Skip to content

/document-feature

Create comprehensive documentation for features, maintaining living documentation that evolves with your code.

Overview

  • Purpose: Intelligent feature documentation
  • Category: Core Orchestration
  • Type: Dynamic prompt
  • MCP Tools: None (documentation generation)

Syntax

bash
/document-feature [feature-name]

Usage Examples

bash
# Document specific feature
/document-feature "authentication system"

# Document recent implementation
/document-feature "shopping cart"

# Document API endpoints
/document-feature "user management API"

# Document integration
/document-feature "Stripe payment integration"

Documentation Created

Feature Documentation

Creates CLAUDE.md in feature directory:

markdown
# Authentication System

## Overview
JWT-based authentication with refresh tokens

## Architecture
- Token generation in /lib/auth/tokens.ts
- Middleware in /middleware/auth.ts
- User model in /models/User.ts

## Implementation Details
- Access tokens: 15 minutes
- Refresh tokens: 7 days
- Secure httpOnly cookies
- Role-based permissions

## API Endpoints
- POST /auth/login
- POST /auth/register
- POST /auth/refresh
- POST /auth/logout

## Security Measures
- Password hashing with bcrypt
- Rate limiting on auth endpoints
- CSRF protection
- Session invalidation

## Usage Examples
```typescript
// Login example
const { token } = await auth.login(email, password);

Testing

  • Unit tests: /tests/auth/unit
  • Integration: /tests/auth/integration
  • Coverage: 95%

Future Improvements

  • Add OAuth providers
  • Implement 2FA
  • Add device management

### API Documentation
Generates OpenAPI/Swagger specs when applicable

### User Documentation
Creates user-facing guides in `/docs`

## Best Practices

## Prompt Adaptation

This prompt dynamically adapts based on:

### Context Discovery
- Analyzes current project state and structure
- Discovers existing patterns and conventions
- Understands team workflows and preferences
- Adapts to technology stack and architecture

### Intelligence Patterns
- Learns from previous executions in the project
- Adapts complexity based on team expertise
- Prioritizes based on project phase
- Suggests optimizations from accumulated knowledge

## Memory Integration

This prompt actively uses and updates distributed memory:

### Reads From
- `CLAUDE.md` - Project context and conventions
- `.orchestre/` - Orchestration state and patterns
- Feature-specific CLAUDE.md files
- Previous execution results

### Updates
- Relevant CLAUDE.md files with new insights
- `.orchestre/` with execution patterns
- Documentation as part of the workflow
- Pattern library with successful approaches


### 1. Document While Fresh
```bash
/execute-task "Implement feature"
/document-feature "feature"  # Document immediately

2. Include Examples

Documentation includes:

  • Code examples
  • API calls
  • Common use cases
  • Error scenarios

3. Living Documentation

Updates existing docs rather than replacing

Integration

With Development Flow

bash
/execute-task "Add payment processing"
/document-feature "payment processing"
/review  # Reviews include documentation

With Learning

bash
/learn patterns
/document-feature "discovered patterns"

Output

📝 Documenting Feature: Authentication System

🔍 Analyzing implementation...
Found 12 files related to authentication

📋 Generating documentation...
✅ Created src/auth/CLAUDE.md
✅ Updated API documentation
✅ Added usage examples
✅ Documented security measures
✅ Created test documentation

📊 Documentation Coverage:
- Technical: 100%
- API: 100%
- Examples: 8 scenarios
- Tests: Documented

💡 Suggestions:
- Add troubleshooting section
- Include performance metrics
- Document error codes

Direct Invocation

This is a dynamic prompt that Claude executes directly - no file installation needed:

bash
# Simply type the command
/document-feature [parameters]

# Claude will:
# 1. Analyze current context
# 2. Discover relevant patterns
# 3. Execute intelligently
# 4. Update distributed memory
# 5. Provide detailed results

Built with ❤️ for the AI Coding community, by Praney Behl