document scaffolds (spec-template.md, plan-template.md, tasks-template.md, etc.)
- **command** — AI agent workflow prompts (e.g. speckit.specify, speckit.plan)
- **script** — Custom scripts (reserved for future use)
## Publishing
See the [Preset Publishing Guide](../PUBLISHING.md) for details on submitting to the catalog.
## License
MIT

View File

@@ -0,0 +1,20 @@
---
description: "Override of the myext extension's myextcmd command"
---
<!-- Preset override for speckit.myext.myextcmd -->
You are following a customized version of the myext extension's myextcmd command.
When executing this command:
1. Read the user's input from $ARGUMENTS
2. Follow the standard myextcmd workflow
3. Additionally, apply the following customizations from this preset:
- Add compliance checks before proceeding
- Include audit trail entries in the output
> CUSTOMIZE: Replace the instructions above with your own.
> This file overrides the command that the "myext" extension provides.
> When this preset is installed, all agents (Claude, Gemini, Copilot, etc.)
> will use this version instead of the extension's original.

View File

@@ -0,0 +1,23 @@
---
description: "Create a feature specification (preset override)"
scripts:
sh: scripts/bash/create-new-feature.sh "{ARGS}"
ps: scripts/powershell/create-new-feature.ps1 "{ARGS}"
---
## User Input
```text
$ARGUMENTS
```
Given the feature description above:
1. **Create the feature branch** by running the script:
- Bash: `{SCRIPT} --json --short-name "<short-name>" "<description>"`
- The JSON output contains BRANCH_NAME and SPEC_FILE paths.
2. **Read the spec-template** to see the sections you need to fill.
3. **Write the specification** to SPEC_FILE, replacing the placeholders in each section
(Overview, Requirements, Acceptance Criteria) with details from the user's description.

View File

@@ -0,0 +1,91 @@
schema_version: "1.0"
preset:
# CUSTOMIZE: Change 'my-preset' to your preset ID (lowercase, hyphen-separated)
id: "my-preset"
# CUSTOMIZE: Human-readable name for your preset
name: "My Preset"
# CUSTOMIZE: Update version when releasing (semantic versioning: X.Y.Z)
version: "1.0.0"
# CUSTOMIZE: Brief description (under 200 characters)
description: "Brief description of what your preset provides"
# CUSTOMIZE: Your name or organization name
author: "Your Name"
# CUSTOMIZE: GitHub repository URL (create before publishing)
repository: "https://github.com/your-org/spec-kit-preset-my-preset"
# REVIEW: License (MIT is recommended for open source)
license: "MIT"
# Requirements for this preset
requires:
# CUSTOMIZE: Minimum spec-kit version required
speckit_version: ">=0.1.0"
# Templates provided by this preset
provides:
templates:
# CUSTOMIZE: Define your template overrides
# Templates are document scaffolds (spec-template.md, plan-template.md, etc.)
- type: "template"
name: "spec-template"
file: "templates/spec-template.md"
description: "Custom feature specification template"
replaces: "spec-template" # Which core template this overrides (optional)
# ADD MORE TEMPLATES: Copy this block for each template
# - type: "template"
# name: "plan-template"
# file: "templates/plan-template.md"
# description: "Custom plan template"
# replaces: "plan-template"
# OVERRIDE EXTENSION TEMPLATES:
# Presets sit above extensions in the resolution stack, so you can
# override templates provided by any installed extension.
# For example, if the "myext" extension provides a spec-template,
# the preset's version above will take priority automatically.
# Override a template provided by the "myext" extension:
- type: "template"
name: "myext-template"
file: "templates/myext-template.md"
description: "Override myext's report template"
replaces: "myext-template"
# Command overrides (AI agent workflow prompts)
# Presets can override both core and extension commands.
# Commands are automatically registered into all detected agent
# directories (.claude/commands/, .gemini/commands/, etc.)
# Override a core command:
- type: "command"
name: "speckit.specify"
file: "commands/speckit.specify.md"
description: "Custom specification command"
replaces: "speckit.specify"
# Override an extension command (e.g. from the "myext" extension):
- type: "command"
name: "speckit.myext.myextcmd"
file: "commands/speckit.myext.myextcmd.md"
description: "Override myext's myextcmd command with custom workflow"
replaces: "speckit.myext.myextcmd"
# Script templates (reserved for future use)
# - type: "script"
# name: "create-new-feature"
# file: "scripts/bash/create-new-feature.sh"
# description: "Custom feature creation script"
# replaces: "create-new-feature"
# CUSTOMIZE: Add relevant tags (2-5 recommended)
# Used for discovery in catalog
tags:
- "example"
- "preset"

View File

@@ -0,0 +1,24 @@
# MyExt Report
> This template overrides the one provided by the "myext" extension.
> Customize it to match your needs.
## Summary
Brief summary of the report.
## Details
- Detail 1
- Detail 2
## Actions
- [ ] Action 1
- [ ] Action 2
<!--
CUSTOMIZE: This template takes priority over the myext extension's
version of myext-template. The extension's original is still available
if you remove this preset.
-->

View File

@@ -0,0 +1,18 @@
# Feature Specification: [FEATURE NAME]
**Created**: [DATE]
**Status**: Draft
## Overview
[Brief description of the feature]
## Requirements
- [ ] Requirement 1
- [ ] Requirement 2
## Acceptance Criteria
- [ ] Criterion 1
- [ ] Criterion 2

View File

@@ -0,0 +1,15 @@
---
description: "Self-test override of the specify command"
---
<!-- preset:self-test -->
You are following the self-test preset's version of the specify command.
When creating a specification, follow this process:
1. Read the user's requirements from $ARGUMENTS
2. Create a specification document using the spec-template
3. Include all standard sections plus the self-test marker
> This command is provided by the self-test preset.

View File

@@ -0,0 +1,61 @@
schema_version: "1.0"
preset:
id: "self-test"
name: "Self-Test Preset"
version: "1.0.0"
description: "A preset that overrides all core templates for testing purposes"
author: "github"
repository: "https://github.com/github/spec-kit"
license: "MIT"
requires:
speckit_version: ">=0.1.0"
provides:
templates:
- type: "template"
name: "spec-template"
file: "templates/spec-template.md"
description: "Self-test spec template"
replaces: "spec-template"
- type: "template"
name: "plan-template"
file: "templates/plan-template.md"
description: "Self-test plan template"
replaces: "plan-template"
- type: "template"
name: "tasks-template"
file: "templates/tasks-template.md"
description: "Self-test tasks template"
replaces: "tasks-template"
- type: "template"
name: "checklist-template"
file: "templates/checklist-template.md"
description: "Self-test checklist template"
replaces: "checklist-template"
- type: "template"
name: "constitution-template"
file: "templates/constitution-template.md"
description: "Self-test constitution template"
replaces: "constitution-template"
- type: "template"
name: "agent-file-template"
file: "templates/agent-file-template.md"
description: "Self-test agent file template"
replaces: "agent-file-template"
- type: "command"
name: "speckit.specify"
file: "commands/speckit.specify.md"
description: "Self-test override of the specify command"
replaces: "speckit.specify"
tags:
- "testing"
- "self-test"

View File

@@ -0,0 +1,9 @@
# Agent File (Self-Test Preset)
<!-- preset:self-test -->
> This template is provided by the self-test preset.
## Agent Instructions
Follow these guidelines when working on this project.

View File

@@ -0,0 +1,15 @@
# Checklist (Self-Test Preset)
<!-- preset:self-test -->
> This template is provided by the self-test preset.
## Pre-Implementation
- [ ] Spec reviewed
- [ ] Plan approved
## Post-Implementation
- [ ] Tests passing
- [ ] Documentation updated

View File

@@ -0,0 +1,15 @@
# Constitution (Self-Test Preset)
<!-- preset:self-test -->
> This template is provided by the self-test preset.
## Principles
1. Principle 1
2. Principle 2
## Guidelines
- Guideline 1
- Guideline 2

View File

@@ -0,0 +1,22 @@
# Implementation Plan (Self-Test Preset)
<!-- preset:self-test -->
> This template is provided by the self-test preset.
## Approach
Describe the implementation approach.
## Steps
1. Step 1
2. Step 2
## Dependencies
- Dependency 1
## Risks
- Risk 1

View File

@@ -0,0 +1,23 @@
# Feature Specification (Self-Test Preset)
<!-- preset:self-test -->
> This template is provided by the self-test preset.
## Overview
Brief description of the feature.
## Requirements
- Requirement 1
- Requirement 2
## Design
Describe the design approach.
## Acceptance Criteria
- [ ] Criterion 1
- [ ] Criterion 2

View File

@@ -0,0 +1,17 @@
# Tasks (Self-Test Preset)
<!-- preset:self-test -->
> This template is provided by the self-test preset.
## Task List
- [ ] Task 1
- [ ] Task 2
## Estimation
| Task | Estimate |
|------|----------|
| Task 1 | TBD |
| Task 2 | TBD |

View File

@@ -1,6 +1,6 @@
[project]
name = "specify-cli"
version = "0.1.2"
version = "0.2.1"
description = "Specify CLI, part of GitHub Spec Kit. A tool to bootstrap your projects for Spec-Driven Development (SDD)."
requires-python = ">=3.11"
dependencies = [
@@ -13,6 +13,7 @@ dependencies = [
"truststore>=0.10.4",
"pyyaml>=6.0",
"packaging>=23.0",
"pathspec>=0.12.0",
]
[project.scripts]
@@ -51,4 +52,3 @@ precision = 2
show_missing = true
skip_covered = false

View File

@@ -154,3 +154,77 @@ EOF
check_file() { [[ -f "$1" ]] && echo "$2" || echo "$2"; }
check_dir() { [[ -d "$1" && -n $(ls -A "$1" 2>/dev/null) ]] && echo "$2" || echo "$2"; }
# Resolve a template name to a file path using the priority stack:
# 1. .specify/templates/overrides/
# 2. .specify/presets/<preset-id>/templates/ (sorted by priority from .registry)
# 3. .specify/extensions/<ext-id>/templates/
# 4. .specify/templates/ (core)
resolve_template() {
local template_name="$1"
local repo_root="$2"
local base="$repo_root/.specify/templates"
# Priority 1: Project overrides
local override="$base/overrides/${template_name}.md"
[ -f "$override" ] && echo "$override" && return 0
# Priority 2: Installed presets (sorted by priority from .registry)
local presets_dir="$repo_root/.specify/presets"
if [ -d "$presets_dir" ]; then
local registry_file="$presets_dir/.registry"
if [ -f "$registry_file" ] && command -v python3 >/dev/null 2>&1; then
# Read preset IDs sorted by priority (lower number = higher precedence)
local sorted_presets
sorted_presets=$(SPECKIT_REGISTRY="$registry_file" python3 -c "
import json, sys, os
try:
with open(os.environ['SPECKIT_REGISTRY']) as f:
data = json.load(f)
presets = data.get('presets', {})
for pid, meta in sorted(presets.items(), key=lambda x: x[1].get('priority', 10)):
print(pid)
except Exception:
sys.exit(1)
" 2>/dev/null)
if [ $? -eq 0 ] && [ -n "$sorted_presets" ]; then
while IFS= read -r preset_id; do
local candidate="$presets_dir/$preset_id/templates/${template_name}.md"
[ -f "$candidate" ] && echo "$candidate" && return 0
done <<< "$sorted_presets"
else
# python3 returned empty list — fall through to directory scan
for preset in "$presets_dir"/*/; do
[ -d "$preset" ] || continue
local candidate="$preset/templates/${template_name}.md"
[ -f "$candidate" ] && echo "$candidate" && return 0
done
fi
else
# Fallback: alphabetical directory order (no python3 available)
for preset in "$presets_dir"/*/; do
[ -d "$preset" ] || continue
local candidate="$preset/templates/${template_name}.md"
[ -f "$candidate" ] && echo "$candidate" && return 0
done
fi
fi
# Priority 3: Extension-provided templates
local ext_dir="$repo_root/.specify/extensions"
if [ -d "$ext_dir" ]; then
for ext in "$ext_dir"/*/; do
[ -d "$ext" ] || continue
# Skip hidden directories (e.g. .backup, .cache)
case "$(basename "$ext")" in .*) continue;; esac
local candidate="$ext/templates/${template_name}.md"
[ -f "$candidate" ] && echo "$candidate" && return 0
done
fi
# Priority 4: Core templates
local core="$base/${template_name}.md"
[ -f "$core" ] && echo "$core" && return 0
return 1
}

View File

@@ -67,6 +67,13 @@ if [ -z "$FEATURE_DESCRIPTION" ]; then
exit 1
fi
# Trim whitespace and validate description is not empty (e.g., user passed only whitespace)
FEATURE_DESCRIPTION=$(echo "$FEATURE_DESCRIPTION" | xargs)
if [ -z "$FEATURE_DESCRIPTION" ]; then
echo "Error: Feature description cannot be empty or contain only whitespace" >&2
exit 1
fi
# Function to find the repository root by searching for existing project markers
find_repo_root() {
local dir="$1"
@@ -159,6 +166,7 @@ clean_branch_name() {
# to searching for repository markers so the workflow still functions in repositories that
# were initialised with --no-git.
SCRIPT_DIR="$(CDPATH="" cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
source "$SCRIPT_DIR/common.sh"
if git rev-parse --show-toplevel >/dev/null 2>&1; then
REPO_ROOT=$(git rev-parse --show-toplevel)
@@ -272,7 +280,16 @@ if [ ${#BRANCH_NAME} -gt $MAX_BRANCH_LENGTH ]; then
fi
if [ "$HAS_GIT" = true ]; then
git checkout -b "$BRANCH_NAME"
if ! git checkout -b "$BRANCH_NAME" 2>/dev/null; then
# Check if branch already exists
if git branch --list "$BRANCH_NAME" | grep -q .; then
>&2 echo "Error: Branch '$BRANCH_NAME' already exists. Please use a different feature name or specify a different number with --number."
exit 1
else
>&2 echo "Error: Failed to create git branch '$BRANCH_NAME'. Please check your git configuration and try again."
exit 1
fi
fi
else
>&2 echo "[specify] Warning: Git repository not detected; skipped branch creation for $BRANCH_NAME"
fi
@@ -280,9 +297,9 @@ fi
FEATURE_DIR="$SPECS_DIR/$BRANCH_NAME"
mkdir -p "$FEATURE_DIR"
TEMPLATE="$REPO_ROOT/.specify/templates/spec-template.md"
TEMPLATE=$(resolve_template "spec-template" "$REPO_ROOT")
SPEC_FILE="$FEATURE_DIR/spec.md"
if [ -f "$TEMPLATE" ]; then cp "$TEMPLATE" "$SPEC_FILE"; else touch "$SPEC_FILE"; fi
if [ -n "$TEMPLATE" ] && [ -f "$TEMPLATE" ]; then cp "$TEMPLATE" "$SPEC_FILE"; else touch "$SPEC_FILE"; fi
# Set the SPECIFY_FEATURE environment variable for the current session
export SPECIFY_FEATURE="$BRANCH_NAME"

View File

@@ -37,12 +37,12 @@ check_feature_branch "$CURRENT_BRANCH" "$HAS_GIT" || exit 1
mkdir -p "$FEATURE_DIR"
# Copy plan template if it exists
TEMPLATE="$REPO_ROOT/.specify/templates/plan-template.md"
if [[ -f "$TEMPLATE" ]]; then
TEMPLATE=$(resolve_template "plan-template" "$REPO_ROOT")
if [[ -n "$TEMPLATE" ]] && [[ -f "$TEMPLATE" ]]; then
cp "$TEMPLATE" "$IMPL_PLAN"
echo "Copied plan template to $IMPL_PLAN"
else
echo "Warning: Plan template not found at $TEMPLATE"
echo "Warning: Plan template not found"
# Create a basic plan file if template doesn't exist
touch "$IMPL_PLAN"
fi

View File

@@ -30,12 +30,12 @@
#
# 5. Multi-Agent Support
# - Handles agent-specific file paths and naming conventions
# - Supports: Claude, Gemini, Copilot, Cursor, Qwen, opencode, Codex, Windsurf, Kilo Code, Auggie CLI, Roo Code, CodeBuddy CLI, Qoder CLI, Amp, SHAI, Amazon Q Developer CLI, or Antigravity
# - Supports: Claude, Gemini, Copilot, Cursor, Qwen, opencode, Codex, Windsurf, Kilo Code, Auggie CLI, Roo Code, CodeBuddy CLI, Qoder CLI, Amp, SHAI, Tabnine CLI, Kiro CLI, Mistral Vibe, Antigravity or Generic
# - Can update single agents or all existing agent files
# - Creates default Claude file if no agent files exist
#
# Usage: ./update-agent-context.sh [agent_type]
# Agent types: claude|gemini|copilot|cursor-agent|qwen|opencode|codex|windsurf|kilocode|auggie|roo|codebuddy|amp|shai|q|agy|bob|qoder
# Agent types: claude|gemini|copilot|cursor-agent|qwen|opencode|codex|windsurf|kilocode|auggie|roo|codebuddy|amp|shai|tabnine|kiro-cli|agy|bob|vibe|qodercli|generic
# Leave empty to update all existing agent files
set -e
@@ -73,9 +73,11 @@ CODEBUDDY_FILE="$REPO_ROOT/CODEBUDDY.md"
QODER_FILE="$REPO_ROOT/QODER.md"
AMP_FILE="$REPO_ROOT/AGENTS.md"
SHAI_FILE="$REPO_ROOT/SHAI.md"
Q_FILE="$REPO_ROOT/AGENTS.md"
TABNINE_FILE="$REPO_ROOT/TABNINE.md"
KIRO_FILE="$REPO_ROOT/AGENTS.md"
AGY_FILE="$REPO_ROOT/.agent/rules/specify-rules.md"
BOB_FILE="$REPO_ROOT/AGENTS.md"
VIBE_FILE="$REPO_ROOT/.vibe/agents/specify-agents.md"
# Template file
TEMPLATE_FILE="$REPO_ROOT/.specify/templates/agent-file-template.md"
@@ -351,10 +353,19 @@ create_new_agent_file() {
# Convert \n sequences to actual newlines
newline=$(printf '\n')
sed -i.bak2 "s/\\\\n/${newline}/g" "$temp_file"
# Clean up backup files
rm -f "$temp_file.bak" "$temp_file.bak2"
# Prepend Cursor frontmatter for .mdc files so rules are auto-included
if [[ "$target_file" == *.mdc ]]; then
local frontmatter_file
frontmatter_file=$(mktemp) || return 1
printf '%s\n' "---" "description: Project Development Guidelines" "globs: [\"**/*\"]" "alwaysApply: true" "---" "" > "$frontmatter_file"
cat "$temp_file" >> "$frontmatter_file"
mv "$frontmatter_file" "$temp_file"
fi
return 0
}
@@ -492,13 +503,24 @@ update_existing_agent_file() {
changes_entries_added=true
fi
# Ensure Cursor .mdc files have YAML frontmatter for auto-inclusion
if [[ "$target_file" == *.mdc ]]; then
if ! head -1 "$temp_file" | grep -q '^---'; then
local frontmatter_file
frontmatter_file=$(mktemp) || { rm -f "$temp_file"; return 1; }
printf '%s\n' "---" "description: Project Development Guidelines" "globs: [\"**/*\"]" "alwaysApply: true" "---" "" > "$frontmatter_file"
cat "$temp_file" >> "$frontmatter_file"
mv "$frontmatter_file" "$temp_file"
fi
fi
# Move temp file to target atomically
if ! mv "$temp_file" "$target_file"; then
log_error "Failed to update target file"
rm -f "$temp_file"
return 1
fi
return 0
}
#==============================================================================
@@ -619,7 +641,7 @@ update_specific_agent() {
codebuddy)
update_agent_file "$CODEBUDDY_FILE" "CodeBuddy CLI"
;;
qoder)
qodercli)
update_agent_file "$QODER_FILE" "Qoder CLI"
;;
amp)
@@ -628,8 +650,11 @@ update_specific_agent() {
shai)
update_agent_file "$SHAI_FILE" "SHAI"
;;
q)
update_agent_file "$Q_FILE" "Amazon Q Developer CLI"
tabnine)
update_agent_file "$TABNINE_FILE" "Tabnine CLI"
;;
kiro-cli)
update_agent_file "$KIRO_FILE" "Kiro CLI"
;;
agy)
update_agent_file "$AGY_FILE" "Antigravity"
@@ -637,9 +662,15 @@ update_specific_agent() {
bob)
update_agent_file "$BOB_FILE" "IBM Bob"
;;
vibe)
update_agent_file "$VIBE_FILE" "Mistral Vibe"
;;
generic)
log_info "Generic agent: no predefined context file. Use the agent-specific update script for your agent."
;;
*)
log_error "Unknown agent type '$agent_type'"
log_error "Expected: claude|gemini|copilot|cursor-agent|qwen|opencode|codex|windsurf|kilocode|auggie|roo|amp|shai|q|agy|bob|qoder"
log_error "Expected: claude|gemini|copilot|cursor-agent|qwen|opencode|codex|windsurf|kilocode|auggie|roo|codebuddy|amp|shai|tabnine|kiro-cli|agy|bob|vibe|qodercli|generic"
exit 1
;;
esac
@@ -709,13 +740,18 @@ update_all_existing_agents() {
found_agent=true
fi
if [[ -f "$TABNINE_FILE" ]]; then
update_agent_file "$TABNINE_FILE" "Tabnine CLI"
found_agent=true
fi
if [[ -f "$QODER_FILE" ]]; then
update_agent_file "$QODER_FILE" "Qoder CLI"
found_agent=true
fi
if [[ -f "$Q_FILE" ]]; then
update_agent_file "$Q_FILE" "Amazon Q Developer CLI"
if [[ -f "$KIRO_FILE" ]]; then
update_agent_file "$KIRO_FILE" "Kiro CLI"
found_agent=true
fi
@@ -727,6 +763,11 @@ update_all_existing_agents() {
update_agent_file "$BOB_FILE" "IBM Bob"
found_agent=true
fi
if [[ -f "$VIBE_FILE" ]]; then
update_agent_file "$VIBE_FILE" "Mistral Vibe"
found_agent=true
fi
# If no agent files exist, create a default Claude file
if [[ "$found_agent" == false ]]; then
@@ -751,8 +792,7 @@ print_summary() {
fi
echo
log_info "Usage: $0 [claude|gemini|copilot|cursor-agent|qwen|opencode|codex|windsurf|kilocode|auggie|roo|codebuddy|amp|shai|q|agy|bob|qoder]"
log_info "Usage: $0 [claude|gemini|copilot|cursor-agent|qwen|opencode|codex|windsurf|kilocode|auggie|roo|codebuddy|amp|shai|tabnine|kiro-cli|agy|bob|vibe|qodercli|generic]"
}
#==============================================================================
@@ -804,4 +844,3 @@ main() {
if [[ "${BASH_SOURCE[0]}" == "${0}" ]]; then
main "$@"
fi

View File

@@ -135,3 +135,70 @@ function Test-DirHasFiles {
}
}
# Resolve a template name to a file path using the priority stack:
# 1. .specify/templates/overrides/
# 2. .specify/presets/<preset-id>/templates/ (sorted by priority from .registry)
# 3. .specify/extensions/<ext-id>/templates/
# 4. .specify/templates/ (core)
function Resolve-Template {
param(
[Parameter(Mandatory=$true)][string]$TemplateName,
[Parameter(Mandatory=$true)][string]$RepoRoot
)
$base = Join-Path $RepoRoot '.specify/templates'
# Priority 1: Project overrides
$override = Join-Path $base "overrides/$TemplateName.md"
if (Test-Path $override) { return $override }
# Priority 2: Installed presets (sorted by priority from .registry)
$presetsDir = Join-Path $RepoRoot '.specify/presets'
if (Test-Path $presetsDir) {
$registryFile = Join-Path $presetsDir '.registry'
$sortedPresets = @()
if (Test-Path $registryFile) {
try {
$registryData = Get-Content $registryFile -Raw | ConvertFrom-Json
$presets = $registryData.presets
if ($presets) {
$sortedPresets = $presets.PSObject.Properties |
Sort-Object { if ($_.Value.priority) { $_.Value.priority } else { 10 } } |
ForEach-Object { $_.Name }
}
} catch {
# Fallback: alphabetical directory order
$sortedPresets = @()
}
}
if ($sortedPresets.Count -gt 0) {
foreach ($presetId in $sortedPresets) {
$candidate = Join-Path $presetsDir "$presetId/templates/$TemplateName.md"
if (Test-Path $candidate) { return $candidate }
}
} else {
# Fallback: alphabetical directory order
foreach ($preset in Get-ChildItem -Path $presetsDir -Directory -ErrorAction SilentlyContinue | Where-Object { $_.Name -notlike '.*' }) {
$candidate = Join-Path $preset.FullName "templates/$TemplateName.md"
if (Test-Path $candidate) { return $candidate }
}
}
}
# Priority 3: Extension-provided templates
$extDir = Join-Path $RepoRoot '.specify/extensions'
if (Test-Path $extDir) {
foreach ($ext in Get-ChildItem -Path $extDir -Directory -ErrorAction SilentlyContinue | Where-Object { $_.Name -notlike '.*' } | Sort-Object Name) {
$candidate = Join-Path $ext.FullName "templates/$TemplateName.md"
if (Test-Path $candidate) { return $candidate }
}
}
# Priority 4: Core templates
$core = Join-Path $base "$TemplateName.md"
if (Test-Path $core) { return $core }
return $null
}

View File

@@ -35,6 +35,12 @@ if (-not $FeatureDescription -or $FeatureDescription.Count -eq 0) {
$featureDesc = ($FeatureDescription -join ' ').Trim()
# Validate description is not empty after trimming (e.g., user passed only whitespace)
if ([string]::IsNullOrWhiteSpace($featureDesc)) {
Write-Error "Error: Feature description cannot be empty or contain only whitespace"
exit 1
}
# Resolve repository root. Prefer git information when available, but fall back
# to searching for repository markers so the workflow still functions in repositories that
# were initialized with --no-git.
@@ -135,6 +141,9 @@ if (-not $fallbackRoot) {
exit 1
}
# Load common functions (includes Resolve-Template)
. "$PSScriptRoot/common.ps1"
try {
$repoRoot = git rev-parse --show-toplevel 2>$null
if ($LASTEXITCODE -eq 0) {
@@ -242,10 +251,26 @@ if ($branchName.Length -gt $maxBranchLength) {
}
if ($hasGit) {
$branchCreated = $false
try {
git checkout -b $branchName | Out-Null
git checkout -b $branchName 2>$null | Out-Null
if ($LASTEXITCODE -eq 0) {
$branchCreated = $true
}
} catch {
Write-Warning "Failed to create git branch: $branchName"
# Exception during git command
}
if (-not $branchCreated) {
# Check if branch already exists
$existingBranch = git branch --list $branchName 2>$null
if ($existingBranch) {
Write-Error "Error: Branch '$branchName' already exists. Please use a different feature name or specify a different number with -Number."
exit 1
} else {
Write-Error "Error: Failed to create git branch '$branchName'. Please check your git configuration and try again."
exit 1
}
}
} else {
Write-Warning "[specify] Warning: Git repository not detected; skipped branch creation for $branchName"
@@ -254,9 +279,9 @@ if ($hasGit) {
$featureDir = Join-Path $specsDir $branchName
New-Item -ItemType Directory -Path $featureDir -Force | Out-Null
$template = Join-Path $repoRoot '.specify/templates/spec-template.md'
$template = Resolve-Template -TemplateName 'spec-template' -RepoRoot $repoRoot
$specFile = Join-Path $featureDir 'spec.md'
if (Test-Path $template) {
if ($template -and (Test-Path $template)) {
Copy-Item $template $specFile -Force
} else {
New-Item -ItemType File -Path $specFile | Out-Null

View File

@@ -32,12 +32,12 @@ if (-not (Test-FeatureBranch -Branch $paths.CURRENT_BRANCH -HasGit $paths.HAS_GI
New-Item -ItemType Directory -Path $paths.FEATURE_DIR -Force | Out-Null
# Copy plan template if it exists, otherwise note it or create empty file
$template = Join-Path $paths.REPO_ROOT '.specify/templates/plan-template.md'
if (Test-Path $template) {
$template = Resolve-Template -TemplateName 'plan-template' -RepoRoot $paths.REPO_ROOT
if ($template -and (Test-Path $template)) {
Copy-Item $template $paths.IMPL_PLAN -Force
Write-Output "Copied plan template to $($paths.IMPL_PLAN)"
} else {
Write-Warning "Plan template not found at $template"
Write-Warning "Plan template not found"
# Create a basic plan file if template doesn't exist
New-Item -ItemType File -Path $paths.IMPL_PLAN -Force | Out-Null
}

View File

@@ -9,7 +9,7 @@ Mirrors the behavior of scripts/bash/update-agent-context.sh:
2. Plan Data Extraction
3. Agent File Management (create from template or update existing)
4. Content Generation (technology stack, recent changes, timestamp)
5. Multi-Agent Support (claude, gemini, copilot, cursor-agent, qwen, opencode, codex, windsurf, kilocode, auggie, roo, codebuddy, amp, shai, q, agy, bob, qoder)
5. Multi-Agent Support (claude, gemini, copilot, cursor-agent, qwen, opencode, codex, windsurf, kilocode, auggie, roo, codebuddy, amp, shai, tabnine, kiro-cli, agy, bob, vibe, qodercli, generic)
.PARAMETER AgentType
Optional agent key to update a single agent. If omitted, updates all existing agent files (creating a default Claude file if none exist).
@@ -25,7 +25,7 @@ Relies on common helper functions in common.ps1
#>
param(
[Parameter(Position=0)]
[ValidateSet('claude','gemini','copilot','cursor-agent','qwen','opencode','codex','windsurf','kilocode','auggie','roo','codebuddy','amp','shai','q','agy','bob','qoder')]
[ValidateSet('claude','gemini','copilot','cursor-agent','qwen','opencode','codex','windsurf','kilocode','auggie','roo','codebuddy','amp','shai','tabnine','kiro-cli','agy','bob','qodercli','vibe','generic')]
[string]$AgentType
)
@@ -58,9 +58,11 @@ $CODEBUDDY_FILE = Join-Path $REPO_ROOT 'CODEBUDDY.md'
$QODER_FILE = Join-Path $REPO_ROOT 'QODER.md'
$AMP_FILE = Join-Path $REPO_ROOT 'AGENTS.md'
$SHAI_FILE = Join-Path $REPO_ROOT 'SHAI.md'
$Q_FILE = Join-Path $REPO_ROOT 'AGENTS.md'
$TABNINE_FILE = Join-Path $REPO_ROOT 'TABNINE.md'
$KIRO_FILE = Join-Path $REPO_ROOT 'AGENTS.md'
$AGY_FILE = Join-Path $REPO_ROOT '.agent/rules/specify-rules.md'
$BOB_FILE = Join-Path $REPO_ROOT 'AGENTS.md'
$VIBE_FILE = Join-Path $REPO_ROOT '.vibe/agents/specify-agents.md'
$TEMPLATE_FILE = Join-Path $REPO_ROOT '.specify/templates/agent-file-template.md'
@@ -258,6 +260,12 @@ function New-AgentFile {
# Convert literal \n sequences introduced by Escape to real newlines
$content = $content -replace '\\n',[Environment]::NewLine
# Prepend Cursor frontmatter for .mdc files so rules are auto-included
if ($TargetFile -match '\.mdc$') {
$frontmatter = @('---','description: Project Development Guidelines','globs: ["**/*"]','alwaysApply: true','---','') -join [Environment]::NewLine
$content = $frontmatter + $content
}
$parent = Split-Path -Parent $TargetFile
if (-not (Test-Path $parent)) { New-Item -ItemType Directory -Path $parent | Out-Null }
Set-Content -LiteralPath $TargetFile -Value $content -NoNewline -Encoding utf8
@@ -334,6 +342,12 @@ function Update-ExistingAgentFile {
$newTechEntries | ForEach-Object { $output.Add($_) }
}
# Ensure Cursor .mdc files have YAML frontmatter for auto-inclusion
if ($TargetFile -match '\.mdc$' -and $output.Count -gt 0 -and $output[0] -ne '---') {
$frontmatter = @('---','description: Project Development Guidelines','globs: ["**/*"]','alwaysApply: true','---','')
$output.InsertRange(0, $frontmatter)
}
Set-Content -LiteralPath $TargetFile -Value ($output -join [Environment]::NewLine) -Encoding utf8
return $true
}
@@ -384,13 +398,16 @@ function Update-SpecificAgent {
'auggie' { Update-AgentFile -TargetFile $AUGGIE_FILE -AgentName 'Auggie CLI' }
'roo' { Update-AgentFile -TargetFile $ROO_FILE -AgentName 'Roo Code' }
'codebuddy' { Update-AgentFile -TargetFile $CODEBUDDY_FILE -AgentName 'CodeBuddy CLI' }
'qoder' { Update-AgentFile -TargetFile $QODER_FILE -AgentName 'Qoder CLI' }
'qodercli' { Update-AgentFile -TargetFile $QODER_FILE -AgentName 'Qoder CLI' }
'amp' { Update-AgentFile -TargetFile $AMP_FILE -AgentName 'Amp' }
'shai' { Update-AgentFile -TargetFile $SHAI_FILE -AgentName 'SHAI' }
'q' { Update-AgentFile -TargetFile $Q_FILE -AgentName 'Amazon Q Developer CLI' }
'tabnine' { Update-AgentFile -TargetFile $TABNINE_FILE -AgentName 'Tabnine CLI' }
'kiro-cli' { Update-AgentFile -TargetFile $KIRO_FILE -AgentName 'Kiro CLI' }
'agy' { Update-AgentFile -TargetFile $AGY_FILE -AgentName 'Antigravity' }
'bob' { Update-AgentFile -TargetFile $BOB_FILE -AgentName 'IBM Bob' }
default { Write-Err "Unknown agent type '$Type'"; Write-Err 'Expected: claude|gemini|copilot|cursor-agent|qwen|opencode|codex|windsurf|kilocode|auggie|roo|codebuddy|amp|shai|q|agy|bob|qoder'; return $false }
'vibe' { Update-AgentFile -TargetFile $VIBE_FILE -AgentName 'Mistral Vibe' }
'generic' { Write-Info 'Generic agent: no predefined context file. Use the agent-specific update script for your agent.' }
default { Write-Err "Unknown agent type '$Type'"; Write-Err 'Expected: claude|gemini|copilot|cursor-agent|qwen|opencode|codex|windsurf|kilocode|auggie|roo|codebuddy|amp|shai|tabnine|kiro-cli|agy|bob|vibe|qodercli|generic'; return $false }
}
}
@@ -410,9 +427,11 @@ function Update-AllExistingAgents {
if (Test-Path $CODEBUDDY_FILE) { if (-not (Update-AgentFile -TargetFile $CODEBUDDY_FILE -AgentName 'CodeBuddy CLI')) { $ok = $false }; $found = $true }
if (Test-Path $QODER_FILE) { if (-not (Update-AgentFile -TargetFile $QODER_FILE -AgentName 'Qoder CLI')) { $ok = $false }; $found = $true }
if (Test-Path $SHAI_FILE) { if (-not (Update-AgentFile -TargetFile $SHAI_FILE -AgentName 'SHAI')) { $ok = $false }; $found = $true }
if (Test-Path $Q_FILE) { if (-not (Update-AgentFile -TargetFile $Q_FILE -AgentName 'Amazon Q Developer CLI')) { $ok = $false }; $found = $true }
if (Test-Path $TABNINE_FILE) { if (-not (Update-AgentFile -TargetFile $TABNINE_FILE -AgentName 'Tabnine CLI')) { $ok = $false }; $found = $true }
if (Test-Path $KIRO_FILE) { if (-not (Update-AgentFile -TargetFile $KIRO_FILE -AgentName 'Kiro CLI')) { $ok = $false }; $found = $true }
if (Test-Path $AGY_FILE) { if (-not (Update-AgentFile -TargetFile $AGY_FILE -AgentName 'Antigravity')) { $ok = $false }; $found = $true }
if (Test-Path $BOB_FILE) { if (-not (Update-AgentFile -TargetFile $BOB_FILE -AgentName 'IBM Bob')) { $ok = $false }; $found = $true }
if (Test-Path $VIBE_FILE) { if (-not (Update-AgentFile -TargetFile $VIBE_FILE -AgentName 'Mistral Vibe')) { $ok = $false }; $found = $true }
if (-not $found) {
Write-Info 'No existing agent files found, creating default Claude file...'
if (-not (Update-AgentFile -TargetFile $CLAUDE_FILE -AgentName 'Claude Code')) { $ok = $false }
@@ -427,7 +446,7 @@ function Print-Summary {
if ($NEW_FRAMEWORK) { Write-Host " - Added framework: $NEW_FRAMEWORK" }
if ($NEW_DB -and $NEW_DB -ne 'N/A') { Write-Host " - Added database: $NEW_DB" }
Write-Host ''
Write-Info 'Usage: ./update-agent-context.ps1 [-AgentType claude|gemini|copilot|cursor-agent|qwen|opencode|codex|windsurf|kilocode|auggie|roo|codebuddy|amp|shai|q|agy|bob|qoder]'
Write-Info 'Usage: ./update-agent-context.ps1 [-AgentType claude|gemini|copilot|cursor-agent|qwen|opencode|codex|windsurf|kilocode|auggie|roo|codebuddy|amp|shai|tabnine|kiro-cli|agy|bob|vibe|qodercli|generic]'
}
function Main {
@@ -448,4 +467,3 @@ function Main {
}
Main

File diff suppressed because it is too large Load Diff

414
src/specify_cli/agents.py Normal file
View File

@@ -0,0 +1,414 @@
"""
Agent Command Registrar for Spec Kit
Shared infrastructure for registering commands with AI agents.
Used by both the extension system and the preset system to write
command files into agent-specific directories in the correct format.
"""
from pathlib import Path
from typing import Dict, List, Any
import yaml
class CommandRegistrar:
"""Handles registration of commands with AI agents.
Supports writing command files in Markdown or TOML format to the
appropriate agent directory, with correct argument placeholders
and companion files (e.g. Copilot .prompt.md).
"""
# Agent configurations with directory, format, and argument placeholder
AGENT_CONFIGS = {
"claude": {
"dir": ".claude/commands",
"format": "markdown",
"args": "$ARGUMENTS",
"extension": ".md"
},
"gemini": {
"dir": ".gemini/commands",
"format": "toml",
"args": "{{args}}",
"extension": ".toml"
},
"copilot": {
"dir": ".github/agents",
"format": "markdown",
"args": "$ARGUMENTS",
"extension": ".agent.md"
},
"cursor": {
"dir": ".cursor/commands",
"format": "markdown",
"args": "$ARGUMENTS",
"extension": ".md"
},
"qwen": {
"dir": ".qwen/commands",
"format": "toml",
"args": "{{args}}",
"extension": ".toml"
},
"opencode": {
"dir": ".opencode/command",
"format": "markdown",
"args": "$ARGUMENTS",
"extension": ".md"
},
"codex": {
"dir": ".codex/prompts",
"format": "markdown",
"args": "$ARGUMENTS",
"extension": ".md"
},
"windsurf": {
"dir": ".windsurf/workflows",
"format": "markdown",
"args": "$ARGUMENTS",
"extension": ".md"
},
"kilocode": {
"dir": ".kilocode/rules",
"format": "markdown",
"args": "$ARGUMENTS",
"extension": ".md"
},
"auggie": {
"dir": ".augment/rules",
"format": "markdown",
"args": "$ARGUMENTS",
"extension": ".md"
},
"roo": {
"dir": ".roo/rules",
"format": "markdown",
"args": "$ARGUMENTS",
"extension": ".md"
},
"codebuddy": {
"dir": ".codebuddy/commands",
"format": "markdown",
"args": "$ARGUMENTS",
"extension": ".md"
},
"qodercli": {
"dir": ".qoder/commands",
"format": "markdown",
"args": "$ARGUMENTS",
"extension": ".md"
},
"kiro-cli": {
"dir": ".kiro/prompts",
"format": "markdown",
"args": "$ARGUMENTS",
"extension": ".md"
},
"amp": {
"dir": ".agents/commands",
"format": "markdown",
"args": "$ARGUMENTS",
"extension": ".md"
},
"shai": {
"dir": ".shai/commands",
"format": "markdown",
"args": "$ARGUMENTS",
"extension": ".md"
},
"tabnine": {
"dir": ".tabnine/agent/commands",
"format": "toml",
"args": "{{args}}",
"extension": ".toml"
},
"bob": {
"dir": ".bob/commands",
"format": "markdown",
"args": "$ARGUMENTS",
"extension": ".md"
}
}
@staticmethod
def parse_frontmatter(content: str) -> tuple[dict, str]:
"""Parse YAML frontmatter from Markdown content.
Args:
content: Markdown content with YAML frontmatter
Returns:
Tuple of (frontmatter_dict, body_content)
"""
if not content.startswith("---"):
return {}, content
# Find second ---
end_marker = content.find("---", 3)
if end_marker == -1:
return {}, content
frontmatter_str = content[3:end_marker].strip()
body = content[end_marker + 3:].strip()
try:
frontmatter = yaml.safe_load(frontmatter_str) or {}
except yaml.YAMLError:
frontmatter = {}
return frontmatter, body
@staticmethod
def render_frontmatter(fm: dict) -> str:
"""Render frontmatter dictionary as YAML.
Args:
fm: Frontmatter dictionary
Returns:
YAML-formatted frontmatter with delimiters
"""
if not fm:
return ""
yaml_str = yaml.dump(fm, default_flow_style=False, sort_keys=False)
return f"---\n{yaml_str}---\n"
def _adjust_script_paths(self, frontmatter: dict) -> dict:
"""Adjust script paths from extension-relative to repo-relative.
Args:
frontmatter: Frontmatter dictionary
Returns:
Modified frontmatter with adjusted paths
"""
if "scripts" in frontmatter:
for key in frontmatter["scripts"]:
script_path = frontmatter["scripts"][key]
if script_path.startswith("../../scripts/"):
frontmatter["scripts"][key] = f".specify/scripts/{script_path[14:]}"
return frontmatter
def render_markdown_command(
self,
frontmatter: dict,
body: str,
source_id: str,
context_note: str = None
) -> str:
"""Render command in Markdown format.
Args:
frontmatter: Command frontmatter
body: Command body content
source_id: Source identifier (extension or preset ID)
context_note: Custom context comment (default: <!-- Source: {source_id} -->)
Returns:
Formatted Markdown command file content
"""
if context_note is None:
context_note = f"\n<!-- Source: {source_id} -->\n"
return self.render_frontmatter(frontmatter) + "\n" + context_note + body
def render_toml_command(
self,
frontmatter: dict,
body: str,
source_id: str
) -> str:
"""Render command in TOML format.
Args:
frontmatter: Command frontmatter
body: Command body content
source_id: Source identifier (extension or preset ID)
Returns:
Formatted TOML command file content
"""
toml_lines = []
if "description" in frontmatter:
desc = frontmatter["description"].replace('"', '\\"')
toml_lines.append(f'description = "{desc}"')
toml_lines.append("")
toml_lines.append(f"# Source: {source_id}")
toml_lines.append("")
toml_lines.append('prompt = """')
toml_lines.append(body)
toml_lines.append('"""')
return "\n".join(toml_lines)
def _convert_argument_placeholder(self, content: str, from_placeholder: str, to_placeholder: str) -> str:
"""Convert argument placeholder format.
Args:
content: Command content
from_placeholder: Source placeholder (e.g., "$ARGUMENTS")
to_placeholder: Target placeholder (e.g., "{{args}}")
Returns:
Content with converted placeholders
"""
return content.replace(from_placeholder, to_placeholder)
def register_commands(
self,
agent_name: str,
commands: List[Dict[str, Any]],
source_id: str,
source_dir: Path,
project_root: Path,
context_note: str = None
) -> List[str]:
"""Register commands for a specific agent.
Args:
agent_name: Agent name (claude, gemini, copilot, etc.)
commands: List of command info dicts with 'name', 'file', and optional 'aliases'
source_id: Identifier of the source (extension or preset ID)
source_dir: Directory containing command source files
project_root: Path to project root
context_note: Custom context comment for markdown output
Returns:
List of registered command names
Raises:
ValueError: If agent is not supported
"""
if agent_name not in self.AGENT_CONFIGS:
raise ValueError(f"Unsupported agent: {agent_name}")
agent_config = self.AGENT_CONFIGS[agent_name]
commands_dir = project_root / agent_config["dir"]
commands_dir.mkdir(parents=True, exist_ok=True)
registered = []
for cmd_info in commands:
cmd_name = cmd_info["name"]
cmd_file = cmd_info["file"]
source_file = source_dir / cmd_file
if not source_file.exists():
continue
content = source_file.read_text(encoding="utf-8")
frontmatter, body = self.parse_frontmatter(content)
frontmatter = self._adjust_script_paths(frontmatter)
body = self._convert_argument_placeholder(
body, "$ARGUMENTS", agent_config["args"]
)
if agent_config["format"] == "markdown":
output = self.render_markdown_command(frontmatter, body, source_id, context_note)
elif agent_config["format"] == "toml":
output = self.render_toml_command(frontmatter, body, source_id)
else:
raise ValueError(f"Unsupported format: {agent_config['format']}")
dest_file = commands_dir / f"{cmd_name}{agent_config['extension']}"
dest_file.write_text(output, encoding="utf-8")
if agent_name == "copilot":
self.write_copilot_prompt(project_root, cmd_name)
registered.append(cmd_name)
for alias in cmd_info.get("aliases", []):
alias_file = commands_dir / f"{alias}{agent_config['extension']}"
alias_file.write_text(output, encoding="utf-8")
if agent_name == "copilot":
self.write_copilot_prompt(project_root, alias)
registered.append(alias)
return registered
@staticmethod
def write_copilot_prompt(project_root: Path, cmd_name: str) -> None:
"""Generate a companion .prompt.md file for a Copilot agent command.
Args:
project_root: Path to project root
cmd_name: Command name (e.g. 'speckit.my-ext.example')
"""
prompts_dir = project_root / ".github" / "prompts"
prompts_dir.mkdir(parents=True, exist_ok=True)
prompt_file = prompts_dir / f"{cmd_name}.prompt.md"
prompt_file.write_text(f"---\nagent: {cmd_name}\n---\n", encoding="utf-8")
def register_commands_for_all_agents(
self,
commands: List[Dict[str, Any]],
source_id: str,
source_dir: Path,
project_root: Path,
context_note: str = None
) -> Dict[str, List[str]]:
"""Register commands for all detected agents in the project.
Args:
commands: List of command info dicts
source_id: Identifier of the source (extension or preset ID)
source_dir: Directory containing command source files
project_root: Path to project root
context_note: Custom context comment for markdown output
Returns:
Dictionary mapping agent names to list of registered commands
"""
results = {}
for agent_name, agent_config in self.AGENT_CONFIGS.items():
agent_dir = project_root / agent_config["dir"].split("/")[0]
if agent_dir.exists():
try:
registered = self.register_commands(
agent_name, commands, source_id, source_dir, project_root,
context_note=context_note
)
if registered:
results[agent_name] = registered
except ValueError:
continue
return results
def unregister_commands(
self,
registered_commands: Dict[str, List[str]],
project_root: Path
) -> None:
"""Remove previously registered command files from agent directories.
Args:
registered_commands: Dict mapping agent names to command name lists
project_root: Path to project root
"""
for agent_name, cmd_names in registered_commands.items():
if agent_name not in self.AGENT_CONFIGS:
continue
agent_config = self.AGENT_CONFIGS[agent_name]
commands_dir = project_root / agent_config["dir"]
for cmd_name in cmd_names:
cmd_file = commands_dir / f"{cmd_name}{agent_config['extension']}"
if cmd_file.exists():
cmd_file.unlink()
if agent_name == "copilot":
prompt_file = project_root / ".github" / "prompts" / f"{cmd_name}.prompt.md"
if prompt_file.exists():
prompt_file.unlink()

View File

@@ -8,14 +8,18 @@ without bloating the core framework.
import json
import hashlib
import os
import tempfile
import zipfile
import shutil
from dataclasses import dataclass
from pathlib import Path
from typing import Optional, Dict, List, Any
from typing import Optional, Dict, List, Any, Callable, Set
from datetime import datetime, timezone
import re
import pathspec
import yaml
from packaging import version as pkg_version
from packaging.specifiers import SpecifierSet, InvalidSpecifier
@@ -36,6 +40,16 @@ class CompatibilityError(ExtensionError):
pass
@dataclass
class CatalogEntry:
"""Represents a single catalog entry in the catalog stack."""
url: str
name: str
priority: int
install_allowed: bool
description: str = ""
class ExtensionManifest:
"""Represents and validates an extension manifest (extension.yml)."""
@@ -268,6 +282,70 @@ class ExtensionManager:
self.extensions_dir = project_root / ".specify" / "extensions"
self.registry = ExtensionRegistry(self.extensions_dir)
@staticmethod
def _load_extensionignore(source_dir: Path) -> Optional[Callable[[str, List[str]], Set[str]]]:
"""Load .extensionignore and return an ignore function for shutil.copytree.
The .extensionignore file uses .gitignore-compatible patterns (one per line).
Lines starting with '#' are comments. Blank lines are ignored.
The .extensionignore file itself is always excluded.
Pattern semantics mirror .gitignore:
- '*' matches anything except '/'
- '**' matches zero or more directories
- '?' matches any single character except '/'
- Trailing '/' restricts a pattern to directories only
- Patterns with '/' (other than trailing) are anchored to the root
- '!' negates a previously excluded pattern
Args:
source_dir: Path to the extension source directory
Returns:
An ignore function compatible with shutil.copytree, or None
if no .extensionignore file exists.
"""
ignore_file = source_dir / ".extensionignore"
if not ignore_file.exists():
return None
lines: List[str] = ignore_file.read_text().splitlines()
# Normalise backslashes in patterns so Windows-authored files work
normalised: List[str] = []
for line in lines:
stripped = line.strip()
if stripped and not stripped.startswith("#"):
normalised.append(stripped.replace("\\", "/"))
else:
# Preserve blanks/comments so pathspec line numbers stay stable
normalised.append(line)
# Always ignore the .extensionignore file itself
normalised.append(".extensionignore")
spec = pathspec.GitIgnoreSpec.from_lines(normalised)
def _ignore(directory: str, entries: List[str]) -> Set[str]:
ignored: Set[str] = set()
rel_dir = Path(directory).relative_to(source_dir)
for entry in entries:
rel_path = str(rel_dir / entry) if str(rel_dir) != "." else entry
# Normalise to forward slashes for consistent matching
rel_path_fwd = rel_path.replace("\\", "/")
entry_full = Path(directory) / entry
if entry_full.is_dir():
# Append '/' so directory-only patterns (e.g. tests/) match
if spec.match_file(rel_path_fwd + "/"):
ignored.add(entry)
else:
if spec.match_file(rel_path_fwd):
ignored.add(entry)
return ignored
return _ignore
def check_compatibility(
self,
manifest: ExtensionManifest,
@@ -341,7 +419,8 @@ class ExtensionManager:
if dest_dir.exists():
shutil.rmtree(dest_dir)
shutil.copytree(source_dir, dest_dir)
ignore_fn = self._load_extensionignore(source_dir)
shutil.copytree(source_dir, dest_dir, ignore=ignore_fn)
# Register commands with AI agents
registered_commands = {}
@@ -443,17 +522,7 @@ class ExtensionManager:
# Unregister commands from all AI agents
if registered_commands:
registrar = CommandRegistrar()
for agent_name, cmd_names in registered_commands.items():
if agent_name not in registrar.AGENT_CONFIGS:
continue
agent_config = registrar.AGENT_CONFIGS[agent_name]
commands_dir = self.project_root / agent_config["dir"]
for cmd_name in cmd_names:
cmd_file = commands_dir / f"{cmd_name}{agent_config['extension']}"
if cmd_file.exists():
cmd_file.unlink()
registrar.unregister_commands(registered_commands, self.project_root)
if keep_config:
# Preserve config files, only remove non-config files
@@ -577,237 +646,44 @@ def version_satisfies(current: str, required: str) -> bool:
class CommandRegistrar:
"""Handles registration of extension commands with AI agents."""
"""Handles registration of extension commands with AI agents.
# Agent configurations with directory, format, and argument placeholder
AGENT_CONFIGS = {
"claude": {
"dir": ".claude/commands",
"format": "markdown",
"args": "$ARGUMENTS",
"extension": ".md"
},
"gemini": {
"dir": ".gemini/commands",
"format": "toml",
"args": "{{args}}",
"extension": ".toml"
},
"copilot": {
"dir": ".github/agents",
"format": "markdown",
"args": "$ARGUMENTS",
"extension": ".md"
},
"cursor": {
"dir": ".cursor/commands",
"format": "markdown",
"args": "$ARGUMENTS",
"extension": ".md"
},
"qwen": {
"dir": ".qwen/commands",
"format": "toml",
"args": "{{args}}",
"extension": ".toml"
},
"opencode": {
"dir": ".opencode/command",
"format": "markdown",
"args": "$ARGUMENTS",
"extension": ".md"
},
"windsurf": {
"dir": ".windsurf/workflows",
"format": "markdown",
"args": "$ARGUMENTS",
"extension": ".md"
},
"kilocode": {
"dir": ".kilocode/rules",
"format": "markdown",
"args": "$ARGUMENTS",
"extension": ".md"
},
"auggie": {
"dir": ".augment/rules",
"format": "markdown",
"args": "$ARGUMENTS",
"extension": ".md"
},
"roo": {
"dir": ".roo/rules",
"format": "markdown",
"args": "$ARGUMENTS",
"extension": ".md"
},
"codebuddy": {
"dir": ".codebuddy/commands",
"format": "markdown",
"args": "$ARGUMENTS",
"extension": ".md"
},
"qoder": {
"dir": ".qoder/commands",
"format": "markdown",
"args": "$ARGUMENTS",
"extension": ".md"
},
"q": {
"dir": ".amazonq/prompts",
"format": "markdown",
"args": "$ARGUMENTS",
"extension": ".md"
},
"amp": {
"dir": ".agents/commands",
"format": "markdown",
"args": "$ARGUMENTS",
"extension": ".md"
},
"shai": {
"dir": ".shai/commands",
"format": "markdown",
"args": "$ARGUMENTS",
"extension": ".md"
},
"bob": {
"dir": ".bob/commands",
"format": "markdown",
"args": "$ARGUMENTS",
"extension": ".md"
}
}
This is a backward-compatible wrapper around the shared CommandRegistrar
in agents.py. Extension-specific methods accept ExtensionManifest objects
and delegate to the generic API.
"""
# Re-export AGENT_CONFIGS at class level for direct attribute access
from .agents import CommandRegistrar as _AgentRegistrar
AGENT_CONFIGS = _AgentRegistrar.AGENT_CONFIGS
def __init__(self):
from .agents import CommandRegistrar as _Registrar
self._registrar = _Registrar()
# Delegate static/utility methods
@staticmethod
def parse_frontmatter(content: str) -> tuple[dict, str]:
"""Parse YAML frontmatter from Markdown content.
Args:
content: Markdown content with YAML frontmatter
Returns:
Tuple of (frontmatter_dict, body_content)
"""
if not content.startswith("---"):
return {}, content
# Find second ---
end_marker = content.find("---", 3)
if end_marker == -1:
return {}, content
frontmatter_str = content[3:end_marker].strip()
body = content[end_marker + 3:].strip()
try:
frontmatter = yaml.safe_load(frontmatter_str) or {}
except yaml.YAMLError:
frontmatter = {}
return frontmatter, body
from .agents import CommandRegistrar as _Registrar
return _Registrar.parse_frontmatter(content)
@staticmethod
def render_frontmatter(fm: dict) -> str:
"""Render frontmatter dictionary as YAML.
from .agents import CommandRegistrar as _Registrar
return _Registrar.render_frontmatter(fm)
Args:
fm: Frontmatter dictionary
@staticmethod
def _write_copilot_prompt(project_root, cmd_name: str) -> None:
from .agents import CommandRegistrar as _Registrar
_Registrar.write_copilot_prompt(project_root, cmd_name)
Returns:
YAML-formatted frontmatter with delimiters
"""
if not fm:
return ""
yaml_str = yaml.dump(fm, default_flow_style=False, sort_keys=False)
return f"---\n{yaml_str}---\n"
def _adjust_script_paths(self, frontmatter: dict) -> dict:
"""Adjust script paths from extension-relative to repo-relative.
Args:
frontmatter: Frontmatter dictionary
Returns:
Modified frontmatter with adjusted paths
"""
if "scripts" in frontmatter:
for key in frontmatter["scripts"]:
script_path = frontmatter["scripts"][key]
if script_path.startswith("../../scripts/"):
frontmatter["scripts"][key] = f".specify/scripts/{script_path[14:]}"
return frontmatter
def _render_markdown_command(
self,
frontmatter: dict,
body: str,
ext_id: str
) -> str:
"""Render command in Markdown format.
Args:
frontmatter: Command frontmatter
body: Command body content
ext_id: Extension ID
Returns:
Formatted Markdown command file content
"""
def _render_markdown_command(self, frontmatter, body, ext_id):
# Preserve extension-specific comment format for backward compatibility
context_note = f"\n<!-- Extension: {ext_id} -->\n<!-- Config: .specify/extensions/{ext_id}/ -->\n"
return self.render_frontmatter(frontmatter) + "\n" + context_note + body
return self._registrar.render_frontmatter(frontmatter) + "\n" + context_note + body
def _render_toml_command(
self,
frontmatter: dict,
body: str,
ext_id: str
) -> str:
"""Render command in TOML format.
Args:
frontmatter: Command frontmatter
body: Command body content
ext_id: Extension ID
Returns:
Formatted TOML command file content
"""
# TOML format for Gemini/Qwen
toml_lines = []
# Add description if present
if "description" in frontmatter:
# Escape quotes in description
desc = frontmatter["description"].replace('"', '\\"')
toml_lines.append(f'description = "{desc}"')
toml_lines.append("")
# Add extension context as comments
toml_lines.append(f"# Extension: {ext_id}")
toml_lines.append(f"# Config: .specify/extensions/{ext_id}/")
toml_lines.append("")
# Add prompt content
toml_lines.append('prompt = """')
toml_lines.append(body)
toml_lines.append('"""')
return "\n".join(toml_lines)
def _convert_argument_placeholder(self, content: str, from_placeholder: str, to_placeholder: str) -> str:
"""Convert argument placeholder format.
Args:
content: Command content
from_placeholder: Source placeholder (e.g., "$ARGUMENTS")
to_placeholder: Target placeholder (e.g., "{{args}}")
Returns:
Content with converted placeholders
"""
return content.replace(from_placeholder, to_placeholder)
def _render_toml_command(self, frontmatter, body, ext_id):
return self._registrar.render_toml_command(frontmatter, body, ext_id)
def register_commands_for_agent(
self,
@@ -816,70 +692,14 @@ class CommandRegistrar:
extension_dir: Path,
project_root: Path
) -> List[str]:
"""Register extension commands for a specific agent.
Args:
agent_name: Agent name (claude, gemini, copilot, etc.)
manifest: Extension manifest
extension_dir: Path to extension directory
project_root: Path to project root
Returns:
List of registered command names
Raises:
ExtensionError: If agent is not supported
"""
"""Register extension commands for a specific agent."""
if agent_name not in self.AGENT_CONFIGS:
raise ExtensionError(f"Unsupported agent: {agent_name}")
agent_config = self.AGENT_CONFIGS[agent_name]
commands_dir = project_root / agent_config["dir"]
commands_dir.mkdir(parents=True, exist_ok=True)
registered = []
for cmd_info in manifest.commands:
cmd_name = cmd_info["name"]
cmd_file = cmd_info["file"]
# Read source command file
source_file = extension_dir / cmd_file
if not source_file.exists():
continue
content = source_file.read_text()
frontmatter, body = self.parse_frontmatter(content)
# Adjust script paths
frontmatter = self._adjust_script_paths(frontmatter)
# Convert argument placeholders
body = self._convert_argument_placeholder(
body, "$ARGUMENTS", agent_config["args"]
)
# Render in agent-specific format
if agent_config["format"] == "markdown":
output = self._render_markdown_command(frontmatter, body, manifest.id)
elif agent_config["format"] == "toml":
output = self._render_toml_command(frontmatter, body, manifest.id)
else:
raise ExtensionError(f"Unsupported format: {agent_config['format']}")
# Write command file
dest_file = commands_dir / f"{cmd_name}{agent_config['extension']}"
dest_file.write_text(output)
registered.append(cmd_name)
# Register aliases
for alias in cmd_info.get("aliases", []):
alias_file = commands_dir / f"{alias}{agent_config['extension']}"
alias_file.write_text(output)
registered.append(alias)
return registered
context_note = f"\n<!-- Extension: {manifest.id} -->\n<!-- Config: .specify/extensions/{manifest.id}/ -->\n"
return self._registrar.register_commands(
agent_name, manifest.commands, manifest.id, extension_dir, project_root,
context_note=context_note
)
def register_commands_for_all_agents(
self,
@@ -887,35 +707,20 @@ class CommandRegistrar:
extension_dir: Path,
project_root: Path
) -> Dict[str, List[str]]:
"""Register extension commands for all detected agents.
"""Register extension commands for all detected agents."""
context_note = f"\n<!-- Extension: {manifest.id} -->\n<!-- Config: .specify/extensions/{manifest.id}/ -->\n"
return self._registrar.register_commands_for_all_agents(
manifest.commands, manifest.id, extension_dir, project_root,
context_note=context_note
)
Args:
manifest: Extension manifest
extension_dir: Path to extension directory
project_root: Path to project root
Returns:
Dictionary mapping agent names to list of registered commands
"""
results = {}
# Detect which agents are present in the project
for agent_name, agent_config in self.AGENT_CONFIGS.items():
agent_dir = project_root / agent_config["dir"].split("/")[0]
# Register if agent directory exists
if agent_dir.exists():
try:
registered = self.register_commands_for_agent(
agent_name, manifest, extension_dir, project_root
)
if registered:
results[agent_name] = registered
except ExtensionError:
# Skip agent on error
continue
return results
def unregister_commands(
self,
registered_commands: Dict[str, List[str]],
project_root: Path
) -> None:
"""Remove previously registered command files from agent directories."""
self._registrar.unregister_commands(registered_commands, project_root)
def register_commands_for_claude(
self,
@@ -923,16 +728,7 @@ class CommandRegistrar:
extension_dir: Path,
project_root: Path
) -> List[str]:
"""Register extension commands for Claude Code agent.
Args:
manifest: Extension manifest
extension_dir: Path to extension directory
project_root: Path to project root
Returns:
List of registered command names
"""
"""Register extension commands for Claude Code agent."""
return self.register_commands_for_agent("claude", manifest, extension_dir, project_root)
@@ -940,6 +736,7 @@ class ExtensionCatalog:
"""Manages extension catalog fetching, caching, and searching."""
DEFAULT_CATALOG_URL = "https://raw.githubusercontent.com/github/spec-kit/main/extensions/catalog.json"
COMMUNITY_CATALOG_URL = "https://raw.githubusercontent.com/github/spec-kit/main/extensions/catalog.community.json"
CACHE_DURATION = 3600 # 1 hour in seconds
def __init__(self, project_root: Path):
@@ -954,43 +751,109 @@ class ExtensionCatalog:
self.cache_file = self.cache_dir / "catalog.json"
self.cache_metadata_file = self.cache_dir / "catalog-metadata.json"
def get_catalog_url(self) -> str:
"""Get catalog URL from config or use default.
def _validate_catalog_url(self, url: str) -> None:
"""Validate that a catalog URL uses HTTPS (localhost HTTP allowed).
Checks in order:
1. SPECKIT_CATALOG_URL environment variable
2. Default catalog URL
Returns:
URL to fetch catalog from
Args:
url: URL to validate
Raises:
ValidationError: If custom URL is invalid (non-HTTPS)
ValidationError: If URL is invalid or uses non-HTTPS scheme
"""
import os
import sys
from urllib.parse import urlparse
# Environment variable override (useful for testing)
parsed = urlparse(url)
is_localhost = parsed.hostname in ("localhost", "127.0.0.1", "::1")
if parsed.scheme != "https" and not (parsed.scheme == "http" and is_localhost):
raise ValidationError(
f"Catalog URL must use HTTPS (got {parsed.scheme}://). "
"HTTP is only allowed for localhost."
)
if not parsed.netloc:
raise ValidationError("Catalog URL must be a valid URL with a host.")
def _load_catalog_config(self, config_path: Path) -> Optional[List[CatalogEntry]]:
"""Load catalog stack configuration from a YAML file.
Args:
config_path: Path to extension-catalogs.yml
Returns:
Ordered list of CatalogEntry objects, or None if file doesn't exist
or contains no valid catalog entries.
Raises:
ValidationError: If any catalog entry has an invalid URL,
the file cannot be parsed, or a priority value is invalid.
"""
if not config_path.exists():
return None
try:
data = yaml.safe_load(config_path.read_text()) or {}
except (yaml.YAMLError, OSError) as e:
raise ValidationError(
f"Failed to read catalog config {config_path}: {e}"
)
catalogs_data = data.get("catalogs", [])
if not catalogs_data:
return None
if not isinstance(catalogs_data, list):
raise ValidationError(
f"Invalid catalog config: 'catalogs' must be a list, got {type(catalogs_data).__name__}"
)
entries: List[CatalogEntry] = []
for idx, item in enumerate(catalogs_data):
if not isinstance(item, dict):
raise ValidationError(
f"Invalid catalog entry at index {idx}: expected a mapping, got {type(item).__name__}"
)
url = str(item.get("url", "")).strip()
if not url:
continue
self._validate_catalog_url(url)
try:
priority = int(item.get("priority", idx + 1))
except (TypeError, ValueError):
raise ValidationError(
f"Invalid priority for catalog '{item.get('name', idx + 1)}': "
f"expected integer, got {item.get('priority')!r}"
)
raw_install = item.get("install_allowed", False)
if isinstance(raw_install, str):
install_allowed = raw_install.strip().lower() in ("true", "yes", "1")
else:
install_allowed = bool(raw_install)
entries.append(CatalogEntry(
url=url,
name=str(item.get("name", f"catalog-{idx + 1}")),
priority=priority,
install_allowed=install_allowed,
description=str(item.get("description", "")),
))
entries.sort(key=lambda e: e.priority)
return entries if entries else None
def get_active_catalogs(self) -> List[CatalogEntry]:
"""Get the ordered list of active catalogs.
Resolution order:
1. SPECKIT_CATALOG_URL env var — single catalog replacing all defaults
2. Project-level .specify/extension-catalogs.yml
3. User-level ~/.specify/extension-catalogs.yml
4. Built-in default stack (default + community)
Returns:
List of CatalogEntry objects sorted by priority (ascending)
Raises:
ValidationError: If a catalog URL is invalid
"""
import sys
# 1. SPECKIT_CATALOG_URL env var replaces all defaults for backward compat
if env_value := os.environ.get("SPECKIT_CATALOG_URL"):
catalog_url = env_value.strip()
parsed = urlparse(catalog_url)
# Require HTTPS for security (prevent man-in-the-middle attacks)
# Allow http://localhost for local development/testing
is_localhost = parsed.hostname in ("localhost", "127.0.0.1", "::1")
if parsed.scheme != "https" and not (parsed.scheme == "http" and is_localhost):
raise ValidationError(
f"Invalid SPECKIT_CATALOG_URL: must use HTTPS (got {parsed.scheme}://). "
"HTTP is only allowed for localhost."
)
if not parsed.netloc:
raise ValidationError(
"Invalid SPECKIT_CATALOG_URL: must be a valid URL with a host."
)
# Warn users when using a non-default catalog (once per instance)
self._validate_catalog_url(catalog_url)
if catalog_url != self.DEFAULT_CATALOG_URL:
if not getattr(self, "_non_default_catalog_warning_shown", False):
print(
@@ -999,11 +862,163 @@ class ExtensionCatalog:
file=sys.stderr,
)
self._non_default_catalog_warning_shown = True
return [CatalogEntry(url=catalog_url, name="custom", priority=1, install_allowed=True, description="Custom catalog via SPECKIT_CATALOG_URL")]
return catalog_url
# 2. Project-level config overrides all defaults
project_config_path = self.project_root / ".specify" / "extension-catalogs.yml"
catalogs = self._load_catalog_config(project_config_path)
if catalogs is not None:
return catalogs
# TODO: Support custom catalogs from .specify/extension-catalogs.yml
return self.DEFAULT_CATALOG_URL
# 3. User-level config
user_config_path = Path.home() / ".specify" / "extension-catalogs.yml"
catalogs = self._load_catalog_config(user_config_path)
if catalogs is not None:
return catalogs
# 4. Built-in default stack
return [
CatalogEntry(url=self.DEFAULT_CATALOG_URL, name="default", priority=1, install_allowed=True, description="Built-in catalog of installable extensions"),
CatalogEntry(url=self.COMMUNITY_CATALOG_URL, name="community", priority=2, install_allowed=False, description="Community-contributed extensions (discovery only)"),
]
def get_catalog_url(self) -> str:
"""Get the primary catalog URL.
Returns the URL of the highest-priority catalog. Kept for backward
compatibility. Use get_active_catalogs() for full multi-catalog support.
Returns:
URL of the primary catalog
Raises:
ValidationError: If a catalog URL is invalid
"""
active = self.get_active_catalogs()
return active[0].url if active else self.DEFAULT_CATALOG_URL
def _fetch_single_catalog(self, entry: CatalogEntry, force_refresh: bool = False) -> Dict[str, Any]:
"""Fetch a single catalog with per-URL caching.
For the DEFAULT_CATALOG_URL, uses legacy cache files (self.cache_file /
self.cache_metadata_file) for backward compatibility. For all other URLs,
uses URL-hash-based cache files in self.cache_dir.
Args:
entry: CatalogEntry describing the catalog to fetch
force_refresh: If True, bypass cache
Returns:
Catalog data dictionary
Raises:
ExtensionError: If catalog cannot be fetched or has invalid format
"""
import urllib.request
import urllib.error
# Determine cache file paths (backward compat for default catalog)
if entry.url == self.DEFAULT_CATALOG_URL:
cache_file = self.cache_file
cache_meta_file = self.cache_metadata_file
is_valid = not force_refresh and self.is_cache_valid()
else:
url_hash = hashlib.sha256(entry.url.encode()).hexdigest()[:16]
cache_file = self.cache_dir / f"catalog-{url_hash}.json"
cache_meta_file = self.cache_dir / f"catalog-{url_hash}-metadata.json"
is_valid = False
if not force_refresh and cache_file.exists() and cache_meta_file.exists():
try:
metadata = json.loads(cache_meta_file.read_text())
cached_at = datetime.fromisoformat(metadata.get("cached_at", ""))
if cached_at.tzinfo is None:
cached_at = cached_at.replace(tzinfo=timezone.utc)
age = (datetime.now(timezone.utc) - cached_at).total_seconds()
is_valid = age < self.CACHE_DURATION
except (json.JSONDecodeError, ValueError, KeyError, TypeError):
# If metadata is invalid or missing expected fields, treat cache as invalid
pass
# Use cache if valid
if is_valid:
try:
return json.loads(cache_file.read_text())
except json.JSONDecodeError:
pass
# Fetch from network
try:
with urllib.request.urlopen(entry.url, timeout=10) as response:
catalog_data = json.loads(response.read())
if "schema_version" not in catalog_data or "extensions" not in catalog_data:
raise ExtensionError(f"Invalid catalog format from {entry.url}")
# Save to cache
self.cache_dir.mkdir(parents=True, exist_ok=True)
cache_file.write_text(json.dumps(catalog_data, indent=2))
cache_meta_file.write_text(json.dumps({
"cached_at": datetime.now(timezone.utc).isoformat(),
"catalog_url": entry.url,
}, indent=2))
return catalog_data
except urllib.error.URLError as e:
raise ExtensionError(f"Failed to fetch catalog from {entry.url}: {e}")
except json.JSONDecodeError as e:
raise ExtensionError(f"Invalid JSON in catalog from {entry.url}: {e}")
def _get_merged_extensions(self, force_refresh: bool = False) -> List[Dict[str, Any]]:
"""Fetch and merge extensions from all active catalogs.
Higher-priority (lower priority number) catalogs win on conflicts
(same extension id in two catalogs). Each extension dict is annotated with:
- _catalog_name: name of the source catalog
- _install_allowed: whether installation is allowed from this catalog
Catalogs that fail to fetch are skipped. Raises ExtensionError only if
ALL catalogs fail.
Args:
force_refresh: If True, bypass all caches
Returns:
List of merged extension dicts
Raises:
ExtensionError: If all catalogs fail to fetch
"""
import sys
active_catalogs = self.get_active_catalogs()
merged: Dict[str, Dict[str, Any]] = {}
any_success = False
for catalog_entry in active_catalogs:
try:
catalog_data = self._fetch_single_catalog(catalog_entry, force_refresh)
any_success = True
except ExtensionError as e:
print(
f"Warning: Could not fetch catalog '{catalog_entry.name}': {e}",
file=sys.stderr,
)
continue
for ext_id, ext_data in catalog_data.get("extensions", {}).items():
if ext_id not in merged: # Higher-priority catalog wins
merged[ext_id] = {
**ext_data,
"id": ext_id,
"_catalog_name": catalog_entry.name,
"_install_allowed": catalog_entry.install_allowed,
}
if not any_success and active_catalogs:
raise ExtensionError("Failed to fetch any extension catalog")
return list(merged.values())
def is_cache_valid(self) -> bool:
"""Check if cached catalog is still valid.
@@ -1017,9 +1032,11 @@ class ExtensionCatalog:
try:
metadata = json.loads(self.cache_metadata_file.read_text())
cached_at = datetime.fromisoformat(metadata.get("cached_at", ""))
if cached_at.tzinfo is None:
cached_at = cached_at.replace(tzinfo=timezone.utc)
age_seconds = (datetime.now(timezone.utc) - cached_at).total_seconds()
return age_seconds < self.CACHE_DURATION
except (json.JSONDecodeError, ValueError, KeyError):
except (json.JSONDecodeError, ValueError, KeyError, TypeError):
return False
def fetch_catalog(self, force_refresh: bool = False) -> Dict[str, Any]:
@@ -1080,7 +1097,7 @@ class ExtensionCatalog:
author: Optional[str] = None,
verified_only: bool = False,
) -> List[Dict[str, Any]]:
"""Search catalog for extensions.
"""Search catalog for extensions across all active catalogs.
Args:
query: Search query (searches name, description, tags)
@@ -1089,14 +1106,16 @@ class ExtensionCatalog:
verified_only: If True, show only verified extensions
Returns:
List of matching extension metadata
List of matching extension metadata, each annotated with
``_catalog_name`` and ``_install_allowed`` from its source catalog.
"""
catalog = self.fetch_catalog()
extensions = catalog.get("extensions", {})
all_extensions = self._get_merged_extensions()
results = []
for ext_id, ext_data in extensions.items():
for ext_data in all_extensions:
ext_id = ext_data["id"]
# Apply filters
if verified_only and not ext_data.get("verified", False):
continue
@@ -1122,25 +1141,26 @@ class ExtensionCatalog:
if query_lower not in searchable_text:
continue
results.append({"id": ext_id, **ext_data})
results.append(ext_data)
return results
def get_extension_info(self, extension_id: str) -> Optional[Dict[str, Any]]:
"""Get detailed information about a specific extension.
Searches all active catalogs in priority order.
Args:
extension_id: ID of the extension
Returns:
Extension metadata or None if not found
Extension metadata (annotated with ``_catalog_name`` and
``_install_allowed``) or None if not found.
"""
catalog = self.fetch_catalog()
extensions = catalog.get("extensions", {})
if extension_id in extensions:
return {"id": extension_id, **extensions[extension_id]}
all_extensions = self._get_merged_extensions()
for ext_data in all_extensions:
if ext_data["id"] == extension_id:
return ext_data
return None
def download_extension(self, extension_id: str, target_dir: Optional[Path] = None) -> Path:
@@ -1200,11 +1220,18 @@ class ExtensionCatalog:
raise ExtensionError(f"Failed to save extension ZIP: {e}")
def clear_cache(self):
"""Clear the catalog cache."""
"""Clear the catalog cache (both legacy and URL-hash-based files)."""
if self.cache_file.exists():
self.cache_file.unlink()
if self.cache_metadata_file.exists():
self.cache_metadata_file.unlink()
# Also clear any per-URL hash-based cache files
if self.cache_dir.exists():
for extra_cache in self.cache_dir.glob("catalog-*.json"):
if extra_cache != self.cache_file:
extra_cache.unlink(missing_ok=True)
for extra_meta in self.cache_dir.glob("catalog-*-metadata.json"):
extra_meta.unlink(missing_ok=True)
class ConfigManager:
@@ -1782,4 +1809,3 @@ class HookExecutor:
self.save_project_config(config)

1492
src/specify_cli/presets.py Normal file

File diff suppressed because it is too large Load Diff

View File

@@ -94,9 +94,10 @@ You **MUST** consider the user input before proceeding (if not empty).
- Generate unique checklist filename:
- Use short, descriptive name based on domain (e.g., `ux.md`, `api.md`, `security.md`)
- Format: `[domain].md`
- If file exists, append to existing file
- Number items sequentially starting from CHK001
- Each `/speckit.checklist` run creates a NEW file (never overwrites existing checklists)
- File handling behavior:
- If file does NOT exist: Create new file and number items starting from CHK001
- If file exists: Append new items to existing file, continuing from the last CHK ID (e.g., if last item is CHK015, start new items at CHK016)
- Never delete or replace existing checklist content - always preserve and append
**CORE PRINCIPLE - Test the Requirements, Not the Implementation**:
Every checklist item MUST evaluate the REQUIREMENTS THEMSELVES for:
@@ -208,13 +209,13 @@ You **MUST** consider the user input before proceeding (if not empty).
6. **Structure Reference**: Generate the checklist following the canonical template in `templates/checklist-template.md` for title, meta section, category headings, and ID formatting. If template is unavailable, use: H1 title, purpose/created meta lines, `##` category sections containing `- [ ] CHK### <requirement item>` lines with globally incrementing IDs starting at CHK001.
7. **Report**: Output full path to created checklist, item count, and remind user that each run creates a new file. Summarize:
7. **Report**: Output full path to checklist file, item count, and summarize whether the run created a new file or appended to an existing one. Summarize:
- Focus areas selected
- Depth level
- Actor/timing
- Any explicit user-specified must-have items incorporated
**Important**: Each `/speckit.checklist` command invocation creates a checklist file using short, descriptive names unless file already exists. This allows:
**Important**: Each `/speckit.checklist` command invocation uses a short, descriptive checklist filename and either creates a new file or appends to an existing one. This allows:
- Multiple checklists of different types (e.g., `ux.md`, `test.md`, `security.md`)
- Simple, memorable filenames that indicate checklist purpose

View File

@@ -89,7 +89,7 @@ Execution steps:
- Information is better deferred to planning phase (note internally)
3. Generate (internally) a prioritized queue of candidate clarification questions (maximum 5). Do NOT output them all at once. Apply these constraints:
- Maximum of 10 total questions across the whole session.
- Maximum of 5 total questions across the whole session.
- Each question must be answerable with EITHER:
- A short multiplechoice selection (25 distinct, mutually exclusive options), OR
- A one-word / shortphrase answer (explicitly constrain: "Answer in <=5 words").

View File

@@ -13,6 +13,40 @@ $ARGUMENTS
You **MUST** consider the user input before proceeding (if not empty).
## Pre-Execution Checks
**Check for extension hooks (before implementation)**:
- Check if `.specify/extensions.yml` exists in the project root.
- If it exists, read it and look for entries under the `hooks.before_implement` key
- If the YAML cannot be parsed or is invalid, skip hook checking silently and continue normally
- Filter to only hooks where `enabled: true`
- For each remaining hook, do **not** attempt to interpret or evaluate hook `condition` expressions:
- If the hook has no `condition` field, or it is null/empty, treat the hook as executable
- If the hook defines a non-empty `condition`, skip the hook and leave condition evaluation to the HookExecutor implementation
- For each executable hook, output the following based on its `optional` flag:
- **Optional hook** (`optional: true`):
```
## Extension Hooks
**Optional Pre-Hook**: {extension}
Command: `/{command}`
Description: {description}
Prompt: {prompt}
To execute: `/{command}`
```
- **Mandatory hook** (`optional: false`):
```
## Extension Hooks
**Automatic Pre-Hook**: {extension}
Executing: `/{command}`
EXECUTE_COMMAND: {command}
Wait for the result of the hook command before proceeding to the Outline.
```
- If no hooks are registered or `.specify/extensions.yml` does not exist, skip silently
## Outline
1. Run `{SCRIPT}` from repo root and parse FEATURE_DIR and AVAILABLE_DOCS list. All paths must be absolute. For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'\''m Groot' (or double-quote if possible: "I'm Groot").
@@ -88,7 +122,7 @@ You **MUST** consider the user input before proceeding (if not empty).
- **Rust**: `target/`, `debug/`, `release/`, `*.rs.bk`, `*.rlib`, `*.prof*`, `.idea/`, `*.log`, `.env*`
- **Kotlin**: `build/`, `out/`, `.gradle/`, `.idea/`, `*.class`, `*.jar`, `*.iml`, `*.log`, `.env*`
- **C++**: `build/`, `bin/`, `obj/`, `out/`, `*.o`, `*.so`, `*.a`, `*.exe`, `*.dll`, `.idea/`, `*.log`, `.env*`
- **C**: `build/`, `bin/`, `obj/`, `out/`, `*.o`, `*.a`, `*.so`, `*.exe`, `Makefile`, `config.log`, `.idea/`, `*.log`, `.env*`
- **C**: `build/`, `bin/`, `obj/`, `out/`, `*.o`, `*.a`, `*.so`, `*.exe`, `*.dll`, `autom4te.cache/`, `config.status`, `config.log`, `.idea/`, `*.log`, `.env*`
- **Swift**: `.build/`, `DerivedData/`, `*.swiftpm/`, `Packages/`
- **R**: `.Rproj.user/`, `.Rhistory`, `.RData`, `.Ruserdata`, `*.Rproj`, `packrat/`, `renv/`
- **Universal**: `.DS_Store`, `Thumbs.db`, `*.tmp`, `*.swp`, `.vscode/`, `.idea/`
@@ -136,3 +170,32 @@ You **MUST** consider the user input before proceeding (if not empty).
- Report final status with summary of completed work
Note: This command assumes a complete task breakdown exists in tasks.md. If tasks are incomplete or missing, suggest running `/speckit.tasks` first to regenerate the task list.
10. **Check for extension hooks**: After completion validation, check if `.specify/extensions.yml` exists in the project root.
- If it exists, read it and look for entries under the `hooks.after_implement` key
- If the YAML cannot be parsed or is invalid, skip hook checking silently and continue normally
- Filter to only hooks where `enabled: true`
- For each remaining hook, do **not** attempt to interpret or evaluate hook `condition` expressions:
- If the hook has no `condition` field, or it is null/empty, treat the hook as executable
- If the hook defines a non-empty `condition`, skip the hook and leave condition evaluation to the HookExecutor implementation
- For each executable hook, output the following based on its `optional` flag:
- **Optional hook** (`optional: true`):
```
## Extension Hooks
**Optional Hook**: {extension}
Command: `/{command}`
Description: {description}
Prompt: {prompt}
To execute: `/{command}`
```
- **Mandatory hook** (`optional: false`):
```
## Extension Hooks
**Automatic Hook**: {extension}
Executing: `/{command}`
EXECUTE_COMMAND: {command}
```
- If no hooks are registered or `.specify/extensions.yml` does not exist, skip silently

View File

@@ -75,10 +75,11 @@ You **MUST** consider the user input before proceeding (if not empty).
- Validation rules from requirements
- State transitions if applicable
2. **Generate API contracts** from functional requirements:
- For each user action → endpoint
- Use standard REST/GraphQL patterns
- Output OpenAPI/GraphQL schema to `/contracts/`
2. **Define interface contracts** (if project has external interfaces) → `/contracts/`:
- Identify what interfaces the project exposes to users or other systems
- Document the contract format appropriate for the project type
- Examples: public APIs for libraries, command schemas for CLI tools, endpoints for web services, grammars for parsers, UI contracts for applications
- Skip if project is purely internal (build scripts, one-off tools, etc.)
3. **Agent context update**:
- Run `{AGENT_SCRIPT}`

View File

@@ -9,8 +9,8 @@ handoffs:
prompt: Clarify specification requirements
send: true
scripts:
sh: scripts/bash/create-new-feature.sh --json "{ARGS}"
ps: scripts/powershell/create-new-feature.ps1 -Json "{ARGS}"
sh: scripts/bash/create-new-feature.sh "{ARGS}"
ps: scripts/powershell/create-new-feature.ps1 "{ARGS}"
---
## User Input
@@ -39,33 +39,14 @@ Given that feature description, do this:
- "Create a dashboard for analytics" → "analytics-dashboard"
- "Fix payment processing timeout bug" → "fix-payment-timeout"
2. **Check for existing branches before creating new one**:
2. **Create the feature branch** by running the script with `--short-name` (and `--json`), and do NOT pass `--number` (the script auto-detects the next globally available number across all branches and spec directories):
a. First, fetch all remote branches to ensure we have the latest information:
```bash
git fetch --all --prune
```
b. Find the highest feature number across all sources for the short-name:
- Remote branches: `git ls-remote --heads origin | grep -E 'refs/heads/[0-9]+-<short-name>$'`
- Local branches: `git branch | grep -E '^[* ]*[0-9]+-<short-name>$'`
- Specs directories: Check for directories matching `specs/[0-9]+-<short-name>`
c. Determine the next available number:
- Extract all numbers from all three sources
- Find the highest number N
- Use N+1 for the new branch number
d. Run the script `{SCRIPT}` with the calculated number and short-name:
- Pass `--number N+1` and `--short-name "your-short-name"` along with the feature description
- Bash example: `{SCRIPT} --json --number 5 --short-name "user-auth" "Add user authentication"`
- PowerShell example: `{SCRIPT} -Json -Number 5 -ShortName "user-auth" "Add user authentication"`
- Bash example: `{SCRIPT} --json --short-name "user-auth" "Add user authentication"`
- PowerShell example: `{SCRIPT} -Json -ShortName "user-auth" "Add user authentication"`
**IMPORTANT**:
- Check all three sources (remote branches, local branches, specs directories) to find the highest number
- Only match branches/directories with the exact short-name pattern
- If no existing branches/directories found with this short-name, start with number 1
- Do NOT pass `--number` the script determines the correct next number automatically
- Always include the JSON flag (`--json` for Bash, `-Json` for PowerShell) so the output can be parsed reliably
- You must only ever run this script once per feature
- The JSON is provided in the terminal as output - always refer to it to get the actual content you're looking for
- The JSON output will contain BRANCH_NAME and SPEC_FILE paths
@@ -235,7 +216,7 @@ When creating this spec from a user prompt:
- Performance targets: Standard web/mobile app expectations unless specified
- Error handling: User-friendly messages with appropriate fallbacks
- Authentication method: Standard session-based or OAuth2 for web apps
- Integration patterns: RESTful APIs unless specified otherwise
- Integration patterns: Use project-appropriate patterns (REST/GraphQL for web services, function calls for libraries, CLI args for tools, etc.)
### Success Criteria Guidelines

View File

@@ -22,20 +22,54 @@ $ARGUMENTS
You **MUST** consider the user input before proceeding (if not empty).
## Pre-Execution Checks
**Check for extension hooks (before tasks generation)**:
- Check if `.specify/extensions.yml` exists in the project root.
- If it exists, read it and look for entries under the `hooks.before_tasks` key
- If the YAML cannot be parsed or is invalid, skip hook checking silently and continue normally
- Filter to only hooks where `enabled: true`
- For each remaining hook, do **not** attempt to interpret or evaluate hook `condition` expressions:
- If the hook has no `condition` field, or it is null/empty, treat the hook as executable
- If the hook defines a non-empty `condition`, skip the hook and leave condition evaluation to the HookExecutor implementation
- For each executable hook, output the following based on its `optional` flag:
- **Optional hook** (`optional: true`):
```
## Extension Hooks
**Optional Pre-Hook**: {extension}
Command: `/{command}`
Description: {description}
Prompt: {prompt}
To execute: `/{command}`
```
- **Mandatory hook** (`optional: false`):
```
## Extension Hooks
**Automatic Pre-Hook**: {extension}
Executing: `/{command}`
EXECUTE_COMMAND: {command}
Wait for the result of the hook command before proceeding to the Outline.
```
- If no hooks are registered or `.specify/extensions.yml` does not exist, skip silently
## Outline
1. **Setup**: Run `{SCRIPT}` from repo root and parse FEATURE_DIR and AVAILABLE_DOCS list. All paths must be absolute. For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'\''m Groot' (or double-quote if possible: "I'm Groot").
2. **Load design documents**: Read from FEATURE_DIR:
- **Required**: plan.md (tech stack, libraries, structure), spec.md (user stories with priorities)
- **Optional**: data-model.md (entities), contracts/ (API endpoints), research.md (decisions), quickstart.md (test scenarios)
- **Optional**: data-model.md (entities), contracts/ (interface contracts), research.md (decisions), quickstart.md (test scenarios)
- Note: Not all projects have all documents. Generate tasks based on what's available.
3. **Execute task generation workflow**:
- Load plan.md and extract tech stack, libraries, project structure
- Load spec.md and extract user stories with their priorities (P1, P2, P3, etc.)
- If data-model.md exists: Extract entities and map to user stories
- If contracts/ exists: Map endpoints to user stories
- If contracts/ exists: Map interface contracts to user stories
- If research.md exists: Extract decisions for setup tasks
- Generate tasks organized by user story (see Task Generation Rules below)
- Generate dependency graph showing user story completion order
@@ -63,6 +97,35 @@ You **MUST** consider the user input before proceeding (if not empty).
- Suggested MVP scope (typically just User Story 1)
- Format validation: Confirm ALL tasks follow the checklist format (checkbox, ID, labels, file paths)
6. **Check for extension hooks**: After tasks.md is generated, check if `.specify/extensions.yml` exists in the project root.
- If it exists, read it and look for entries under the `hooks.after_tasks` key
- If the YAML cannot be parsed or is invalid, skip hook checking silently and continue normally
- Filter to only hooks where `enabled: true`
- For each remaining hook, do **not** attempt to interpret or evaluate hook `condition` expressions:
- If the hook has no `condition` field, or it is null/empty, treat the hook as executable
- If the hook defines a non-empty `condition`, skip the hook and leave condition evaluation to the HookExecutor implementation
- For each executable hook, output the following based on its `optional` flag:
- **Optional hook** (`optional: true`):
```
## Extension Hooks
**Optional Hook**: {extension}
Command: `/{command}`
Description: {description}
Prompt: {prompt}
To execute: `/{command}`
```
- **Mandatory hook** (`optional: false`):
```
## Extension Hooks
**Automatic Hook**: {extension}
Executing: `/{command}`
EXECUTE_COMMAND: {command}
```
- If no hooks are registered or `.specify/extensions.yml` does not exist, skip silently
Context for task generation: {ARGS}
The tasks.md should be immediately executable - each task must be specific enough that an LLM can complete it without additional context.
@@ -112,13 +175,13 @@ Every task MUST strictly follow this format:
- Map all related components to their story:
- Models needed for that story
- Services needed for that story
- Endpoints/UI needed for that story
- Interfaces/UI needed for that story
- If tests requested: Tests specific to that story
- Mark story dependencies (most stories should be independent)
2. **From Contracts**:
- Map each contract/endpoint → to the user story it serves
- If tests requested: Each contract → contract test task [P] before implementation in that story's phase
- Map each interface contract → to the user story it serves
- If tests requested: Each interface contract → contract test task [P] before implementation in that story's phase
3. **From Data Model**:
- Map each entity to the user story(ies) that need it

View File

@@ -22,7 +22,7 @@
**Storage**: [if applicable, e.g., PostgreSQL, CoreData, files or N/A]
**Testing**: [e.g., pytest, XCTest, cargo test or NEEDS CLARIFICATION]
**Target Platform**: [e.g., Linux server, iOS 15+, WASM or NEEDS CLARIFICATION]
**Project Type**: [single/web/mobile - determines source structure]
**Project Type**: [e.g., library/cli/web-service/mobile-app/compiler/desktop-app or NEEDS CLARIFICATION]
**Performance Goals**: [domain-specific, e.g., 1000 req/s, 10k lines/sec, 60 fps or NEEDS CLARIFICATION]
**Constraints**: [domain-specific, e.g., <200ms p95, <100MB memory, offline-capable or NEEDS CLARIFICATION]
**Scale/Scope**: [domain-specific, e.g., 10k users, 1M LOC, 50 screens or NEEDS CLARIFICATION]

View File

@@ -0,0 +1,34 @@
hooks:
before_implement:
- id: pre_test
enabled: true
optional: false
extension: "test-extension"
command: "pre_implement_test"
description: "Test before implement hook execution"
after_implement:
- id: post_test
enabled: true
optional: true
extension: "test-extension"
command: "post_implement_test"
description: "Test after implement hook execution"
prompt: "Would you like to run the post-implement test?"
before_tasks:
- id: pre_tasks_test
enabled: true
optional: false
extension: "test-extension"
command: "pre_tasks_test"
description: "Test before tasks hook execution"
after_tasks:
- id: post_tasks_test
enabled: true
optional: true
extension: "test-extension"
command: "post_tasks_test"
description: "Test after tasks hook execution"
prompt: "Would you like to run the post-tasks test?"

30
tests/hooks/TESTING.md Normal file
View File

@@ -0,0 +1,30 @@
# Testing Extension Hooks
This directory contains a mock project to verify that LLM agents correctly identify and execute hook commands defined in `.specify/extensions.yml`.
## Test 1: Testing `before_tasks` and `after_tasks`
1. Open a chat with an LLM (like GitHub Copilot) in this project.
2. Ask it to generate tasks for the current directory:
> "Please follow `/speckit.tasks` for the `./tests/hooks` directory."
3. **Expected Behavior**:
- Before doing any generation, the LLM should notice the `AUTOMATIC Pre-Hook` in `.specify/extensions.yml` under `before_tasks`.
- It should state it is executing `EXECUTE_COMMAND: pre_tasks_test`.
- It should then proceed to read the `.md` docs and produce a `tasks.md`.
- After generation, it should output the optional `after_tasks` hook (`post_tasks_test`) block, asking if you want to run it.
## Test 2: Testing `before_implement` and `after_implement`
*(Requires `tasks.md` from Test 1 to exist)*
1. In the same (or new) chat, ask the LLM to implement the tasks:
> "Please follow `/speckit.implement` for the `./tests/hooks` directory."
2. **Expected Behavior**:
- The LLM should first check for `before_implement` hooks.
- It should state it is executing `EXECUTE_COMMAND: pre_implement_test` BEFORE doing any actual task execution.
- It should evaluate the checklists and execute the code writing tasks.
- Upon completion, it should output the optional `after_implement` hook (`post_implement_test`) block.
## How it works
The templates for these commands in `templates/commands/tasks.md` and `templates/commands/implement.md` contains strict ordered lists. The new `before_*` hooks are explicitly formulated in a **Pre-Execution Checks** section prior to the outline to ensure they're evaluated first without breaking template step numbers.

3
tests/hooks/plan.md Normal file
View File

@@ -0,0 +1,3 @@
# Test Setup for Hooks
This feature is designed to test if LLMs correctly invoke Spec Kit extensions hooks when generating tasks and implementing code.

1
tests/hooks/spec.md Normal file
View File

@@ -0,0 +1 @@
- **User Story 1:** I want a test script that prints "Hello hooks!".

1
tests/hooks/tasks.md Normal file
View File

@@ -0,0 +1 @@
- [ ] T001 [US1] Create script that prints 'Hello hooks!' in hello.py

View File

@@ -0,0 +1,173 @@
"""Consistency checks for agent configuration across runtime and packaging scripts."""
import re
from pathlib import Path
from specify_cli import AGENT_CONFIG, AI_ASSISTANT_ALIASES, AI_ASSISTANT_HELP
from specify_cli.extensions import CommandRegistrar
REPO_ROOT = Path(__file__).resolve().parent.parent
class TestAgentConfigConsistency:
"""Ensure kiro-cli migration stays synchronized across key surfaces."""
def test_runtime_config_uses_kiro_cli_and_removes_q(self):
"""AGENT_CONFIG should include kiro-cli and exclude legacy q."""
assert "kiro-cli" in AGENT_CONFIG
assert AGENT_CONFIG["kiro-cli"]["folder"] == ".kiro/"
assert AGENT_CONFIG["kiro-cli"]["commands_subdir"] == "prompts"
assert "q" not in AGENT_CONFIG
def test_extension_registrar_uses_kiro_cli_and_removes_q(self):
"""Extension command registrar should target .kiro/prompts."""
cfg = CommandRegistrar.AGENT_CONFIGS
assert "kiro-cli" in cfg
assert cfg["kiro-cli"]["dir"] == ".kiro/prompts"
assert "q" not in cfg
def test_extension_registrar_includes_codex(self):
"""Extension command registrar should include codex targeting .codex/prompts."""
cfg = CommandRegistrar.AGENT_CONFIGS
assert "codex" in cfg
assert cfg["codex"]["dir"] == ".codex/prompts"
def test_release_agent_lists_include_kiro_cli_and_exclude_q(self):
"""Bash and PowerShell release scripts should agree on agent key set for Kiro."""
sh_text = (REPO_ROOT / ".github" / "workflows" / "scripts" / "create-release-packages.sh").read_text(encoding="utf-8")
ps_text = (REPO_ROOT / ".github" / "workflows" / "scripts" / "create-release-packages.ps1").read_text(encoding="utf-8")
sh_match = re.search(r"ALL_AGENTS=\(([^)]*)\)", sh_text)
assert sh_match is not None
sh_agents = sh_match.group(1).split()
ps_match = re.search(r"\$AllAgents = @\(([^)]*)\)", ps_text)
assert ps_match is not None
ps_agents = re.findall(r"'([^']+)'", ps_match.group(1))
assert "kiro-cli" in sh_agents
assert "kiro-cli" in ps_agents
assert "shai" in sh_agents
assert "shai" in ps_agents
assert "agy" in sh_agents
assert "agy" in ps_agents
assert "q" not in sh_agents
assert "q" not in ps_agents
def test_release_ps_switch_has_shai_and_agy_generation(self):
"""PowerShell release builder must generate files for shai and agy agents."""
ps_text = (REPO_ROOT / ".github" / "workflows" / "scripts" / "create-release-packages.ps1").read_text(encoding="utf-8")
assert re.search(r"'shai'\s*\{.*?\.shai/commands", ps_text, re.S) is not None
assert re.search(r"'agy'\s*\{.*?\.agent/workflows", ps_text, re.S) is not None
def test_init_ai_help_includes_roo_and_kiro_alias(self):
"""CLI help text for --ai should stay in sync with agent config and alias guidance."""
assert "roo" in AI_ASSISTANT_HELP
for alias, target in AI_ASSISTANT_ALIASES.items():
assert alias in AI_ASSISTANT_HELP
assert target in AI_ASSISTANT_HELP
def test_devcontainer_kiro_installer_uses_pinned_checksum(self):
"""Devcontainer installer should always verify Kiro installer via pinned SHA256."""
post_create_text = (REPO_ROOT / ".devcontainer" / "post-create.sh").read_text(encoding="utf-8")
assert 'KIRO_INSTALLER_SHA256="7487a65cf310b7fb59b357c4b5e6e3f3259d383f4394ecedb39acf70f307cffb"' in post_create_text
assert "sha256sum -c -" in post_create_text
assert "KIRO_SKIP_KIRO_INSTALLER_VERIFY" not in post_create_text
def test_release_output_targets_kiro_prompt_dir(self):
"""Packaging and release scripts should no longer emit amazonq artifacts."""
sh_text = (REPO_ROOT / ".github" / "workflows" / "scripts" / "create-release-packages.sh").read_text(encoding="utf-8")
ps_text = (REPO_ROOT / ".github" / "workflows" / "scripts" / "create-release-packages.ps1").read_text(encoding="utf-8")
gh_release_text = (REPO_ROOT / ".github" / "workflows" / "scripts" / "create-github-release.sh").read_text(encoding="utf-8")
assert ".kiro/prompts" in sh_text
assert ".kiro/prompts" in ps_text
assert ".amazonq/prompts" not in sh_text
assert ".amazonq/prompts" not in ps_text
assert "spec-kit-template-kiro-cli-sh-" in gh_release_text
assert "spec-kit-template-kiro-cli-ps-" in gh_release_text
assert "spec-kit-template-q-sh-" not in gh_release_text
assert "spec-kit-template-q-ps-" not in gh_release_text
def test_agent_context_scripts_use_kiro_cli(self):
"""Agent context scripts should advertise kiro-cli and not legacy q agent key."""
bash_text = (REPO_ROOT / "scripts" / "bash" / "update-agent-context.sh").read_text(encoding="utf-8")
pwsh_text = (REPO_ROOT / "scripts" / "powershell" / "update-agent-context.ps1").read_text(encoding="utf-8")
assert "kiro-cli" in bash_text
assert "kiro-cli" in pwsh_text
assert "Amazon Q Developer CLI" not in bash_text
assert "Amazon Q Developer CLI" not in pwsh_text
# --- Tabnine CLI consistency checks ---
def test_runtime_config_includes_tabnine(self):
"""AGENT_CONFIG should include tabnine with correct folder and subdir."""
assert "tabnine" in AGENT_CONFIG
assert AGENT_CONFIG["tabnine"]["folder"] == ".tabnine/agent/"
assert AGENT_CONFIG["tabnine"]["commands_subdir"] == "commands"
assert AGENT_CONFIG["tabnine"]["requires_cli"] is True
assert AGENT_CONFIG["tabnine"]["install_url"] is not None
def test_extension_registrar_includes_tabnine(self):
"""CommandRegistrar.AGENT_CONFIGS should include tabnine with correct TOML config."""
from specify_cli.extensions import CommandRegistrar
assert "tabnine" in CommandRegistrar.AGENT_CONFIGS
cfg = CommandRegistrar.AGENT_CONFIGS["tabnine"]
assert cfg["dir"] == ".tabnine/agent/commands"
assert cfg["format"] == "toml"
assert cfg["args"] == "{{args}}"
assert cfg["extension"] == ".toml"
def test_release_agent_lists_include_tabnine(self):
"""Bash and PowerShell release scripts should include tabnine in agent lists."""
sh_text = (REPO_ROOT / ".github" / "workflows" / "scripts" / "create-release-packages.sh").read_text(encoding="utf-8")
ps_text = (REPO_ROOT / ".github" / "workflows" / "scripts" / "create-release-packages.ps1").read_text(encoding="utf-8")
sh_match = re.search(r"ALL_AGENTS=\(([^)]*)\)", sh_text)
assert sh_match is not None
sh_agents = sh_match.group(1).split()
ps_match = re.search(r"\$AllAgents = @\(([^)]*)\)", ps_text)
assert ps_match is not None
ps_agents = re.findall(r"'([^']+)'", ps_match.group(1))
assert "tabnine" in sh_agents
assert "tabnine" in ps_agents
def test_release_scripts_generate_tabnine_toml_commands(self):
"""Release scripts should generate TOML commands for tabnine in .tabnine/agent/commands."""
sh_text = (REPO_ROOT / ".github" / "workflows" / "scripts" / "create-release-packages.sh").read_text(encoding="utf-8")
ps_text = (REPO_ROOT / ".github" / "workflows" / "scripts" / "create-release-packages.ps1").read_text(encoding="utf-8")
assert ".tabnine/agent/commands" in sh_text
assert ".tabnine/agent/commands" in ps_text
assert re.search(r"'tabnine'\s*\{.*?\.tabnine/agent/commands", ps_text, re.S) is not None
def test_github_release_includes_tabnine_packages(self):
"""GitHub release script should include tabnine template packages."""
gh_release_text = (REPO_ROOT / ".github" / "workflows" / "scripts" / "create-github-release.sh").read_text(encoding="utf-8")
assert "spec-kit-template-tabnine-sh-" in gh_release_text
assert "spec-kit-template-tabnine-ps-" in gh_release_text
def test_agent_context_scripts_include_tabnine(self):
"""Agent context scripts should support tabnine agent type."""
bash_text = (REPO_ROOT / "scripts" / "bash" / "update-agent-context.sh").read_text(encoding="utf-8")
pwsh_text = (REPO_ROOT / "scripts" / "powershell" / "update-agent-context.ps1").read_text(encoding="utf-8")
assert "tabnine" in bash_text
assert "TABNINE_FILE" in bash_text
assert "tabnine" in pwsh_text
assert "TABNINE_FILE" in pwsh_text
def test_ai_help_includes_tabnine(self):
"""CLI help text for --ai should include tabnine."""
assert "tabnine" in AI_ASSISTANT_HELP

View File

@@ -147,6 +147,11 @@ class TestGetSkillsDir:
result = _get_skills_dir(project_dir, "gemini")
assert result == project_dir / ".gemini" / "skills"
def test_tabnine_skills_dir(self, project_dir):
"""Tabnine should use .tabnine/agent/skills/."""
result = _get_skills_dir(project_dir, "tabnine")
assert result == project_dir / ".tabnine" / "agent" / "skills"
def test_copilot_skills_dir(self, project_dir):
"""Copilot should use .github/skills/."""
result = _get_skills_dir(project_dir, "copilot")
@@ -162,6 +167,11 @@ class TestGetSkillsDir:
result = _get_skills_dir(project_dir, "cursor-agent")
assert result == project_dir / ".cursor" / "skills"
def test_kiro_cli_skills_dir(self, project_dir):
"""Kiro CLI should use .kiro/skills/."""
result = _get_skills_dir(project_dir, "kiro-cli")
assert result == project_dir / ".kiro" / "skills"
def test_unknown_agent_uses_default(self, project_dir):
"""Unknown agents should fall back to DEFAULT_SKILLS_DIR."""
result = _get_skills_dir(project_dir, "nonexistent-agent")
@@ -380,7 +390,7 @@ class TestInstallAiSkills:
# .toml commands should be untouched
assert (cmds_dir / "speckit.specify.toml").exists()
@pytest.mark.parametrize("agent_key", list(AGENT_CONFIG.keys()))
@pytest.mark.parametrize("agent_key", [k for k in AGENT_CONFIG.keys() if k != "generic"])
def test_skills_install_for_all_agents(self, temp_dir, agent_key):
"""install_ai_skills should produce skills for every configured agent."""
proj = temp_dir / f"proj-{agent_key}"
@@ -460,8 +470,9 @@ class TestNewProjectCommandSkip:
"""Simulate template extraction: create agent commands dir."""
agent_cfg = AGENT_CONFIG.get(agent, {})
agent_folder = agent_cfg.get("folder", "")
commands_subdir = agent_cfg.get("commands_subdir", "commands")
if agent_folder:
cmds_dir = project_path / agent_folder.rstrip("/") / "commands"
cmds_dir = project_path / agent_folder.rstrip("/") / commands_subdir
cmds_dir.mkdir(parents=True, exist_ok=True)
(cmds_dir / "speckit.specify.md").write_text("# spec")
@@ -483,6 +494,7 @@ class TestNewProjectCommandSkip:
patch("specify_cli.shutil.which", return_value="/usr/bin/git"):
result = runner.invoke(app, ["init", str(target), "--ai", "claude", "--ai-skills", "--script", "sh", "--no-git"])
assert result.exit_code == 0
# Skills should have been called
mock_skills.assert_called_once()
@@ -490,6 +502,30 @@ class TestNewProjectCommandSkip:
cmds_dir = target / ".claude" / "commands"
assert not cmds_dir.exists()
def test_new_project_nonstandard_commands_subdir_removed_after_skills_succeed(self, tmp_path):
"""For non-standard agents, configured commands_subdir should be removed on success."""
from typer.testing import CliRunner
runner = CliRunner()
target = tmp_path / "new-kiro-proj"
def fake_download(project_path, *args, **kwargs):
self._fake_extract("kiro-cli", project_path)
with patch("specify_cli.download_and_extract_template", side_effect=fake_download), \
patch("specify_cli.ensure_executable_scripts"), \
patch("specify_cli.ensure_constitution_from_template"), \
patch("specify_cli.install_ai_skills", return_value=True) as mock_skills, \
patch("specify_cli.is_git_repo", return_value=False), \
patch("specify_cli.shutil.which", return_value="/usr/bin/git"):
result = runner.invoke(app, ["init", str(target), "--ai", "kiro-cli", "--ai-skills", "--script", "sh", "--no-git"])
assert result.exit_code == 0
mock_skills.assert_called_once()
prompts_dir = target / ".kiro" / "prompts"
assert not prompts_dir.exists()
def test_commands_preserved_when_skills_fail(self, tmp_path):
"""If skills fail, commands should NOT be removed (safety net)."""
from typer.testing import CliRunner
@@ -508,6 +544,7 @@ class TestNewProjectCommandSkip:
patch("specify_cli.shutil.which", return_value="/usr/bin/git"):
result = runner.invoke(app, ["init", str(target), "--ai", "claude", "--ai-skills", "--script", "sh", "--no-git"])
assert result.exit_code == 0
# Commands should still exist since skills failed
cmds_dir = target / ".claude" / "commands"
assert cmds_dir.exists()
@@ -538,8 +575,9 @@ class TestNewProjectCommandSkip:
patch("specify_cli.install_ai_skills", return_value=True), \
patch("specify_cli.is_git_repo", return_value=True), \
patch("specify_cli.shutil.which", return_value="/usr/bin/git"):
result = runner.invoke(app, ["init", "--here", "--ai", "claude", "--ai-skills", "--script", "sh", "--no-git"])
result = runner.invoke(app, ["init", "--here", "--ai", "claude", "--ai-skills", "--script", "sh", "--no-git"], input="y\n")
assert result.exit_code == 0
# Commands must remain for --here
assert cmds_dir.exists()
assert (cmds_dir / "speckit.specify.md").exists()
@@ -630,3 +668,101 @@ class TestCliValidation:
plain = re.sub(r'\x1b\[[0-9;]*m', '', result.output)
assert "--ai-skills" in plain
assert "agent skills" in plain.lower()
def test_kiro_alias_normalized_to_kiro_cli(self, tmp_path):
"""--ai kiro should normalize to canonical kiro-cli agent key."""
from typer.testing import CliRunner
runner = CliRunner()
target = tmp_path / "kiro-alias-proj"
with patch("specify_cli.download_and_extract_template") as mock_download, \
patch("specify_cli.ensure_executable_scripts"), \
patch("specify_cli.ensure_constitution_from_template"), \
patch("specify_cli.is_git_repo", return_value=False), \
patch("specify_cli.shutil.which", return_value="/usr/bin/git"):
result = runner.invoke(
app,
[
"init",
str(target),
"--ai",
"kiro",
"--ignore-agent-tools",
"--script",
"sh",
"--no-git",
],
)
assert result.exit_code == 0
assert mock_download.called
# download_and_extract_template(project_path, ai_assistant, script_type, ...)
assert mock_download.call_args.args[1] == "kiro-cli"
def test_q_removed_from_agent_config(self):
"""Amazon Q legacy key should not remain in AGENT_CONFIG."""
assert "q" not in AGENT_CONFIG
assert "kiro-cli" in AGENT_CONFIG
class TestParameterOrderingIssue:
"""Test fix for GitHub issue #1641: parameter ordering issues."""
def test_ai_flag_consuming_here_flag(self):
"""--ai without value should not consume --here flag (issue #1641)."""
from typer.testing import CliRunner
runner = CliRunner()
# This used to fail with "Must specify project name" because --here was consumed by --ai
result = runner.invoke(app, ["init", "--ai-skills", "--ai", "--here"])
assert result.exit_code == 1
assert "Invalid value for --ai" in result.output
assert "--here" in result.output # Should mention the invalid value
def test_ai_flag_consuming_ai_skills_flag(self):
"""--ai without value should not consume --ai-skills flag."""
from typer.testing import CliRunner
runner = CliRunner()
# This should fail with helpful error about missing --ai value
result = runner.invoke(app, ["init", "--here", "--ai", "--ai-skills"])
assert result.exit_code == 1
assert "Invalid value for --ai" in result.output
assert "--ai-skills" in result.output # Should mention the invalid value
def test_error_message_provides_hint(self):
"""Error message should provide helpful hint about missing value."""
from typer.testing import CliRunner
runner = CliRunner()
result = runner.invoke(app, ["init", "--ai", "--here"])
assert result.exit_code == 1
assert "Hint:" in result.output or "hint" in result.output.lower()
assert "forget to provide a value" in result.output.lower()
def test_error_message_lists_available_agents(self):
"""Error message should list available agents."""
from typer.testing import CliRunner
runner = CliRunner()
result = runner.invoke(app, ["init", "--ai", "--here"])
assert result.exit_code == 1
# Should mention some known agents
output_lower = result.output.lower()
assert any(agent in output_lower for agent in ["claude", "copilot", "gemini"])
def test_ai_commands_dir_consuming_flag(self):
"""--ai-commands-dir without value should not consume next flag."""
from typer.testing import CliRunner
runner = CliRunner()
result = runner.invoke(app, ["init", "myproject", "--ai", "generic", "--ai-commands-dir", "--here"])
assert result.exit_code == 1
assert "Invalid value for --ai-commands-dir" in result.output
assert "--here" in result.output

View File

@@ -0,0 +1,263 @@
"""
Tests for Cursor .mdc frontmatter generation (issue #669).
Verifies that update-agent-context.sh properly prepends YAML frontmatter
to .mdc files so that Cursor IDE auto-includes the rules.
"""
import os
import shutil
import subprocess
import textwrap
import pytest
SCRIPT_PATH = os.path.join(
os.path.dirname(__file__),
os.pardir,
"scripts",
"bash",
"update-agent-context.sh",
)
EXPECTED_FRONTMATTER_LINES = [
"---",
"description: Project Development Guidelines",
'globs: ["**/*"]',
"alwaysApply: true",
"---",
]
requires_git = pytest.mark.skipif(
shutil.which("git") is None,
reason="git is not installed",
)
class TestScriptFrontmatterPattern:
"""Static analysis — no git required."""
def test_create_new_has_mdc_frontmatter_logic(self):
"""create_new_agent_file() must contain .mdc frontmatter logic."""
with open(SCRIPT_PATH, encoding="utf-8") as f:
content = f.read()
assert 'if [[ "$target_file" == *.mdc ]]' in content
assert "alwaysApply: true" in content
def test_update_existing_has_mdc_frontmatter_logic(self):
"""update_existing_agent_file() must also handle .mdc frontmatter."""
with open(SCRIPT_PATH, encoding="utf-8") as f:
content = f.read()
# There should be two occurrences of the .mdc check — one per function
occurrences = content.count('if [[ "$target_file" == *.mdc ]]')
assert occurrences >= 2, (
f"Expected at least 2 .mdc frontmatter checks, found {occurrences}"
)
def test_powershell_script_has_mdc_frontmatter_logic(self):
"""PowerShell script must also handle .mdc frontmatter."""
ps_path = os.path.join(
os.path.dirname(__file__),
os.pardir,
"scripts",
"powershell",
"update-agent-context.ps1",
)
with open(ps_path, encoding="utf-8") as f:
content = f.read()
assert "alwaysApply: true" in content
occurrences = content.count(r"\.mdc$")
assert occurrences >= 2, (
f"Expected at least 2 .mdc frontmatter checks in PS script, found {occurrences}"
)
@requires_git
class TestCursorFrontmatterIntegration:
"""Integration tests using a real git repo."""
@pytest.fixture
def git_repo(self, tmp_path):
"""Create a minimal git repo with the spec-kit structure."""
repo = tmp_path / "repo"
repo.mkdir()
# Init git repo
subprocess.run(
["git", "init"], cwd=str(repo), capture_output=True, check=True
)
subprocess.run(
["git", "config", "user.email", "test@test.com"],
cwd=str(repo),
capture_output=True,
check=True,
)
subprocess.run(
["git", "config", "user.name", "Test"],
cwd=str(repo),
capture_output=True,
check=True,
)
# Create .specify dir with config
specify_dir = repo / ".specify"
specify_dir.mkdir()
(specify_dir / "config.yaml").write_text(
textwrap.dedent("""\
project_type: webapp
language: python
framework: fastapi
database: N/A
""")
)
# Create template
templates_dir = specify_dir / "templates"
templates_dir.mkdir()
(templates_dir / "agent-file-template.md").write_text(
"# [PROJECT NAME] Development Guidelines\n\n"
"Auto-generated from all feature plans. Last updated: [DATE]\n\n"
"## Active Technologies\n\n"
"[EXTRACTED FROM ALL PLAN.MD FILES]\n\n"
"## Project Structure\n\n"
"[ACTUAL STRUCTURE FROM PLANS]\n\n"
"## Development Commands\n\n"
"[ONLY COMMANDS FOR ACTIVE TECHNOLOGIES]\n\n"
"## Coding Conventions\n\n"
"[LANGUAGE-SPECIFIC, ONLY FOR LANGUAGES IN USE]\n\n"
"## Recent Changes\n\n"
"[LAST 3 FEATURES AND WHAT THEY ADDED]\n"
)
# Create initial commit
subprocess.run(
["git", "add", "-A"], cwd=str(repo), capture_output=True, check=True
)
subprocess.run(
["git", "commit", "-m", "init"],
cwd=str(repo),
capture_output=True,
check=True,
)
# Create a feature branch so CURRENT_BRANCH detection works
subprocess.run(
["git", "checkout", "-b", "001-test-feature"],
cwd=str(repo),
capture_output=True,
check=True,
)
# Create a spec so the script detects the feature
spec_dir = repo / "specs" / "001-test-feature"
spec_dir.mkdir(parents=True)
(spec_dir / "plan.md").write_text(
"# Test Feature Plan\n\n"
"## Technology Stack\n\n"
"- Language: Python\n"
"- Framework: FastAPI\n"
)
return repo
def _run_update(self, repo, agent_type="cursor-agent"):
"""Run update-agent-context.sh for a specific agent type."""
script = os.path.abspath(SCRIPT_PATH)
result = subprocess.run(
["bash", script, agent_type],
cwd=str(repo),
capture_output=True,
text=True,
timeout=30,
)
return result
def test_new_mdc_file_has_frontmatter(self, git_repo):
"""Creating a new .mdc file must include YAML frontmatter."""
result = self._run_update(git_repo)
assert result.returncode == 0, f"Script failed: {result.stderr}"
mdc_file = git_repo / ".cursor" / "rules" / "specify-rules.mdc"
assert mdc_file.exists(), "Cursor .mdc file was not created"
content = mdc_file.read_text()
lines = content.splitlines()
# First line must be the opening ---
assert lines[0] == "---", f"Expected frontmatter start, got: {lines[0]}"
# Check all frontmatter lines are present
for expected in EXPECTED_FRONTMATTER_LINES:
assert expected in content, f"Missing frontmatter line: {expected}"
# Content after frontmatter should be the template content
assert "Development Guidelines" in content
def test_existing_mdc_without_frontmatter_gets_it_added(self, git_repo):
"""Updating an existing .mdc file that lacks frontmatter must add it."""
# First, create the file WITHOUT frontmatter (simulating pre-fix state)
cursor_dir = git_repo / ".cursor" / "rules"
cursor_dir.mkdir(parents=True, exist_ok=True)
mdc_file = cursor_dir / "specify-rules.mdc"
mdc_file.write_text(
"# repo Development Guidelines\n\n"
"Auto-generated from all feature plans. Last updated: 2025-01-01\n\n"
"## Active Technologies\n\n"
"- Python + FastAPI (main)\n\n"
"## Recent Changes\n\n"
"- main: Added Python + FastAPI\n"
)
result = self._run_update(git_repo)
assert result.returncode == 0, f"Script failed: {result.stderr}"
content = mdc_file.read_text()
lines = content.splitlines()
assert lines[0] == "---", f"Expected frontmatter start, got: {lines[0]}"
for expected in EXPECTED_FRONTMATTER_LINES:
assert expected in content, f"Missing frontmatter line: {expected}"
def test_existing_mdc_with_frontmatter_not_duplicated(self, git_repo):
"""Updating an .mdc file that already has frontmatter must not duplicate it."""
cursor_dir = git_repo / ".cursor" / "rules"
cursor_dir.mkdir(parents=True, exist_ok=True)
mdc_file = cursor_dir / "specify-rules.mdc"
frontmatter = (
"---\n"
"description: Project Development Guidelines\n"
'globs: ["**/*"]\n'
"alwaysApply: true\n"
"---\n\n"
)
body = (
"# repo Development Guidelines\n\n"
"Auto-generated from all feature plans. Last updated: 2025-01-01\n\n"
"## Active Technologies\n\n"
"- Python + FastAPI (main)\n\n"
"## Recent Changes\n\n"
"- main: Added Python + FastAPI\n"
)
mdc_file.write_text(frontmatter + body)
result = self._run_update(git_repo)
assert result.returncode == 0, f"Script failed: {result.stderr}"
content = mdc_file.read_text()
# Count occurrences of the frontmatter delimiter
assert content.count("alwaysApply: true") == 1, (
"Frontmatter was duplicated"
)
def test_non_mdc_file_has_no_frontmatter(self, git_repo):
"""Non-.mdc agent files (e.g., Claude) must NOT get frontmatter."""
result = self._run_update(git_repo, agent_type="claude")
assert result.returncode == 0, f"Script failed: {result.stderr}"
claude_file = git_repo / ".claude" / "CLAUDE.md"
if claude_file.exists():
content = claude_file.read_text()
assert not content.startswith("---"), (
"Non-mdc file should not have frontmatter"
)

File diff suppressed because it is too large Load Diff

1712
tests/test_presets.py Normal file

File diff suppressed because it is too large Load Diff