ros/claude-plugins-official
1
0
Fork 0
mirror of https://github.com/anthropics/claude-plugins-official.git synced 2026-01-31 04:52:02 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: add claude-code-setup and claude-md-management plugins

Browse Source
This commit is contained in:
Isabella He
2026-01-16 14:34:43 -08:00
parent 9627620588
commit a86e34672c
19 changed files with 2262 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
plugins/claude-code-setup/.claude-plugin/plugin.json Normal file
View File

@@ -0,0 +1,9 @@
{
"name": "claude-code-setup",
"description": "Analyze codebases and recommend tailored Claude Code automations",
"version": "1.0.0",
"author": {
"name": "Isabella He",
"email": "isabella@anthropic.com"
}
}

29
plugins/claude-code-setup/README.md Normal file
View File

@@ -0,0 +1,29 @@
# Claude Code Setup Plugin
Analyze codebases and recommend tailored Claude Code automations - hooks, skills, MCP servers, and more.
## What It Does
Claude uses this skill to scan your codebase and recommend the top 1-2 automations in each category:
- **MCP Servers** - External integrations (context7 for docs, Playwright for frontend)
- **Skills** - Packaged expertise (Plan agent, frontend-design)
- **Hooks** - Automatic actions (auto-format, auto-lint, block sensitive files)
- **Subagents** - Specialized reviewers (security, performance, accessibility)
- **Slash Commands** - Quick workflows (/test, /pr-review, /explain)
This skill is **read-only** - it analyzes but doesn't modify files.
## Usage
```
"recommend automations for this project"
"help me set up Claude Code"
"what hooks should I use?"
```
<img src="automation-recommender-example.png" alt="Automation recommender analyzing a codebase and providing tailored recommendations" width="600">
## Author
Isabella He (isabella@anthropic.com)

BIN
plugins/claude-code-setup/automation-recommender-example.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 522 KiB

287
plugins/claude-code-setup/skills/claude-automation-recommender/SKILL.md Normal file
View File

@@ -0,0 +1,287 @@
---
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.
tools: Read, Glob, Grep, Bash
---
# Claude Automation Recommender
Analyze codebase patterns to recommend tailored Claude Code automations across all extensibility options.
**This skill is read-only.** It analyzes the codebase and outputs recommendations. It does NOT create or modify any files. Users implement the recommendations themselves or ask Claude separately to help build them.
## Output Guidelines
- **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)
- **Tell users they can ask for more**: End by noting they can request more recommendations for any specific category
## Automation Types Overview
| Type | Best For |
|------|----------|
| **Hooks** | Automatic actions on tool events (format on save, lint, block edits) |
| **Subagents** | Specialized reviewers/analyzers that run in parallel |
| **Skills** | Packaged expertise with workflows and reference material |
| **Slash Commands** | Quick, repeatable prompts with arguments |
| **Plugins** | Collections of skills that can be installed |
| **MCP Servers** | External tool integrations (databases, APIs, browsers, docs) |
## Workflow
### Phase 1: Codebase Analysis
Gather project context:
```bash
# Detect project type and tools
ls -la package.json pyproject.toml Cargo.toml go.mod pom.xml 2>/dev/null
cat package.json 2>/dev/null | head -50
# Check dependencies for MCP server recommendations
cat package.json 2>/dev/null | grep -E '"(react|vue|angular|next|express|fastapi|django|prisma|supabase|stripe)"'
# Check for existing Claude Code config
ls -la .claude/ CLAUDE.md 2>/dev/null
# Analyze project structure
ls -la src/ app/ lib/ tests/ components/ pages/ api/ 2>/dev/null
```
**Key Indicators to Capture:**
| Category | What to Look For | Informs Recommendations For |
|----------|------------------|----------------------------|
| Language/Framework | package.json, pyproject.toml, import patterns | Hooks, MCP servers |
| Frontend stack | React, Vue, Angular, Next.js | Playwright MCP, frontend skills |
| Backend stack | Express, FastAPI, Django | API documentation tools |
| Database | Prisma, Supabase, raw SQL | Database MCP servers |
| External APIs | Stripe, OpenAI, AWS SDKs | context7 MCP for docs |
| Testing | Jest, pytest, Playwright configs | Testing hooks, subagents |
| CI/CD | GitHub Actions, CircleCI | GitHub MCP server |
| Issue tracking | Linear, Jira references | Issue tracker MCP |
| Docs patterns | OpenAPI, JSDoc, docstrings | Documentation skills |
### Phase 2: Generate Recommendations
Based on analysis, generate recommendations across all categories:
#### A. MCP Server Recommendations
See [references/mcp-servers.md](references/mcp-servers.md) for detailed patterns.
| Codebase Signal | Recommended MCP Server |
|-----------------|------------------------|
| Uses popular libraries (React, Express, etc.) | **context7** - Live documentation lookup |
| Frontend with UI testing needs | **Playwright** - Browser automation/testing |
| Uses Supabase | **Supabase MCP** - Direct database operations |
| PostgreSQL/MySQL database | **Database MCP** - Query and schema tools |
| GitHub repository | **GitHub MCP** - Issues, PRs, actions |
| Uses Linear for issues | **Linear MCP** - Issue management |
| AWS infrastructure | **AWS MCP** - Cloud resource management |
| Slack workspace | **Slack MCP** - Team notifications |
| Memory/context persistence | **Memory MCP** - Cross-session memory |
| Sentry error tracking | **Sentry MCP** - Error investigation |
| Docker containers | **Docker MCP** - Container management |
#### B. Skills Recommendations
See [references/skills-reference.md](references/skills-reference.md) for patterns.
| Codebase Signal | Recommended Skill |
|-----------------|-------------------|
| Complex implementation tasks | **Plan agent** - Architecture planning |
| Large codebase | **Explore agent** - Codebase navigation |
| Creates documents | **docx skill** - Word document generation |
| Creates spreadsheets | **xlsx skill** - Excel creation |
| Creates presentations | **pptx skill** - PowerPoint generation |
| PDF workflows | **pdf skill** - PDF manipulation |
| Frontend UI work | **frontend-design** - UI component design |
| Needs custom Claude tools | **mcp-builder** - Build MCP servers |
| Wants branded output | **brand-guidelines** - Apply brand styling |
| Testing web apps | **webapp-testing** - Playwright testing |
#### C. Hooks Recommendations
See [references/hooks-patterns.md](references/hooks-patterns.md) for configurations.
| Codebase Signal | Recommended Hook |
|-----------------|------------------|
| Prettier configured | PostToolUse: auto-format on edit |
| ESLint/Ruff configured | PostToolUse: auto-lint on edit |
| TypeScript project | PostToolUse: type-check on edit |
| Tests directory exists | PostToolUse: run related tests |
| `.env` files present | PreToolUse: block `.env` edits |
| Lock files present | PreToolUse: block lock file edits |
| Security-sensitive code | PreToolUse: require confirmation |
#### D. Subagent Recommendations
See [references/subagent-templates.md](references/subagent-templates.md) for templates.
| Codebase Signal | Recommended Subagent |
|-----------------|---------------------|
| Large codebase (>500 files) | **code-reviewer** - Parallel code review |
| Auth/payments code | **security-reviewer** - Security audits |
| API project | **api-documenter** - OpenAPI generation |
| Performance critical | **performance-analyzer** - Bottleneck detection |
| Frontend heavy | **ui-reviewer** - Accessibility review |
| Needs more tests | **test-writer** - Test generation |
#### E. Slash Command 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.
| Codebase Signal | Recommended Plugin |
|-----------------|-------------------|
| General productivity | **anthropic-agent-skills** - Core skills bundle |
| Document workflows | Install docx, xlsx, pdf skills |
| Frontend development | **frontend-design** plugin |
| Building AI tools | **mcp-builder** for MCP development |
### Phase 3: Output Recommendations Report
Format recommendations clearly. **Only include 1-2 recommendations per category** - the most valuable ones for this specific codebase. Skip categories that aren't relevant.
```markdown
## Claude Code Automation Recommendations
I've analyzed your codebase and identified the top automations for each category. Here are my top 1-2 recommendations per type:
### Codebase Profile
- **Type**: [detected language/runtime]
- **Framework**: [detected framework]
- **Key Libraries**: [relevant libraries detected]
---
### 🔌 MCP Servers
#### context7
**Why**: [specific reason based on detected libraries]
**Install**: `claude mcp add context7`
---
### 🎯 Skills
#### [skill name]
**Why**: [specific reason]
**How**: [invocation method]
---
### ⚡ Hooks
#### [hook name]
**Why**: [specific reason based on detected config]
**Where**: `.claude/settings.json`
---
### 🤖 Subagents
#### [agent name]
**Why**: [specific reason based on codebase patterns]
**Where**: `.claude/agents/[name].md`
---
### 📝 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 help implementing any of these?** Just ask and I can help you set up any of the recommendations above.
```
## Decision Framework
### When to Recommend MCP Servers
- External service integration needed (databases, APIs)
- Documentation lookup for libraries/SDKs
- Browser automation or testing
- Team tool integration (GitHub, Linear, Slack)
- Cloud infrastructure management
### When to Recommend Skills
- Complex multi-step workflows
- Document generation needs
- Specialized domain knowledge needed
- Repeatable processes with templates
### When to Recommend Hooks
- Repetitive post-edit actions (formatting, linting)
- Protection rules (block sensitive file edits)
- Validation checks (tests, type checks)
### When to Recommend Subagents
- Specialized expertise needed (security, performance)
- Parallel review workflows
- Background quality checks
### When to Recommend Slash Commands
- Frequently repeated prompts
- Commands with arguments
- Quick project-specific workflows
### When to Recommend Plugins
- Need multiple related skills
- Want pre-packaged automation bundles
- Team-wide standardization
---
## Configuration Tips
### MCP Server Setup
**Team sharing**: Check `.mcp.json` into repo so entire team gets same MCP servers
**Debugging**: Use `--mcp-debug` flag to identify configuration issues
**Prerequisites to recommend:**
- GitHub CLI (`gh`) - enables native GitHub operations
- Puppeteer/Playwright CLI - for browser MCP servers
### Headless Mode (for CI/Automation)
Recommend headless Claude for automated pipelines:
```bash
# Pre-commit hook example
claude -p "fix lint errors in src/" --allowedTools Edit,Write
# CI pipeline with structured output
claude -p "<prompt>" --output-format stream-json | your_command
```
### Permissions for Hooks
Configure allowed tools in `.claude/settings.json`:
```json
{
"permissions": {
"allow": ["Edit", "Write", "Bash(npm test:*)", "Bash(git commit:*)"]
}
}
```

147
plugins/claude-code-setup/skills/claude-automation-recommender/references/hooks-patterns.md Normal file
View File

@@ -0,0 +1,147 @@
# Hooks Recommendations
Hooks automatically run commands in response to Claude's tool usage. They're ideal for enforcement and automation that should happen consistently.
## Auto-Formatting Hooks
### Prettier (JavaScript/TypeScript)
| Detection | File Exists |
|-----------|-------------|
| `.prettierrc`, `.prettierrc.json`, `prettier.config.js` | ✓ |
**Recommend**: PostToolUse hook on Edit/Write to auto-format
**Value**: Code stays formatted without thinking about it
### ESLint (JavaScript/TypeScript)
| Detection | File Exists |
|-----------|-------------|
| `.eslintrc`, `.eslintrc.json`, `eslint.config.js` | ✓ |
**Recommend**: PostToolUse hook on Edit/Write to auto-fix
**Value**: Lint errors fixed automatically
### Black/isort (Python)
| Detection | File Exists |
|-----------|-------------|
| `pyproject.toml` with black/isort, `.black`, `setup.cfg` | ✓ |
**Recommend**: PostToolUse hook to format Python files
**Value**: Consistent Python formatting
### Ruff (Python - Modern)
| Detection | File Exists |
|-----------|-------------|
| `ruff.toml`, `pyproject.toml` with `[tool.ruff]` | ✓ |
**Recommend**: PostToolUse hook for lint + format
**Value**: Fast, comprehensive Python linting
### gofmt (Go)
| Detection | File Exists |
|-----------|-------------|
| `go.mod` | ✓ |
**Recommend**: PostToolUse hook to run gofmt
**Value**: Standard Go formatting
### rustfmt (Rust)
| Detection | File Exists |
|-----------|-------------|
| `Cargo.toml` | ✓ |
**Recommend**: PostToolUse hook to run rustfmt
**Value**: Standard Rust formatting
---
## Type Checking Hooks
### TypeScript
| Detection | File Exists |
|-----------|-------------|
| `tsconfig.json` | ✓ |
**Recommend**: PostToolUse hook to run tsc --noEmit
**Value**: Catch type errors immediately
### mypy/pyright (Python)
| Detection | File Exists |
|-----------|-------------|
| `mypy.ini`, `pyrightconfig.json`, pyproject.toml with mypy | ✓ |
**Recommend**: PostToolUse hook for type checking
**Value**: Catch type errors in Python
---
## Protection Hooks
### Block Sensitive File Edits
| Detection | Presence Of |
|-----------|-------------|
| `.env`, `.env.local`, `.env.production` | Environment files |
| `credentials.json`, `secrets.yaml` | Secret files |
| `.git/` directory | Git internals |
**Recommend**: PreToolUse hook that blocks Edit/Write to these paths
**Value**: Prevent accidental secret exposure or git corruption
### Block Lock File Edits
| Detection | Presence Of |
|-----------|-------------|
| `package-lock.json`, `yarn.lock`, `pnpm-lock.yaml` | JS lock files |
| `Cargo.lock`, `poetry.lock`, `Pipfile.lock` | Other lock files |
**Recommend**: PreToolUse hook that blocks direct edits
**Value**: Lock files should only change via package manager
---
## Test Runner Hooks
### Jest (JavaScript/TypeScript)
| Detection | Presence Of |
|-----------|-------------|
| `jest.config.js`, `jest` in package.json | Jest configured |
| `__tests__/`, `*.test.ts`, `*.spec.ts` | Test files exist |
**Recommend**: PostToolUse hook to run related tests after edit
**Value**: Immediate test feedback on changes
### pytest (Python)
| Detection | Presence Of |
|-----------|-------------|
| `pytest.ini`, `pyproject.toml` with pytest | pytest configured |
| `tests/`, `test_*.py` | Test files exist |
**Recommend**: PostToolUse hook to run pytest on changed files
**Value**: Immediate test feedback
---
## 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 |
---
## Hook Placement
Hooks go in `.claude/settings.json`:
```
.claude/
└── settings.json ← Hook configurations here
```
Recommend creating the `.claude/` directory if it doesn't exist.

261
plugins/claude-code-setup/skills/claude-automation-recommender/references/mcp-servers.md Normal file
View File

@@ -0,0 +1,261 @@
# MCP Server Recommendations
MCP (Model Context Protocol) servers extend Claude's capabilities by connecting to external tools and services.
## Setup & Team Sharing
**Connection methods:**
1. **Project config** (`.mcp.json`) - Available only in that directory
2. **Global config** (`~/.claude.json`) - Available across all projects
3. **Checked-in `.mcp.json`** - Available to entire team (recommended!)
**Tip**: Check `.mcp.json` into git so your whole team gets the same MCP servers.
**Debugging**: Use `claude --mcp-debug` to identify configuration issues.
## Documentation & Knowledge
### context7
**Best for**: Projects using popular libraries/SDKs where you want Claude to code with up-to-date documentation
| Recommend When | Examples |
|----------------|----------|
| Using React, Vue, Angular | Frontend frameworks |
| Using Express, FastAPI, Django | Backend frameworks |
| Using Prisma, Drizzle | ORMs |
| Using Stripe, Twilio, SendGrid | Third-party APIs |
| Using AWS SDK, Google Cloud | Cloud SDKs |
| Using LangChain, OpenAI SDK | AI/ML libraries |
**Value**: Claude fetches live documentation instead of relying on training data, reducing hallucinated APIs and outdated patterns.
---
## Browser & Frontend
### Playwright MCP
**Best for**: Frontend projects needing browser automation, testing, or screenshots
| Recommend When | Examples |
|----------------|----------|
| React/Vue/Angular app | UI component testing |
| E2E tests needed | User flow validation |
| Visual regression testing | Screenshot comparisons |
| Debugging UI issues | See what user sees |
| Form testing | Multi-step workflows |
**Value**: Claude can interact with your running app, take screenshots, fill forms, and verify UI behavior.
### Puppeteer MCP
**Best for**: Headless browser automation, web scraping
| Recommend When | Examples |
|----------------|----------|
| PDF generation from HTML | Report generation |
| Web scraping tasks | Data extraction |
| Headless testing | CI environments |
---
## Databases
### Supabase MCP
**Best for**: Projects using Supabase for backend/database
| Recommend When | Examples |
|----------------|----------|
| Supabase project detected | `@supabase/supabase-js` in deps |
| Auth + database needs | User management apps |
| Real-time features | Live data sync |
**Value**: Claude can query tables, manage auth, and interact with Supabase storage directly.
### PostgreSQL MCP
**Best for**: Direct PostgreSQL database access
| Recommend When | Examples |
|----------------|----------|
| Raw PostgreSQL usage | No ORM layer |
| Database migrations | Schema management |
| Data analysis tasks | Complex queries |
| Debugging data issues | Inspect actual data |
### Neon MCP
**Best for**: Neon serverless Postgres users
### Turso MCP
**Best for**: Turso/libSQL edge database users
---
## Version Control & DevOps
### GitHub MCP
**Best for**: GitHub-hosted repositories needing issue/PR integration
| Recommend When | Examples |
|----------------|----------|
| GitHub repository | `.git` with GitHub remote |
| Issue-driven development | Reference issues in commits |
| PR workflows | Review, merge operations |
| GitHub Actions | CI/CD pipeline access |
| Release management | Tag and release automation |
**Value**: Claude can create issues, review PRs, check workflow runs, and manage releases.
### GitLab MCP
**Best for**: GitLab-hosted repositories
### Linear MCP
**Best for**: Teams using Linear for issue tracking
| Recommend When | Examples |
|----------------|----------|
| Linear workspace | Issue references like `ABC-123` |
| Sprint planning | Backlog management |
| Issue creation from code | Auto-create issues for TODOs |
---
## Cloud Infrastructure
### AWS MCP
**Best for**: AWS infrastructure management
| Recommend When | Examples |
|----------------|----------|
| AWS SDK in dependencies | `@aws-sdk/*` packages |
| Infrastructure as code | Terraform, CDK, SAM |
| Lambda development | Serverless functions |
| S3, DynamoDB usage | Cloud data services |
### Cloudflare MCP
**Best for**: Cloudflare Workers, Pages, R2, D1
| Recommend When | Examples |
|----------------|----------|
| Cloudflare Workers | Edge functions |
| Pages deployment | Static site hosting |
| R2 storage | Object storage |
| D1 database | Edge SQL database |
### Vercel MCP
**Best for**: Vercel deployment and configuration
---
## Monitoring & Observtic
### Sentry MCP
**Best for**: Error tracking and debugging
| Recommend When | Examples |
|----------------|----------|
| Sentry configured | `@sentry/*` in deps |
| Production debugging | Investigate errors |
| Error patterns | Group similar issues |
| Release tracking | Correlate deploys with errors |
**Value**: Claude can investigate Sentry issues, find root causes, and suggest fixes.
### Datadog MCP
**Best for**: APM, logs, and metrics
---
## Communication
### Slack MCP
**Best for**: Slack workspace integration
| Recommend When | Examples |
|----------------|----------|
| Team uses Slack | Send notifications |
| Deployment notifications | Alert channels |
| Incident response | Post updates |
### Notion MCP
**Best for**: Notion workspace for documentation
| Recommend When | Examples |
|----------------|----------|
| Notion for docs | Read/update pages |
| Knowledge base | Search documentation |
| Meeting notes | Create summaries |
---
## File & Data
### Filesystem MCP
**Best for**: Enhanced file operations beyond built-in tools
| Recommend When | Examples |
|----------------|----------|
| Complex file operations | Batch processing |
| File watching | Monitor changes |
| Advanced search | Custom patterns |
### Memory MCP
**Best for**: Persistent memory across sessions
| Recommend When | Examples |
|----------------|----------|
| Long-running projects | Remember context |
| User preferences | Store settings |
| Learning patterns | Build knowledge |
**Value**: Claude remembers project context, decisions, and patterns across conversations.
---
## Containers & DevOps
### Docker MCP
**Best for**: Container management
| Recommend When | Examples |
|----------------|----------|
| Docker Compose file | Container orchestration |
| Dockerfile present | Build images |
| Container debugging | Inspect logs, exec |
### Kubernetes MCP
**Best for**: Kubernetes cluster management
| Recommend When | Examples |
|----------------|----------|
| K8s manifests | Deploy, scale pods |
| Helm charts | Package management |
| Cluster debugging | Pod logs, status |
---
## AI & ML
### Exa MCP
**Best for**: Web search and research
| Recommend When | Examples |
|----------------|----------|
| Research tasks | Find current info |
| Competitive analysis | Market research |
| Documentation gaps | Find examples |
---
## Quick Reference: Detection Patterns
| Look For | Suggests MCP Server |
|----------|-------------------|
| Popular npm packages | context7 |
| React/Vue/Next.js | Playwright MCP |
| `@supabase/supabase-js` | Supabase MCP |
| `pg` or `postgres` | PostgreSQL MCP |
| GitHub remote | GitHub MCP |
| `.linear` or Linear refs | Linear MCP |
| `@aws-sdk/*` | AWS MCP |
| `@sentry/*` | Sentry MCP |
| `docker-compose.yml` | Docker MCP |
| Slack webhook URLs | Slack MCP |
| `@anthropic-ai/sdk` | context7 for Anthropic docs |

89
plugins/claude-code-setup/skills/claude-automation-recommender/references/plugins-reference.md Normal file
View File

@@ -0,0 +1,89 @@
# Plugin Recommendations
Plugins are installable collections of skills that extend Claude's capabilities. They bundle related skills, reference materials, and workflows together.
## Available 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
**Specialized frontend UI development**
| Recommend When | Examples |
|----------------|----------|
| 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 vs Individual Skills
### When to Recommend Plugin Installation
- User needs multiple related skills
- Team standardization desired
- First-time Claude Code setup
- Comprehensive capability needed
### When to Recommend Individual Skill Usage
- Specific one-time task
- Already have plugin installed
- Just need one capability
---
## Checking Installed Plugins
```bash
# List installed plugins
claude plugins list
# Check available skills
claude skills list
```
---
## Custom Plugin Development
For teams wanting to bundle their own skills:
| Recommend When | Examples |
|----------------|----------|
| Company-specific workflows | Internal processes |
| 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 |

216
plugins/claude-code-setup/skills/claude-automation-recommender/references/skills-reference.md Normal file
View File

@@ -0,0 +1,216 @@
# Skills Recommendations
Skills are packaged expertise with workflows, reference materials, and best practices that Claude can invoke for specialized tasks.
## Built-in Agents
### Plan Agent
**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
### docx (Word Documents)
**Best for**: Creating and editing Word documents
| Recommend When | Examples |
|----------------|----------|
| Report generation | Technical reports |
| Contract templates | Legal documents |
| Documentation export | Share with non-developers |
| Tracked changes | Review workflows |
### xlsx (Spreadsheets)
**Best for**: Creating and analyzing Excel files
| Recommend When | Examples |
|----------------|----------|
| Data analysis | Process CSV/Excel data |
| Report generation | Formatted tables |
| Financial models | Formulas and calculations |
| Data transformation | Clean and reshape data |
### pptx (Presentations)
**Best for**: Creating PowerPoint presentations
| Recommend When | Examples |
|----------------|----------|
| Technical presentations | Architecture diagrams |
| 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.
### canvas-design
**Best for**: Creating visual art and static designs
| Recommend When | Examples |
|----------------|----------|
| Poster creation | Marketing materials |
| Visual diagrams | Architecture visuals |
| Infographics | Data visualization |
### algorithmic-art
**Best for**: Generative art with p5.js
| Recommend When | Examples |
|----------------|----------|
| Interactive visuals | Creative coding |
| 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
### mcp-builder
**Best for**: Creating MCP servers to extend Claude
| Recommend When | Examples |
|----------------|----------|
| Custom tool needs | Internal APIs |
| API integrations | Third-party services |
| 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
### doc-coauthoring
**Best for**: Co-authoring documentation with users
| Recommend When | Examples |
|----------------|----------|
| Technical specs | RFC documents |
| Decision docs | ADRs |
| Proposals | Feature proposals |
| Documentation | User guides |
**Value**: Structured workflow for iterative document refinement.
### internal-comms
**Best for**: Writing internal communications
| Recommend When | Examples |
|----------------|----------|
| Status reports | Project updates |
| Announcements | Team comms |
| Incident reports | Post-mortems |
| FAQs | Knowledge sharing |
---
## Multimedia Skills
### slack-gif-creator
**Best for**: Creating animated GIFs for Slack
| Recommend When | Examples |
|----------------|----------|
| Team celebrations | Achievements |
| Demo animations | Feature previews |
| Fun reactions | Custom emoji-style GIFs |
---
## Quick Reference: Detection Patterns
| Look For | Suggests Skill |
|----------|---------------|
| Complex task, multiple files | Plan agent |
| "How does X work?" | Explore agent |
| `.docx` files or doc requests | docx skill |
| `.xlsx` files or spreadsheet work | xlsx skill |
| Presentation needs | pptx skill |
| PDF files to process | pdf skill |
| React/Vue/Angular components | frontend-design |
| UI design requests | canvas-design |
| Testing local web app | webapp-testing |
| "Build an MCP server" | mcp-builder |
| Documentation writing | doc-coauthoring |
| Internal announcement | internal-comms |

251
plugins/claude-code-setup/skills/claude-automation-recommender/references/slash-command-examples.md Normal file
View File

@@ -0,0 +1,251 @@
# 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 |

179
plugins/claude-code-setup/skills/claude-automation-recommender/references/subagent-templates.md Normal file
View File

@@ -0,0 +1,179 @@
# Subagent Recommendations
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.
## Code Review Agents
### code-reviewer
**Best for**: Automated code quality checks on large codebases
| Recommend When | Detection |
|----------------|-----------|
| Large codebase (>500 files) | File count |
| Frequent code changes | Active development |
| Team wants consistent review | Quality focus |
**Value**: Runs code review in parallel while you continue working
**Model**: sonnet (balanced quality/speed)
**Tools**: Read, Grep, Glob, Bash
---
### security-reviewer
**Best for**: Security-focused code review
| Recommend When | Detection |
|----------------|-----------|
| Auth code present | `auth/`, `login`, `session` patterns |
| Payment processing | `stripe`, `payment`, `billing` patterns |
| User data handling | `user`, `profile`, `pii` patterns |
| API keys in code | Environment variable patterns |
**Value**: Catches OWASP vulnerabilities, auth issues, data exposure
**Model**: sonnet
**Tools**: Read, Grep, Glob (read-only for safety)
---
### test-writer
**Best for**: Generating comprehensive test coverage
| Recommend When | Detection |
|----------------|-----------|
| Low test coverage | Few test files vs source files |
| Test suite exists | `tests/`, `__tests__/` present |
| Testing framework configured | jest, pytest, vitest in deps |
**Value**: Generates tests matching project conventions
**Model**: sonnet
**Tools**: Read, Write, Grep, Glob
---
## Specialized Agents
### api-documenter
**Best for**: API documentation generation
| Recommend When | Detection |
|----------------|-----------|
| REST endpoints | Express routes, FastAPI paths |
| GraphQL schema | `.graphql` files |
| OpenAPI exists | `openapi.yaml`, `swagger.json` |
| Undocumented APIs | Routes without docs |
**Value**: Generates OpenAPI specs, endpoint documentation
**Model**: sonnet
**Tools**: Read, Write, Grep, Glob
---
### performance-analyzer
**Best for**: Finding performance bottlenecks
| Recommend When | Detection |
|----------------|-----------|
| Database queries | ORM usage, raw SQL |
| High-traffic code | API endpoints, hot paths |
| Performance complaints | User reports slowness |
| Complex algorithms | Nested loops, recursion |
**Value**: Finds N+1 queries, O(n²) algorithms, memory leaks
**Model**: sonnet
**Tools**: Read, Grep, Glob, Bash
---
### ui-reviewer
**Best for**: Frontend accessibility and UX review
| Recommend When | Detection |
|----------------|-----------|
| React/Vue/Angular | Frontend framework detected |
| Component library | `components/` directory |
| User-facing UI | Not just API project |
**Value**: Catches accessibility issues, UX problems, responsive design gaps
**Model**: sonnet
**Tools**: Read, Grep, Glob
---
## Utility Agents
### dependency-updater
**Best for**: Safe dependency updates
| Recommend When | Detection |
|----------------|-----------|
| Outdated deps | `npm outdated` has results |
| Security advisories | `npm audit` warnings |
| Major version behind | Significant version gaps |
**Value**: Updates dependencies incrementally with testing
**Model**: sonnet
**Tools**: Read, Write, Bash, Grep
---
### migration-helper
**Best for**: Framework/version migrations
| Recommend When | Detection |
|----------------|-----------|
| Major upgrade needed | Framework version very old |
| Breaking changes coming | Deprecation warnings |
| Refactoring planned | Architectural changes |
**Value**: Plans and executes migrations incrementally
**Model**: opus (complex reasoning needed)
**Tools**: Read, Write, Grep, Glob, Bash
---
## Quick Reference: Detection → Recommendation
| If You See | Recommend Subagent |
|------------|-------------------|
| Large codebase | code-reviewer |
| Auth/payment code | security-reviewer |
| Few tests | test-writer |
| API routes | api-documenter |
| Database heavy | performance-analyzer |
| Frontend components | ui-reviewer |
| Outdated packages | dependency-updater |
| Old framework version | migration-helper |
---
## Subagent Placement
Subagents go in `.claude/agents/`:
```
.claude/
└── agents/
├── code-reviewer.md
├── security-reviewer.md
└── test-writer.md
```
---
## Model Selection Guide
| Model | Best For | Trade-off |
|-------|----------|-----------|
| **haiku** | Simple, repetitive checks | Fast, cheap, less thorough |
| **sonnet** | Most review/analysis tasks | Balanced (recommended default) |
| **opus** | Complex migrations, architecture | Thorough, slower, more expensive |
---
## Tool Access Guide
| Access Level | Tools | Use Case |
|--------------|-------|----------|
| Read-only | Read, Grep, Glob | Reviews, analysis |
| Writing | + Write | Code generation, docs |
| Full | + Bash | Migrations, testing |

9
plugins/claude-md-management/.claude-plugin/plugin.json Normal file
View File

@@ -0,0 +1,9 @@
{
"name": "claude-md-management",
"description": "Tools to maintain and improve CLAUDE.md files",
"version": "1.0.0",
"author": {
"name": "Isabella He",
"email": "isabella@anthropic.com"
}
}

40
plugins/claude-md-management/README.md Normal file
View File

@@ -0,0 +1,40 @@
# CLAUDE.md Management Plugin
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
## What It Does
Two complementary tools for different purposes:
| | claude-md-improver (skill) | /revise-claude-md (command) |
|---|---|---|
| **Purpose** | Keep CLAUDE.md aligned with codebase | Capture session learnings |
| **Triggered by** | Codebase changes | End of session |
| **Use when** | Periodic maintenance | Session revealed missing context |
## Usage
### Skill: claude-md-improver
Audits CLAUDE.md files against current codebase state:
```
"audit my CLAUDE.md files"
"check if my CLAUDE.md is up to date"
```
<img src="claude-md-improver-example.png" alt="CLAUDE.md improver showing quality scores and recommended updates" width="600">
### Command: /revise-claude-md
Captures learnings from the current session:
```
/revise-claude-md
```
<img src="revise-claude-md-example.png" alt="Revise command capturing session learnings into CLAUDE.md" width="600">
## Author
Isabella He (isabella@anthropic.com)

BIN
plugins/claude-md-management/claude-md-improver-example.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 507 KiB

54
plugins/claude-md-management/commands/revise-claude-md.md Normal file
View File

@@ -0,0 +1,54 @@
---
description: Update CLAUDE.md with learnings from this session
allowed-tools: Read, Edit, Glob
---
Review this session for learnings about working with Claude Code in this codebase. Update CLAUDE.md with context that would help future Claude sessions be more effective.
## Step 1: Reflect
What context was missing that would have helped Claude work more effectively?
- Bash commands that were used or discovered
- Code style patterns followed
- Testing approaches that worked
- Environment/configuration quirks
- Warnings or gotchas encountered
## Step 2: Find CLAUDE.md Files
```bash
find . -name "CLAUDE.md" -o -name ".claude.local.md" 2>/dev/null | head -20
```
Decide where each addition belongs:
- `CLAUDE.md` - Team-shared (checked into git)
- `.claude.local.md` - Personal/local only (gitignored)
## Step 3: Draft Additions
**Keep it concise** - one line per concept. CLAUDE.md is part of the prompt, so brevity matters.
Format: `<command or pattern>` - `<brief description>`
Avoid:
- Verbose explanations
- Obvious information
- One-off fixes unlikely to recur
## Step 4: Show Proposed Changes
For each addition:
```
### Update: ./CLAUDE.md
**Why:** [one-line reason]
\`\`\`diff
+ [the addition - keep it brief]
\`\`\`
```
## Step 5: Apply with Approval
Ask if the user wants to apply the changes. Only edit files they approve.

BIN
plugins/claude-md-management/revise-claude-md-example.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 542 KiB

179
plugins/claude-md-management/skills/claude-md-improver/SKILL.md Normal file
View File

@@ -0,0 +1,179 @@
---
name: claude-md-improver
description: Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project memory optimization".
tools: Read, Glob, Grep, Bash, Edit
---
# CLAUDE.md Improver
Audit, evaluate, and improve CLAUDE.md files across a codebase to ensure Claude Code has optimal project context.
**This skill can write to CLAUDE.md files.** After presenting a quality report and getting user approval, it updates CLAUDE.md files with targeted improvements.
## Workflow
### Phase 1: Discovery
Find all CLAUDE.md files in the repository:
```bash
find . -name "CLAUDE.md" -o -name ".claude.md" -o -name ".claude.local.md" 2>/dev/null | head -50
```
**File Types & Locations:**
| Type | Location | Purpose |
|------|----------|---------|
| Project root | `./CLAUDE.md` | Primary project context (checked into git, shared with team) |
| Local overrides | `./.claude.local.md` | Personal/local settings (gitignored, not shared) |
| Global defaults | `~/.claude/CLAUDE.md` | User-wide defaults across all projects |
| Package-specific | `./packages/*/CLAUDE.md` | Module-level context in monorepos |
| Subdirectory | Any nested location | Feature/domain-specific context |
**Note:** Claude auto-discovers CLAUDE.md files in parent directories, making monorepo setups work automatically.
### Phase 2: Quality Assessment
For each CLAUDE.md file, evaluate against quality criteria. See [references/quality-criteria.md](references/quality-criteria.md) for detailed rubrics.
**Quick Assessment Checklist:**
| Criterion | Weight | Check |
|-----------|--------|-------|
| Commands/workflows documented | High | Are build/test/deploy commands present? |
| Architecture clarity | High | Can Claude understand the codebase structure? |
| Non-obvious patterns | Medium | Are gotchas and quirks documented? |
| Conciseness | Medium | No verbose explanations or obvious info? |
| Currency | High | Does it reflect current codebase state? |
| Actionability | High | Are instructions executable, not vague? |
**Quality Scores:**
- **A (90-100)**: Comprehensive, current, actionable
- **B (70-89)**: Good coverage, minor gaps
- **C (50-69)**: Basic info, missing key sections
- **D (30-49)**: Sparse or outdated
- **F (0-29)**: Missing or severely outdated
### Phase 3: Quality Report Output
**ALWAYS output the quality report BEFORE making any updates.**
Format:
```
## CLAUDE.md Quality Report
### Summary
- Files found: X
- Average score: X/100
- Files needing update: X
### File-by-File Assessment
#### 1. ./CLAUDE.md (Project Root)
**Score: XX/100 (Grade: X)**
| Criterion | Score | Notes |
|-----------|-------|-------|
| Commands/workflows | X/20 | ... |
| Architecture clarity | X/20 | ... |
| Non-obvious patterns | X/15 | ... |
| Conciseness | X/15 | ... |
| Currency | X/15 | ... |
| Actionability | X/15 | ... |
**Issues:**
- [List specific problems]
**Recommended additions:**
- [List what should be added]
#### 2. ./packages/api/CLAUDE.md (Package-specific)
...
```
### Phase 4: Targeted Updates
After outputting the quality report, ask user for confirmation before updating.
**Update Guidelines (Critical):**
1. **Propose targeted additions only** - Focus on genuinely useful info:
- Commands or workflows discovered during analysis
- Gotchas or non-obvious patterns found in code
- Package relationships that weren't clear
- Testing approaches that work
- Configuration quirks
2. **Keep it minimal** - Avoid:
- Restating what's obvious from the code
- Generic best practices already covered
- One-off fixes unlikely to recur
- Verbose explanations when a one-liner suffices
3. **Show diffs** - For each change, show:
- Which CLAUDE.md file to update
- The specific addition (as a diff or quoted block)
- Brief explanation of why this helps future sessions
**Diff Format:**
```markdown
### Update: ./CLAUDE.md
**Why:** Build command was missing, causing confusion about how to run the project.
```diff
+ ## Quick Start
+
+ ```bash
+ npm install
+ npm run dev # Start development server on port 3000
+ ```
```
```
### Phase 5: Apply Updates
After user approval, apply changes using the Edit tool. Preserve existing content structure.
## Templates
See [references/templates.md](references/templates.md) for CLAUDE.md templates by project type.
## Common Issues to Flag
1. **Stale commands**: Build commands that no longer work
2. **Missing dependencies**: Required tools not mentioned
3. **Outdated architecture**: File structure that's changed
4. **Missing environment setup**: Required env vars or config
5. **Broken test commands**: Test scripts that have changed
6. **Undocumented gotchas**: Non-obvious patterns not captured
## User Tips to Share
When presenting recommendations, remind users:
- **`#` key shortcut**: During a Claude session, press `#` to have Claude auto-incorporate learnings into CLAUDE.md
- **Keep it concise**: CLAUDE.md should be human-readable; dense is better than verbose
- **Actionable commands**: All documented commands should be copy-paste ready
- **Use `.claude.local.md`**: For personal preferences not shared with team (add to `.gitignore`)
- **Global defaults**: Put user-wide preferences in `~/.claude/CLAUDE.md`
## What Makes a Great CLAUDE.md
**Key principles:**
- Concise and human-readable
- Actionable commands that can be copy-pasted
- Project-specific patterns, not generic advice
- Non-obvious gotchas and warnings
**Recommended sections** (use only what's relevant):
- Commands (build, test, dev, lint)
- Architecture (directory structure)
- Key Files (entry points, config)
- Code Style (project conventions)
- Environment (required vars, setup)
- Testing (commands, patterns)
- Gotchas (quirks, common mistakes)
- Workflow (when to do what)

109
plugins/claude-md-management/skills/claude-md-improver/references/quality-criteria.md Normal file
View File

@@ -0,0 +1,109 @@
# CLAUDE.md Quality Criteria
## Scoring Rubric
### 1. Commands/Workflows (20 points)
**20 points**: All essential commands documented with context
- Build, test, lint, deploy commands present
- Development workflow clear
- Common operations documented
**15 points**: Most commands present, some missing context
**10 points**: Basic commands only, no workflow
**5 points**: Few commands, many missing
**0 points**: No commands documented
### 2. Architecture Clarity (20 points)
**20 points**: Clear codebase map
- Key directories explained
- Module relationships documented
- Entry points identified
- Data flow described where relevant
**15 points**: Good structure overview, minor gaps
**10 points**: Basic directory listing only
**5 points**: Vague or incomplete
**0 points**: No architecture info
### 3. Non-Obvious Patterns (15 points)
**15 points**: Gotchas and quirks captured
- Known issues documented
- Workarounds explained
- Edge cases noted
- "Why we do it this way" for unusual patterns
**10 points**: Some patterns documented
**5 points**: Minimal pattern documentation
**0 points**: No patterns or gotchas
### 4. Conciseness (15 points)
**15 points**: Dense, valuable content
- No filler or obvious info
- Each line adds value
- No redundancy with code comments
**10 points**: Mostly concise, some padding
**5 points**: Verbose in places
**0 points**: Mostly filler or restates obvious code
### 5. Currency (15 points)
**15 points**: Reflects current codebase
- Commands work as documented
- File references accurate
- Tech stack current
**10 points**: Mostly current, minor staleness
**5 points**: Several outdated references
**0 points**: Severely outdated
### 6. Actionability (15 points)
**15 points**: Instructions are executable
- Commands can be copy-pasted
- Steps are concrete
- Paths are real
**10 points**: Mostly actionable
**5 points**: Some vague instructions
**0 points**: Vague or theoretical
## Assessment Process
1. Read the CLAUDE.md file completely
2. Cross-reference with actual codebase:
- Run documented commands (mentally or actually)
- Check if referenced files exist
- Verify architecture descriptions
3. Score each criterion
4. Calculate total and assign grade
5. List specific issues found
6. Propose concrete improvements
## Red Flags
- Commands that would fail (wrong paths, missing deps)
- References to deleted files/folders
- Outdated tech versions
- Copy-paste from templates without customization
- Generic advice not specific to the project
- "TODO" items never completed
- Duplicate info across multiple CLAUDE.md files

253
plugins/claude-md-management/skills/claude-md-improver/references/templates.md Normal file
View File

@@ -0,0 +1,253 @@
# CLAUDE.md Templates
## Key Principles
- **Concise**: Dense, human-readable content; one line per concept when possible
- **Actionable**: Commands should be copy-paste ready
- **Project-specific**: Document patterns unique to this project, not generic advice
- **Current**: All info should reflect actual codebase state
---
## Recommended Sections
Use only the sections relevant to the project. Not all sections are needed.
### Commands
Document the essential commands for working with the project.
```markdown
## Commands
| Command | Description |
|---------|-------------|
| `<install command>` | Install dependencies |
| `<dev command>` | Start development server |
| `<build command>` | Production build |
| `<test command>` | Run tests |
| `<lint command>` | Lint/format code |
```
### Architecture
Describe the project structure so Claude understands where things live.
```markdown
## Architecture
```
<root>/
<dir>/ # <purpose>
<dir>/ # <purpose>
<dir>/ # <purpose>
```
```
### Key Files
List important files that Claude should know about.
```markdown
## Key Files
- `<path>` - <purpose>
- `<path>` - <purpose>
```
### Code Style
Document project-specific coding conventions.
```markdown
## Code Style
- <convention>
- <convention>
- <preference over alternative>
```
### Environment
Document required environment variables and setup.
```markdown
## Environment
Required:
- `<VAR_NAME>` - <purpose>
- `<VAR_NAME>` - <purpose>
Setup:
- <setup step>
```
### Testing
Document testing approach and commands.
```markdown
## Testing
- `<test command>` - <what it tests>
- <testing convention or pattern>
```
### Gotchas
Document non-obvious patterns, quirks, and warnings.
```markdown
## Gotchas
- <non-obvious thing that causes issues>
- <ordering dependency or prerequisite>
- <common mistake to avoid>
```
### Workflow
Document development workflow patterns.
```markdown
## Workflow
- <when to do X>
- <preferred approach for Y>
```
---
## Template: Project Root (Minimal)
```markdown
# <Project Name>
<One-line description>
## Commands
| Command | Description |
|---------|-------------|
| `<command>` | <description> |
## Architecture
```
<structure>
```
## Gotchas
- <gotcha>
```
---
## Template: Project Root (Comprehensive)
```markdown
# <Project Name>
<One-line description>
## Commands
| Command | Description |
|---------|-------------|
| `<command>` | <description> |
## Architecture
```
<structure with descriptions>
```
## Key Files
- `<path>` - <purpose>
## Code Style
- <convention>
## Environment
- `<VAR>` - <purpose>
## Testing
- `<command>` - <scope>
## Gotchas
- <gotcha>
```
---
## Template: Package/Module
For packages within a monorepo or distinct modules.
```markdown
# <Package Name>
<Purpose of this package>
## Usage
```
<import/usage example>
```
## Key Exports
- `<export>` - <purpose>
## Dependencies
- `<dependency>` - <why needed>
## Notes
- <important note>
```
---
## Template: Monorepo Root
```markdown
# <Monorepo Name>
<Description>
## Packages
| Package | Description | Path |
|---------|-------------|------|
| `<name>` | <purpose> | `<path>` |
## Commands
| Command | Description |
|---------|-------------|
| `<command>` | <description> |
## Cross-Package Patterns
- <shared pattern>
- <generation/sync pattern>
```
---
## Update Principles
When updating any CLAUDE.md:
1. **Be specific**: Use actual file paths, real commands from this project
2. **Be current**: Verify info against the actual codebase
3. **Be brief**: One line per concept when possible
4. **Be useful**: Would this help a new Claude session understand the project?

150
plugins/claude-md-management/skills/claude-md-improver/references/update-guidelines.md Normal file
View File

@@ -0,0 +1,150 @@
# CLAUDE.md Update Guidelines
## Core Principle
Only add information that will genuinely help future Claude sessions. The context window is precious - every line must earn its place.
## What TO Add
### 1. Commands/Workflows Discovered
```markdown
## Build
`npm run build:prod` - Full production build with optimization
`npm run build:dev` - Fast dev build (no minification)
```
Why: Saves future sessions from discovering these again.
### 2. Gotchas and Non-Obvious Patterns
```markdown
## Gotchas
- Tests must run sequentially (`--runInBand`) due to shared DB state
- `yarn.lock` is authoritative; delete `node_modules` if deps mismatch
```
Why: Prevents repeating debugging sessions.
### 3. Package Relationships
```markdown
## Dependencies
The `auth` module depends on `crypto` being initialized first.
Import order matters in `src/bootstrap.ts`.
```
Why: Architecture knowledge that isn't obvious from code.
### 4. Testing Approaches That Worked
```markdown
## Testing
For API endpoints: Use `supertest` with the test helper in `tests/setup.ts`
Mocking: Factory functions in `tests/factories/` (not inline mocks)
```
Why: Establishes patterns that work.
### 5. Configuration Quirks
```markdown
## Config
- `NEXT_PUBLIC_*` vars must be set at build time, not runtime
- Redis connection requires `?family=0` suffix for IPv6
```
Why: Environment-specific knowledge.
## What NOT to Add
### 1. Obvious Code Info
Bad:
```markdown
The `UserService` class handles user operations.
```
The class name already tells us this.
### 2. Generic Best Practices
Bad:
```markdown
Always write tests for new features.
Use meaningful variable names.
```
This is universal advice, not project-specific.
### 3. One-Off Fixes
Bad:
```markdown
We fixed a bug in commit abc123 where the login button didn't work.
```
Won't recur; clutters the file.
### 4. Verbose Explanations
Bad:
```markdown
The authentication system uses JWT tokens. JWT (JSON Web Tokens) are
an open standard (RFC 7519) that defines a compact and self-contained
way for securely transmitting information between parties as a JSON
object. In our implementation, we use the HS256 algorithm which...
```
Good:
```markdown
Auth: JWT with HS256, tokens in `Authorization: Bearer <token>` header.
```
## Diff Format for Updates
For each suggested change:
### 1. Identify the File
```
File: ./CLAUDE.md
Section: Commands (new section after ## Architecture)
```
### 2. Show the Change
```diff
## Architecture
...
+## Commands
+
+| Command | Purpose |
+|---------|---------|
+| `npm run dev` | Dev server with HMR |
+| `npm run build` | Production build |
+| `npm test` | Run test suite |
```
### 3. Explain Why
> **Why this helps:** The build commands weren't documented, causing
> confusion about how to run the project. This saves future sessions
> from needing to inspect `package.json`.
## Validation Checklist
Before finalizing an update, verify:
- [ ] Each addition is project-specific
- [ ] No generic advice or obvious info
- [ ] Commands are tested and work
- [ ] File paths are accurate
- [ ] Would a new Claude session find this helpful?
- [ ] Is this the most concise way to express the info?