Files
claude-task-master/assets/claude/commands/tm/add-task/add-task.md
Joe Danziger 95c299df64 Unify and streamline profile system architecture (#853)
* move claude rules and commands to assets/claude

* update claude profile to copy assets/claude to .claude

* fix formatting

* feat(profiles): Implement unified profile system

- Convert Claude and Codex profiles to use createProfile() factory
- Remove simple vs complex profile distinction in rule transformer
- Unify convertAllRulesToProfileRules() to handle all profiles consistently
- Fix mcpConfigPath construction in base-profile.js for null mcpConfigName
- Update terminology from 'simpleProfiles' to 'assetOnlyProfiles' throughout
- Ensure Claude .claude directory copying works in both CLI and MCP contexts
- All profiles now follow same execution flow with proper lifecycle functions

Changes:
- src/profiles/claude.js: Convert to createProfile() factory pattern
- src/profiles/codex.js: Convert to createProfile() factory pattern
- src/utils/rule-transformer.js: Unified profile handling logic
- src/utils/profiles.js: Remove simple profile categorization
- src/profiles/base-profile.js: Fix mcpConfigPath construction
- scripts/modules/commands.js: Update variable naming
- tests/: Update all tests for unified system and terminology

Fixes Claude profile asset copying issue in MCP context.
All tests passing (617 passed, 11 skipped).

* re-checkin claude files

* fix formatting

* chore: clean up test Claude rules files

* chore: add changeset for unified profile system

* add claude files back

* add changeset

* restore proper gitignore

* remove claude agents file from root

* remove incorrect doc

* simplify profiles and update tests

* update changeset

* update changeset

* remove profile specific code

* streamline profiles with defaults and update tests

* update changeset

* add newline at end of gitignore

* restore changes

* streamline profiles with defaults; update tests and add vscode test

* update rule profile tests

* update wording for clearer profile management

* refactor and clarify terminology

* use original projectRoot var name

* revert param desc

* use updated claude assets from neno

* add "YOUR_" before api key here

* streamline codex profile

* add gemini profile

* update gemini profile

* update tests

* relocate function

* update rules interactive setup Gemini desc

* remove duplicative code

* add comma
2025-07-09 13:22:11 +02:00

1.8 KiB

Add new tasks with intelligent parsing and context awareness.

Arguments: $ARGUMENTS

Smart Task Addition

Parse natural language to create well-structured tasks.

1. Input Understanding

I'll intelligently parse your request:

  • Natural language → Structured task
  • Detect priority from keywords (urgent, ASAP, important)
  • Infer dependencies from context
  • Suggest complexity based on description
  • Determine task type (feature, bug, refactor, test, docs)

2. Smart Parsing Examples

"Add urgent task to fix login bug" → Title: Fix login bug → Priority: high → Type: bug → Suggested complexity: medium

"Create task for API documentation after task 23 is done" → Title: API documentation → Dependencies: [23] → Type: documentation → Priority: medium

"Need to refactor auth module - depends on 12 and 15, high complexity" → Title: Refactor auth module → Dependencies: [12, 15] → Complexity: high → Type: refactor

3. Context Enhancement

Based on current project state:

  • Suggest related existing tasks
  • Warn about potential conflicts
  • Recommend dependencies
  • Propose subtasks if complex

4. Interactive Refinement

Task Preview:
─────────────
Title: [Extracted title]
Priority: [Inferred priority]
Dependencies: [Detected dependencies]
Complexity: [Estimated complexity]

Suggestions:
- Similar task #34 exists, consider as dependency?
- This seems complex, break into subtasks?
- Tasks #45-47 work on same module

5. Validation & Creation

Before creating:

  • Validate dependencies exist
  • Check for duplicates
  • Ensure logical ordering
  • Verify task completeness

6. Smart Defaults

Intelligent defaults based on:

  • Task type patterns
  • Team conventions
  • Historical data
  • Current sprint/phase

Result: High-quality tasks from minimal input.