Merge pull request #266 from anthropics/isabella/enablement-plugins

Merge slash commands and skills in claude-automation-recommender skill
This commit is contained in:
isabella-anthropic
2026-01-20 21:38:07 -08:00
committed by GitHub
8 changed files with 576 additions and 542 deletions

Binary file not shown.

Before

Width:  |  Height:  |  Size: 522 KiB

After

Width:  |  Height:  |  Size: 532 KiB

View File

@@ -1,6 +1,6 @@
--- ---
name: claude-automation-recommender name: claude-automation-recommender
description: Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, slash commands, plugins, MCP servers). Use when user asks for automation recommendations, wants to optimize their Claude Code setup, mentions improving Claude Code workflows, asks how to first set up Claude Code for a project, or wants to know what Claude Code features they should use. description: Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when user asks for automation recommendations, wants to optimize their Claude Code setup, mentions improving Claude Code workflows, asks how to first set up Claude Code for a project, or wants to know what Claude Code features they should use.
tools: Read, Glob, Grep, Bash tools: Read, Glob, Grep, Bash
--- ---
@@ -14,6 +14,7 @@ Analyze codebase patterns to recommend tailored Claude Code automations across a
- **Recommend 1-2 of each type**: Don't overwhelm - surface the top 1-2 most valuable automations per category - **Recommend 1-2 of each type**: Don't overwhelm - surface the top 1-2 most valuable automations per category
- **If user asks for a specific type**: Focus only on that type and provide more options (3-5 recommendations) - **If user asks for a specific type**: Focus only on that type and provide more options (3-5 recommendations)
- **Go beyond the reference lists**: The reference files contain common patterns, but use web search to find recommendations specific to the codebase's tools, frameworks, and libraries
- **Tell users they can ask for more**: End by noting they can request more recommendations for any specific category - **Tell users they can ask for more**: End by noting they can request more recommendations for any specific category
## Automation Types Overview ## Automation Types Overview
@@ -22,8 +23,7 @@ Analyze codebase patterns to recommend tailored Claude Code automations across a
|------|----------| |------|----------|
| **Hooks** | Automatic actions on tool events (format on save, lint, block edits) | | **Hooks** | Automatic actions on tool events (format on save, lint, block edits) |
| **Subagents** | Specialized reviewers/analyzers that run in parallel | | **Subagents** | Specialized reviewers/analyzers that run in parallel |
| **Skills** | Packaged expertise with workflows and reference material | | **Skills** | Packaged expertise, workflows, and repeatable tasks (invoked by Claude or user via `/skill-name`) |
| **Slash Commands** | Quick, repeatable prompts with arguments |
| **Plugins** | Collections of skills that can be installed | | **Plugins** | Collections of skills that can be installed |
| **MCP Servers** | External tool integrations (databases, APIs, browsers, docs) | | **MCP Servers** | External tool integrations (databases, APIs, browsers, docs) |
@@ -86,20 +86,30 @@ See [references/mcp-servers.md](references/mcp-servers.md) for detailed patterns
#### B. Skills Recommendations #### B. Skills Recommendations
See [references/skills-reference.md](references/skills-reference.md) for patterns. See [references/skills-reference.md](references/skills-reference.md) for details.
| Codebase Signal | Recommended Skill | Create skills in `.claude/skills/<name>/SKILL.md`. Some are also available via plugins:
|-----------------|-------------------|
| Complex implementation tasks | **Plan agent** - Architecture planning | | Codebase Signal | Skill | Plugin |
| Large codebase | **Explore agent** - Codebase navigation | |-----------------|-------|--------|
| Creates documents | **docx skill** - Word document generation | | Building plugins | skill-development | plugin-dev |
| Creates spreadsheets | **xlsx skill** - Excel creation | | Git commits | commit | commit-commands |
| Creates presentations | **pptx skill** - PowerPoint generation | | React/Vue/Angular | frontend-design | frontend-design |
| PDF workflows | **pdf skill** - PDF manipulation | | Automation rules | writing-rules | hookify |
| Frontend UI work | **frontend-design** - UI component design | | Feature planning | feature-dev | feature-dev |
| Needs custom Claude tools | **mcp-builder** - Build MCP servers |
| Wants branded output | **brand-guidelines** - Apply brand styling | **Custom skills to create** (with templates, scripts, examples):
| Testing web apps | **webapp-testing** - Playwright testing |
| Codebase Signal | Skill to Create | Invocation |
|-----------------|-----------------|------------|
| API routes | **api-doc** (with OpenAPI template) | Both |
| Database project | **create-migration** (with validation script) | User-only |
| Test suite | **gen-test** (with example tests) | User-only |
| Component library | **new-component** (with templates) | User-only |
| PR workflow | **pr-check** (with checklist) | User-only |
| Releases | **release-notes** (with git context) | User-only |
| Code style | **project-conventions** | Claude-only |
| Onboarding | **setup-dev** (with prereq script) | User-only |
#### C. Hooks Recommendations #### C. Hooks Recommendations
@@ -128,20 +138,7 @@ See [references/subagent-templates.md](references/subagent-templates.md) for tem
| Frontend heavy | **ui-reviewer** - Accessibility review | | Frontend heavy | **ui-reviewer** - Accessibility review |
| Needs more tests | **test-writer** - Test generation | | Needs more tests | **test-writer** - Test generation |
#### E. Slash Command Recommendations #### E. Plugin Recommendations
See [references/slash-command-examples.md](references/slash-command-examples.md) for templates.
| Codebase Signal | Recommended Command |
|-----------------|---------------------|
| Git-based workflow | `/pr-review` - Review PR changes |
| Test suite exists | `/test [file]` - Run specific tests |
| CI/CD configured | `/ci-fix` - Debug CI failures |
| Changelog file | `/changelog` - Update changelog |
| API routes | `/api-doc [route]` - Document endpoint |
| Complex codebase | `/explain [file]` - Explain code |
#### F. Plugin Recommendations
See [references/plugins-reference.md](references/plugins-reference.md) for available plugins. See [references/plugins-reference.md](references/plugins-reference.md) for available plugins.
@@ -180,7 +177,16 @@ I've analyzed your codebase and identified the top automations for each category
#### [skill name] #### [skill name]
**Why**: [specific reason] **Why**: [specific reason]
**How**: [invocation method] **Create**: `.claude/skills/[name]/SKILL.md`
**Invocation**: User-only / Both / Claude-only
**Also available in**: [plugin-name] plugin (if applicable)
```yaml
---
name: [skill-name]
description: [what it does]
disable-model-invocation: true # for user-only
---
```
--- ---
@@ -200,14 +206,6 @@ I've analyzed your codebase and identified the top automations for each category
--- ---
### 📝 Slash Commands
#### /[command]
**Why**: [specific reason]
**Where**: `.claude/commands/[name].md`
---
**Want more?** Ask for additional recommendations for any specific category (e.g., "show me more MCP server options" or "what other hooks would help?"). **Want more?** Ask for additional recommendations for any specific category (e.g., "show me more MCP server options" or "what other hooks would help?").
**Want help implementing any of these?** Just ask and I can help you set up any of the recommendations above. **Want help implementing any of these?** Just ask and I can help you set up any of the recommendations above.
@@ -223,10 +221,18 @@ I've analyzed your codebase and identified the top automations for each category
- Cloud infrastructure management - Cloud infrastructure management
### When to Recommend Skills ### When to Recommend Skills
- Complex multi-step workflows
- Document generation needs - Document generation (docx, xlsx, pptx, pdf — also in plugins)
- Specialized domain knowledge needed - Frequently repeated prompts or workflows
- Repeatable processes with templates - Project-specific tasks with arguments
- Applying templates or scripts to tasks (skills can bundle supporting files)
- Quick actions invoked with `/skill-name`
- Workflows that should run in isolation (`context: fork`)
**Invocation control:**
- `disable-model-invocation: true` — User-only (for side effects: deploy, commit, send)
- `user-invocable: false` — Claude-only (for background knowledge)
- Default (omit both) — Both can invoke
### When to Recommend Hooks ### When to Recommend Hooks
- Repetitive post-edit actions (formatting, linting) - Repetitive post-edit actions (formatting, linting)
@@ -238,11 +244,6 @@ I've analyzed your codebase and identified the top automations for each category
- Parallel review workflows - Parallel review workflows
- Background quality checks - Background quality checks
### When to Recommend Slash Commands
- Frequently repeated prompts
- Commands with arguments
- Quick project-specific workflows
### When to Recommend Plugins ### When to Recommend Plugins
- Need multiple related skills - Need multiple related skills
- Want pre-packaged automation bundles - Want pre-packaged automation bundles

View File

@@ -1,6 +1,8 @@
# Hooks Recommendations # Hooks Recommendations
Hooks automatically run commands in response to Claude's tool usage. They're ideal for enforcement and automation that should happen consistently. Hooks automatically run commands in response to Claude Code events. They're ideal for enforcement and automation that should happen consistently.
**Note**: These are common patterns. Use web search to find hooks for tools/frameworks not listed here to recommend the best hooks for the user.
## Auto-Formatting Hooks ## Auto-Formatting Hooks
@@ -135,6 +137,83 @@ Hooks automatically run commands in response to Claude's tool usage. They're ide
--- ---
## Notification Hooks
Notification hooks run when Claude Code sends notifications. Use matchers to filter by notification type.
### Permission Alerts
| Matcher | Use Case |
|---------|----------|
| `permission_prompt` | Alert when Claude requests permissions |
**Recommend**: Play sound, send desktop notification, or log permission requests
**Value**: Never miss permission prompts when multitasking
### Idle Notifications
| Matcher | Use Case |
|---------|----------|
| `idle_prompt` | Alert when Claude is waiting for input (60+ seconds idle) |
**Recommend**: Play sound or send notification when Claude needs attention
**Value**: Know when Claude is ready for your input
### Example Configuration
```json
{
"hooks": {
"Notification": [
{
"matcher": "permission_prompt",
"hooks": [
{
"type": "command",
"command": "afplay /System/Library/Sounds/Ping.aiff"
}
]
},
{
"matcher": "idle_prompt",
"hooks": [
{
"type": "command",
"command": "osascript -e 'display notification \"Claude is waiting\" with title \"Claude Code\"'"
}
]
}
]
}
}
```
### Available Matchers
| Matcher | Triggers When |
|---------|---------------|
| `permission_prompt` | Claude needs permission for a tool |
| `idle_prompt` | Claude waiting for input (60+ seconds) |
| `auth_success` | Authentication succeeds |
| `elicitation_dialog` | MCP tool needs input |
---
## Quick Reference: Detection → Recommendation
| If You See | Recommend This Hook |
|------------|-------------------|
| Prettier config | Auto-format on Edit/Write |
| ESLint config | Auto-lint on Edit/Write |
| Ruff/Black config | Auto-format Python |
| tsconfig.json | Type-check on Edit |
| Test directory | Run related tests on Edit |
| .env files | Block .env edits |
| Lock files | Block lock file edits |
| Go project | gofmt on Edit |
| Rust project | rustfmt on Edit |
| Multitasking workflow | Notification hooks for alerts |
---
## Hook Placement ## Hook Placement
Hooks go in `.claude/settings.json`: Hooks go in `.claude/settings.json`:

View File

@@ -2,6 +2,8 @@
MCP (Model Context Protocol) servers extend Claude's capabilities by connecting to external tools and services. MCP (Model Context Protocol) servers extend Claude's capabilities by connecting to external tools and services.
**Note**: These are common MCP servers. Use web search to find MCP servers specific to the codebase's services and integrations.
## Setup & Team Sharing ## Setup & Team Sharing
**Connection methods:** **Connection methods:**

View File

@@ -1,89 +1,98 @@
# Plugin Recommendations # Plugin Recommendations
Plugins are installable collections of skills that extend Claude's capabilities. They bundle related skills, reference materials, and workflows together. Plugins are installable collections of skills, commands, agents, and hooks. Install via `/plugin install`.
## Available Plugins **Note**: These are plugins from the official repository. Use web search to discover additional community plugins.
### anthropic-agent-skills
**The comprehensive skills bundle from Anthropic**
| Recommend When | Examples |
|----------------|----------|
| General productivity | Default recommendation |
| Document workflows | docx, xlsx, pptx, pdf |
| Frontend development | frontend-design, webapp-testing |
| Building AI tools | mcp-builder, skill-creator |
| Creative work | canvas-design, algorithmic-art |
**Includes**: docx, xlsx, pptx, pdf, frontend-design, canvas-design, algorithmic-art, mcp-builder, skill-creator, webapp-testing, doc-coauthoring, internal-comms, brand-guidelines, theme-factory, slack-gif-creator, web-artifacts-builder
**Install**: This plugin is commonly pre-installed. Check with `claude plugins list`.
--- ---
### frontend-design ## Official Plugins
**Specialized frontend UI development**
| Recommend When | Examples | ### Development & Code Quality
|----------------|----------|
| React/Vue/Angular work | Component development |
| Landing pages | Marketing sites |
| Dashboard UI | Admin interfaces |
| Design system | Component libraries |
**Value**: Creates distinctive, production-grade UI avoiding generic AI aesthetics. | Plugin | Best For | Key Features |
|--------|----------|--------------|
| **plugin-dev** | Building Claude Code plugins | Skills for creating skills, hooks, commands, agents |
| **pr-review-toolkit** | PR review workflows | Specialized review agents (code, tests, types) |
| **code-review** | Automated code review | Multi-agent review with confidence scoring |
| **code-simplifier** | Code refactoring | Simplify code while preserving functionality |
| **feature-dev** | Feature development | End-to-end feature workflow with agents |
### Git & Workflow
| Plugin | Best For | Key Features |
|--------|----------|--------------|
| **commit-commands** | Git workflows | /commit, /commit-push-pr commands |
| **hookify** | Automation rules | Create hooks from conversation patterns |
### Frontend
| Plugin | Best For | Key Features |
|--------|----------|--------------|
| **frontend-design** | UI development | Production-grade UI, avoids generic aesthetics |
### Learning & Guidance
| Plugin | Best For | Key Features |
|--------|----------|--------------|
| **explanatory-output-style** | Learning | Educational insights about code choices |
| **learning-output-style** | Interactive learning | Requests contributions at decision points |
| **security-guidance** | Security awareness | Warns about security issues when editing |
### Language Servers (LSP)
| Plugin | Language |
|--------|----------|
| **typescript-lsp** | TypeScript/JavaScript |
| **pyright-lsp** | Python |
| **gopls-lsp** | Go |
| **rust-analyzer-lsp** | Rust |
| **clangd-lsp** | C/C++ |
| **jdtls-lsp** | Java |
| **kotlin-lsp** | Kotlin |
| **swift-lsp** | Swift |
| **csharp-lsp** | C# |
| **php-lsp** | PHP |
| **lua-lsp** | Lua |
--- ---
## Plugin vs Individual Skills ## Quick Reference: Codebase → Plugin
### When to Recommend Plugin Installation | Codebase Signal | Recommended Plugin |
- User needs multiple related skills |-----------------|-------------------|
- Team standardization desired | Building plugins | plugin-dev |
- First-time Claude Code setup | PR-based workflow | pr-review-toolkit |
- Comprehensive capability needed | Git commits | commit-commands |
| React/Vue/Angular | frontend-design |
### When to Recommend Individual Skill Usage | Want automation rules | hookify |
- Specific one-time task | TypeScript project | typescript-lsp |
- Already have plugin installed | Python project | pyright-lsp |
- Just need one capability | Go project | gopls-lsp |
| Security-sensitive code | security-guidance |
| Learning/onboarding | explanatory-output-style |
--- ---
## Checking Installed Plugins ## Plugin Management
```bash ```bash
# List installed plugins # Install a plugin
claude plugins list /plugin install <plugin-name>
# Check available skills # List installed plugins
claude skills list /plugin list
# View plugin details
/plugin info <plugin-name>
``` ```
--- ---
## Custom Plugin Development ## When to Recommend Plugins
For teams wanting to bundle their own skills: **Recommend plugin installation when:**
- User wants to install Claude Code automations from Anthropic's official repository or another shared marketplace
| Recommend When | Examples | - User needs multiple related capabilities
|----------------|----------| - Team wants standardized workflows
| Company-specific workflows | Internal processes | - First-time Claude Code setup
| Team best practices | Shared patterns |
| Domain expertise | Industry knowledge |
| Tool integrations | Internal tools |
Use the **skill-creator** skill to build individual skills, then bundle them into a plugin for team distribution.
---
## Quick Reference
| Need | Recommended Plugin/Skill |
|------|-------------------------|
| General productivity | anthropic-agent-skills (full bundle) |
| Document creation | docx, xlsx, pptx, pdf skills |
| Frontend work | frontend-design plugin |
| Testing | webapp-testing skill |
| Building tools | mcp-builder skill |
| Custom workflows | skill-creator skill |

View File

@@ -1,216 +1,408 @@
# Skills Recommendations # Skills Recommendations
Skills are packaged expertise with workflows, reference materials, and best practices that Claude can invoke for specialized tasks. Skills are packaged expertise with workflows, reference materials, and best practices. Create them in `.claude/skills/<name>/SKILL.md`. Skills can be invoked by Claude automatically when relevant, or by users directly with `/skill-name`.
## Built-in Agents Some pre-built skills are available through official plugins (install via `/plugin install`).
### Plan Agent **Note**: These are common patterns. Use web search to find skill ideas specific to the codebase's tools and frameworks.
**Best for**: Complex implementations needing architectural planning
| Recommend When | Examples |
|----------------|----------|
| Multi-file changes needed | New feature development |
| Architectural decisions | System design |
| Unknown scope | Needs investigation first |
| Multiple valid approaches | Trade-off analysis |
**Value**: Thinks through implementation before coding, identifies files to change, considers edge cases.
### Explore Agent
**Best for**: Understanding large or unfamiliar codebases
| Recommend When | Examples |
|----------------|----------|
| Large codebase (>500 files) | Navigate efficiently |
| New to the project | Understand structure |
| Finding patterns | How is X done? |
| Debugging | Trace execution paths |
**Value**: Quickly searches, reads, and synthesizes information across many files.
--- ---
## Document Creation Skills ## Available from Official Plugins
### docx (Word Documents) ### Plugin Development (plugin-dev)
**Best for**: Creating and editing Word documents
| Recommend When | Examples | | Skill | Best For |
|----------------|----------| |-------|----------|
| Report generation | Technical reports | | **skill-development** | Creating new skills with proper structure |
| Contract templates | Legal documents | | **hook-development** | Building hooks for automation |
| Documentation export | Share with non-developers | | **command-development** | Creating slash commands |
| Tracked changes | Review workflows | | **agent-development** | Building specialized subagents |
| **mcp-integration** | Integrating MCP servers into plugins |
| **plugin-structure** | Understanding plugin architecture |
### xlsx (Spreadsheets) ### Git Workflows (commit-commands)
**Best for**: Creating and analyzing Excel files
| Recommend When | Examples | | Skill | Best For |
|----------------|----------| |-------|----------|
| Data analysis | Process CSV/Excel data | | **commit** | Creating git commits with proper messages |
| Report generation | Formatted tables | | **commit-push-pr** | Full commit, push, and PR workflow |
| Financial models | Formulas and calculations |
| Data transformation | Clean and reshape data |
### pptx (Presentations) ### Frontend (frontend-design)
**Best for**: Creating PowerPoint presentations
| Recommend When | Examples | | Skill | Best For |
|----------------|----------| |-------|----------|
| Technical presentations | Architecture diagrams | | **frontend-design** | Creating polished UI components |
| Project updates | Status slides |
| Demo decks | Feature walkthroughs |
| Training materials | Educational content |
### pdf (PDF Documents)
**Best for**: PDF manipulation and creation
| Recommend When | Examples |
|----------------|----------|
| Form filling | Complete PDF forms |
| Document merging | Combine files |
| Text extraction | Parse PDF content |
| PDF generation | Create from data |
---
## Frontend & Design Skills
### frontend-design
**Best for**: Creating polished, production-ready UI components
| Recommend When | Examples |
|----------------|----------|
| UI component work | React, Vue, Angular |
| Landing pages | Marketing sites |
| Dashboard design | Data visualization |
| Design system work | Component libraries |
**Value**: Creates distinctive, high-quality UI instead of generic AI aesthetics. **Value**: Creates distinctive, high-quality UI instead of generic AI aesthetics.
### canvas-design ### Automation Rules (hookify)
**Best for**: Creating visual art and static designs
| Recommend When | Examples | | Skill | Best For |
|----------------|----------| |-------|----------|
| Poster creation | Marketing materials | | **writing-rules** | Creating hookify rules for automation |
| Visual diagrams | Architecture visuals |
| Infographics | Data visualization |
### algorithmic-art ### Feature Development (feature-dev)
**Best for**: Generative art with p5.js
| Recommend When | Examples | | Skill | Best For |
|----------------|----------| |-------|----------|
| Interactive visuals | Creative coding | | **feature-dev** | End-to-end feature development workflow |
| Generative patterns | Flow fields, particles |
| Data art | Algorithmic visualization |
### theme-factory
**Best for**: Applying themes to artifacts
| Recommend When | Examples |
|----------------|----------|
| Brand consistency | Apply company colors |
| Document styling | Professional look |
| Presentation themes | Consistent decks |
### brand-guidelines
**Best for**: Applying Anthropic brand styling
| Recommend When | Examples |
|----------------|----------|
| Anthropic materials | Official branding |
| Partner materials | Co-branded content |
--- ---
## Development Skills ## Quick Reference: Official Plugin Skills
### mcp-builder | Codebase Signal | Skill | Plugin |
**Best for**: Creating MCP servers to extend Claude |-----------------|-------|--------|
| Building plugins | skill-development | plugin-dev |
| Recommend When | Examples | | Git commits | commit | commit-commands |
|----------------|----------| | React/Vue/Angular | frontend-design | frontend-design |
| Custom tool needs | Internal APIs | | Automation rules | writing-rules | hookify |
| API integrations | Third-party services | | Feature planning | feature-dev | feature-dev |
| Workflow automation | Custom tooling |
**Value**: Guides creation of well-designed MCP servers in Python (FastMCP) or TypeScript.
### webapp-testing
**Best for**: Testing web applications with Playwright
| Recommend When | Examples |
|----------------|----------|
| UI testing needs | Verify functionality |
| Visual debugging | Screenshot issues |
| Browser automation | Interactive testing |
| Console log analysis | Debug JS errors |
### skill-creator
**Best for**: Creating new skills for Claude
| Recommend When | Examples |
|----------------|----------|
| Repeatable workflows | Standardize processes |
| Domain expertise | Package knowledge |
| Team patterns | Share best practices |
--- ---
## Collaboration Skills ## Custom Project Skills
### doc-coauthoring Create project-specific skills in `.claude/skills/<name>/SKILL.md`.
**Best for**: Co-authoring documentation with users
| Recommend When | Examples | ### Skill Structure
|----------------|----------|
| Technical specs | RFC documents |
| Decision docs | ADRs |
| Proposals | Feature proposals |
| Documentation | User guides |
**Value**: Structured workflow for iterative document refinement. ```
.claude/skills/
└── my-skill/
├── SKILL.md # Main instructions (required)
├── template.yaml # Template to apply
├── scripts/
│ └── validate.sh # Script to run
└── examples/ # Reference examples
```
### internal-comms ### Frontmatter Reference
**Best for**: Writing internal communications
| Recommend When | Examples | ```yaml
|----------------|----------| ---
| Status reports | Project updates | name: skill-name
| Announcements | Team comms | description: What this skill does and when to use it
| Incident reports | Post-mortems | disable-model-invocation: true # Only user can invoke (for side effects)
| FAQs | Knowledge sharing | user-invocable: false # Only Claude can invoke (for background knowledge)
allowed-tools: Read, Grep, Glob # Restrict tool access
context: fork # Run in isolated subagent
agent: Explore # Which agent type when forked
---
```
### Invocation Control
| Setting | User | Claude | Use for |
|---------|------|--------|---------|
| (default) | ✓ | ✓ | General-purpose skills |
| `disable-model-invocation: true` | ✓ | ✗ | Side effects (deploy, send) |
| `user-invocable: false` | ✗ | ✓ | Background knowledge |
--- ---
## Multimedia Skills ## Custom Skill Examples
### slack-gif-creator ### API Documentation with OpenAPI Template
**Best for**: Creating animated GIFs for Slack
| Recommend When | Examples | Apply a YAML template to generate consistent API docs:
|----------------|----------|
| Team celebrations | Achievements | ```
| Demo animations | Feature previews | .claude/skills/api-doc/
| Fun reactions | Custom emoji-style GIFs | ├── SKILL.md
└── openapi-template.yaml
```
**SKILL.md:**
```yaml
---
name: api-doc
description: Generate OpenAPI documentation for an endpoint. Use when documenting API routes.
---
Generate OpenAPI documentation for the endpoint at $ARGUMENTS.
Use the template in [openapi-template.yaml](openapi-template.yaml) as the structure.
1. Read the endpoint code
2. Extract path, method, parameters, request/response schemas
3. Fill in the template with actual values
4. Output the completed YAML
```
**openapi-template.yaml:**
```yaml
paths:
/{path}:
{method}:
summary: ""
description: ""
parameters: []
requestBody:
content:
application/json:
schema: {}
responses:
"200":
description: ""
content:
application/json:
schema: {}
```
--- ---
## Quick Reference: Detection Patterns ### Database Migration Generator with Script
| Look For | Suggests Skill | Generate and validate migrations using a bundled script:
|----------|---------------|
| Complex task, multiple files | Plan agent | ```
| "How does X work?" | Explore agent | .claude/skills/create-migration/
| `.docx` files or doc requests | docx skill | ├── SKILL.md
| `.xlsx` files or spreadsheet work | xlsx skill | └── scripts/
| Presentation needs | pptx skill | └── validate-migration.sh
| PDF files to process | pdf skill | ```
| React/Vue/Angular components | frontend-design |
| UI design requests | canvas-design | **SKILL.md:**
| Testing local web app | webapp-testing | ```yaml
| "Build an MCP server" | mcp-builder | ---
| Documentation writing | doc-coauthoring | name: create-migration
| Internal announcement | internal-comms | description: Create a database migration file
disable-model-invocation: true
allowed-tools: Read, Write, Bash
---
Create a migration for: $ARGUMENTS
1. Generate migration file in `migrations/` with timestamp prefix
2. Include up and down functions
3. Run validation: `bash ~/.claude/skills/create-migration/scripts/validate-migration.sh`
4. Report any issues found
```
**scripts/validate-migration.sh:**
```bash
#!/bin/bash
# Validate migration syntax
npx prisma validate 2>&1 || echo "Validation failed"
```
---
### Test Generator with Examples
Generate tests following project patterns:
```
.claude/skills/gen-test/
├── SKILL.md
└── examples/
├── unit-test.ts
└── integration-test.ts
```
**SKILL.md:**
```yaml
---
name: gen-test
description: Generate tests for a file following project conventions
disable-model-invocation: true
---
Generate tests for: $ARGUMENTS
Reference these examples for the expected patterns:
- Unit tests: [examples/unit-test.ts](examples/unit-test.ts)
- Integration tests: [examples/integration-test.ts](examples/integration-test.ts)
1. Analyze the source file
2. Identify functions/methods to test
3. Generate tests matching project conventions
4. Place in appropriate test directory
```
---
### Component Generator with Template
Scaffold new components from a template:
```
.claude/skills/new-component/
├── SKILL.md
└── templates/
├── component.tsx.template
├── component.test.tsx.template
└── component.stories.tsx.template
```
**SKILL.md:**
```yaml
---
name: new-component
description: Scaffold a new React component with tests and stories
disable-model-invocation: true
---
Create component: $ARGUMENTS
Use templates in [templates/](templates/) directory:
1. Generate component from component.tsx.template
2. Generate tests from component.test.tsx.template
3. Generate Storybook story from component.stories.tsx.template
Replace {{ComponentName}} with the PascalCase name.
Replace {{component-name}} with the kebab-case name.
```
---
### PR Review with Checklist
Review PRs against a project-specific checklist:
```
.claude/skills/pr-check/
├── SKILL.md
└── checklist.md
```
**SKILL.md:**
```yaml
---
name: pr-check
description: Review PR against project checklist
disable-model-invocation: true
context: fork
---
## PR Context
- Diff: !`gh pr diff`
- Description: !`gh pr view`
Review against [checklist.md](checklist.md).
For each item, mark ✅ or ❌ with explanation.
```
**checklist.md:**
```markdown
## PR Checklist
- [ ] Tests added for new functionality
- [ ] No console.log statements
- [ ] Error handling includes user-facing messages
- [ ] API changes are backwards compatible
- [ ] Database migrations are reversible
```
---
### Release Notes Generator
Generate release notes from git history:
**SKILL.md:**
```yaml
---
name: release-notes
description: Generate release notes from commits since last tag
disable-model-invocation: true
---
## Recent Changes
- Commits since last tag: !`git log $(git describe --tags --abbrev=0)..HEAD --oneline`
- Last tag: !`git describe --tags --abbrev=0`
Generate release notes:
1. Group commits by type (feat, fix, docs, etc.)
2. Write user-friendly descriptions
3. Highlight breaking changes
4. Format as markdown
```
---
### Project Conventions (Claude-only)
Background knowledge Claude applies automatically:
**SKILL.md:**
```yaml
---
name: project-conventions
description: Code style and patterns for this project. Apply when writing or reviewing code.
user-invocable: false
---
## Naming Conventions
- React components: PascalCase
- Utilities: camelCase
- Constants: UPPER_SNAKE_CASE
- Files: kebab-case
## Patterns
- Use `Result<T, E>` for fallible operations, not exceptions
- Prefer composition over inheritance
- All API responses use `{ data, error, meta }` shape
## Forbidden
- No `any` types
- No `console.log` in production code
- No synchronous file I/O
```
---
### Environment Setup
Onboard new developers with setup script:
```
.claude/skills/setup-dev/
├── SKILL.md
└── scripts/
└── check-prerequisites.sh
```
**SKILL.md:**
```yaml
---
name: setup-dev
description: Set up development environment for new contributors
disable-model-invocation: true
---
Set up development environment:
1. Check prerequisites: `bash scripts/check-prerequisites.sh`
2. Install dependencies: `npm install`
3. Copy environment template: `cp .env.example .env`
4. Set up database: `npm run db:setup`
5. Verify setup: `npm test`
Report any issues encountered.
```
---
## Argument Patterns
| Pattern | Meaning | Example |
|---------|---------|---------|
| `$ARGUMENTS` | All args as string | `/deploy staging` → "staging" |
Arguments are appended as `ARGUMENTS: <value>` if `$ARGUMENTS` isn't in the skill.
## Dynamic Context Injection
Use `!`command`` to inject live data before the skill runs:
```yaml
## Current State
- Branch: !`git branch --show-current`
- Status: !`git status --short`
```
The command output replaces the placeholder before Claude sees the skill content.

View File

@@ -1,251 +0,0 @@
# Slash Command Recommendations
Slash commands are quick, repeatable prompts with optional arguments. They're ideal for frequently used workflows that don't need the overhead of a subagent.
## Code Review Commands
### /pr-review
**Best for**: Reviewing current branch changes
| Recommend When | Detection |
|----------------|-----------|
| Git-based workflow | `.git/` directory |
| PR-driven development | GitHub/GitLab remote |
| Regular code reviews | Team process |
**Value**: Quick review of PR changes with actionable feedback
---
### /quick-review
**Best for**: Fast review of a specific file
| Recommend When | Detection |
|----------------|-----------|
| Single file review needs | Ad-hoc reviews |
| Pre-commit checks | Before committing |
**Value**: Focused review without full PR context
---
## Testing Commands
### /test
**Best for**: Running tests for a specific file or pattern
| Recommend When | Detection |
|----------------|-----------|
| Jest configured | `jest.config.js`, package.json |
| pytest configured | `pytest.ini`, pyproject.toml |
| vitest configured | `vitest.config.js` |
| Test directory exists | `tests/`, `__tests__/` |
**Value**: Quick test runs with failure analysis
---
### /test-file
**Best for**: Generating tests for a specific file
| Recommend When | Detection |
|----------------|-----------|
| Test framework present | Testing deps installed |
| Source files without tests | Missing test coverage |
**Value**: Generates tests following project conventions
---
## Documentation Commands
### /doc
**Best for**: Generating documentation for code
| Recommend When | Detection |
|----------------|-----------|
| JSDoc/docstring patterns | Existing doc style |
| API code | Public functions/classes |
**Value**: Consistent documentation format
---
### /api-doc
**Best for**: Documenting API endpoints
| Recommend When | Detection |
|----------------|-----------|
| REST endpoints | Express, FastAPI routes |
| OpenAPI/Swagger | Existing spec files |
| Undocumented APIs | Routes without docs |
**Value**: Generates endpoint docs with examples
---
### /changelog
**Best for**: Updating changelog with recent changes
| Recommend When | Detection |
|----------------|-----------|
| CHANGELOG.md exists | Changelog present |
| Release workflow | Semantic versioning |
**Value**: Categorized changelog entries
---
## Debugging Commands
### /debug
**Best for**: Investigating issues in code
| Recommend When | Detection |
|----------------|-----------|
| Bug reports common | Active development |
| Complex codebase | Many files/dependencies |
**Value**: Systematic debugging approach
---
### /ci-fix
**Best for**: Debugging CI/CD failures
| Recommend When | Detection |
|----------------|-----------|
| CI configured | `.github/workflows/`, `.circleci/` |
| Frequent CI failures | Active CI pipeline |
**Value**: Reproduces and fixes CI issues
---
## Refactoring Commands
### /refactor
**Best for**: Improving code structure
| Recommend When | Detection |
|----------------|-----------|
| Legacy code | Old patterns detected |
| Code smells | Long files, complex functions |
**Value**: Guided refactoring with explanations
---
### /extract
**Best for**: Extracting reusable code
| Recommend When | Detection |
|----------------|-----------|
| Code duplication | Similar patterns |
| Long functions | Needs decomposition |
**Value**: Creates clean extractions with proper types
---
## Project Commands
### /init-claude
**Best for**: Setting up Claude Code configuration
| Recommend When | Detection |
|----------------|-----------|
| No `.claude/` directory | New project setup |
| No CLAUDE.md | Missing context |
**Value**: Creates complete Claude Code setup
---
### /setup
**Best for**: Developer environment setup
| Recommend When | Detection |
|----------------|-----------|
| New developer onboarding | README instructions |
| Complex setup | Multiple steps needed |
**Value**: Automated environment setup
---
## Utility Commands
### /explain
**Best for**: Understanding code
| Recommend When | Detection |
|----------------|-----------|
| Complex codebase | New to project |
| Legacy code | Undocumented patterns |
**Value**: Clear explanations without jargon
---
### /find
**Best for**: Locating code by description
| Recommend When | Detection |
|----------------|-----------|
| Large codebase | Many files |
| Unfamiliar structure | New to project |
**Value**: Finds code by concept, not just text
---
## Quick Reference: Detection → Recommendation
| If You See | Recommend Command |
|------------|------------------|
| Git repository | /pr-review |
| Test framework | /test |
| Test gaps | /test-file |
| API routes | /api-doc |
| CHANGELOG.md | /changelog |
| CI/CD config | /ci-fix |
| Complex code | /explain |
| Large codebase | /find |
| No .claude/ | /init-claude |
---
## Slash Command Placement
Commands go in `.claude/commands/`:
```
.claude/
└── commands/
├── test.md
├── pr-review.md
└── explain.md
```
---
## Argument Patterns
| Pattern | Meaning | Example |
|---------|---------|---------|
| `<arg>` | Required | `<file-path>` |
| `[arg]` | Optional | `[branch-name]` |
| `$ARGUMENTS` | All args as string | Full input |
| `$1`, `$2` | Positional args | First, second arg |
---
## Tool Restrictions Guide
| Use Case | Restrict To |
|----------|------------|
| Read-only | Read, Grep, Glob |
| Can edit | + Write |
| Can run commands | + Bash |
| Full access | Omit restriction |

View File

@@ -2,6 +2,8 @@
Subagents are specialized Claude instances that run in parallel, each with their own context window and tool access. They're ideal for focused reviews, analysis, or generation tasks. Subagents are specialized Claude instances that run in parallel, each with their own context window and tool access. They're ideal for focused reviews, analysis, or generation tasks.
**Note**: These are common patterns. Design custom subagents based on the codebase's specific review and analysis needs.
## Code Review Agents ## Code Review Agents
### code-reviewer ### code-reviewer