when-documenting-code-use-doc-generator
关于
This skill automatically generates comprehensive code documentation including API docs, README files, and architecture diagrams. It analyzes your codebase to extract structure and dependencies, then produces evidence-based documentation. Use it when you need to quickly create or improve documentation for your projects.
快速安装
Claude Code
推荐/plugin add https://github.com/DNYoussef/ai-chrome-extensiongit clone https://github.com/DNYoussef/ai-chrome-extension.git ~/.claude/skills/when-documenting-code-use-doc-generator在 Claude Code 中复制并粘贴此命令以安装该技能
技能文档
When Documenting Code - Use Doc Generator
Overview
This skill provides automated, comprehensive documentation generation for codebases. It analyzes code structure, generates API documentation, creates README files, adds inline comments, and produces architecture diagrams using evidence-based documentation patterns.
Core Capabilities
- Code Analysis: Extract APIs, functions, classes, types, and dependencies
- API Documentation: Generate OpenAPI, JSDoc, TypeDoc, and Python docstrings
- README Generation: Create comprehensive project documentation
- Inline Comments: Add missing documentation with context-aware comments
- Diagram Generation: Produce architecture and flow diagrams (Graphviz, Mermaid)
SPARC Methodology: Documentation Generation
Phase 1: SPECIFICATION - Analyze Documentation Requirements
Objective: Understand the codebase structure and documentation needs
Actions:
- Scan project structure and identify file types
- Detect programming languages and frameworks
- Identify existing documentation (README, API docs, comments)
- Analyze documentation gaps and missing coverage
- Determine documentation standards (JSDoc, TSDoc, Python docstrings)
Deliverables:
- Project structure analysis
- Documentation gap report
- Recommended documentation strategy
- Style guide selection
Agent: code-analyzer
Example Analysis:
Project: express-api-server
Languages: JavaScript (TypeScript), 85% | JSON 10% | Markdown 5%
Frameworks: Express.js, Jest
Current Documentation:
- README.md: Exists (outdated, 3 months old)
- API Docs: None
- Inline Comments: 12% coverage
- Type Definitions: 45% coverage
Gaps Identified:
- ❌ No API documentation (12 endpoints undocumented)
- ❌ Missing installation instructions
- ❌ No architecture diagrams
- ⚠️ Low inline comment coverage
- ✅ Package.json well-documented
Recommended Strategy:
1. Generate OpenAPI 3.0 spec for REST API
2. Add JSDoc comments to all public functions
3. Create comprehensive README with badges
4. Generate architecture diagram (system overview)
5. Add usage examples for main features
Phase 2: PSEUDOCODE - Design Documentation Structure
Objective: Plan documentation hierarchy and templates
Actions:
- Design documentation structure (README, API, guides)
- Define comment style and conventions
- Create templates for each documentation type
- Plan diagram types and structure
- Define metadata and frontmatter standards
Deliverables:
- Documentation structure outline
- Template designs for each type
- Comment convention guide
- Diagram specifications
Example Structure:
Documentation Hierarchy:
docs/
├── README.md # Project overview
├── INSTALLATION.md # Setup guide
├── API.md # API reference
├── ARCHITECTURE.md # System design
├── CONTRIBUTING.md # Contribution guide
├── diagrams/
│ ├── system-overview.svg # High-level architecture
│ ├── data-flow.svg # Data flow diagram
│ └── api-endpoints.svg # API structure
└── examples/
├── basic-usage.md
└── advanced-features.md
Comment Standards:
- JSDoc for all exported functions
- TypeDoc for TypeScript interfaces
- File header with purpose and author
- Inline comments for complex logic only
API Documentation:
- OpenAPI 3.0 specification
- Example requests/responses
- Error code documentation
- Authentication guide
Phase 3: ARCHITECTURE - Define Generation Pipeline
Objective: Design the documentation generation workflow
Actions:
- Define code parsing strategy (AST, regex, static analysis)
- Design template engine for documentation generation
- Plan diagram generation pipeline (Graphviz/Mermaid)
- Define validation and quality checks
- Create update and versioning strategy
Deliverables:
- Documentation generation pipeline
- Parser and extractor design
- Template rendering engine
- Validation rules
Pipeline Architecture:
┌─────────────────┐
│ Source Code │
│ Repository │
└────────┬────────┘
│
▼
┌─────────────────────────┐
│ Code Analyzer │
│ - AST Parsing │
│ - Extract Functions │
│ - Extract Types │
│ - Detect Patterns │
└────────┬────────────────┘
│
▼
┌─────────────────────────┐
│ Documentation Engine │
│ ├─ API Generator │
│ ├─ README Generator │
│ ├─ Comment Generator │
│ └─ Diagram Generator │
└────────┬────────────────┘
│
▼
┌─────────────────────────┐
│ Template Renderer │
│ - Mustache/Handlebars │
│ - Markdown Formatting │
│ - Syntax Highlighting │
└────────┬────────────────┘
│
▼
┌─────────────────────────┐
│ Validator │
│ - Link Checking │
│ - Spelling │
│ - Completeness │
└────────┬────────────────┘
│
▼
┌─────────────────────────┐
│ Output │
│ - docs/ │
│ - Inline Comments │
│ - Generated Diagrams │
└─────────────────────────┘
Phase 4: REFINEMENT - Generate and Validate Documentation
Objective: Execute documentation generation with quality checks
Actions:
- Parse source code and extract documentation targets
- Generate API documentation from code signatures
- Create README from templates and project metadata
- Add inline comments to undocumented code
- Generate architecture and flow diagrams
- Validate completeness and accuracy
- Check links and references
- Format and style according to standards
Deliverables:
- Complete API documentation
- Comprehensive README
- Inline code comments
- Architecture diagrams
- Validation report
Generation Examples:
Before (Undocumented Function):
function calculateDiscount(price, customerType, quantity) {
const baseDiscount = customerType === 'premium' ? 0.15 : 0.05;
const volumeDiscount = quantity > 100 ? 0.1 : quantity > 50 ? 0.05 : 0;
return price * (1 - baseDiscount - volumeDiscount);
}
After (With JSDoc):
/**
* Calculates the final price after applying customer and volume discounts
*
* @param {number} price - The original price before discounts
* @param {('standard'|'premium')} customerType - Customer tier level
* @param {number} quantity - Number of items purchased
* @returns {number} The discounted price
*
* @example
* // Premium customer buying 60 items at $100 each
* calculateDiscount(100, 'premium', 60);
* // Returns: 80 (15% customer + 5% volume discount)
*
* @see {@link https://docs.example.com/pricing|Pricing Documentation}
*/
function calculateDiscount(price, customerType, quantity) {
// Premium customers receive 15% base discount, standard customers 5%
const baseDiscount = customerType === 'premium' ? 0.15 : 0.05;
// Volume discounts: 10% for 100+, 5% for 50+, 0% otherwise
const volumeDiscount = quantity > 100 ? 0.1 : quantity > 50 ? 0.05 : 0;
return price * (1 - baseDiscount - volumeDiscount);
}
API Documentation Generation:
# Generated OpenAPI 3.0 Specification
openapi: 3.0.0
info:
title: E-commerce API
version: 1.0.0
description: REST API for e-commerce platform with pricing and inventory
paths:
/api/v1/products/{id}/price:
get:
summary: Calculate product price with discounts
description: Returns the final price after applying customer tier and volume discounts
operationId: calculateProductPrice
tags:
- Pricing
parameters:
- name: id
in: path
required: true
schema:
type: string
description: Product ID
- name: quantity
in: query
required: true
schema:
type: integer
minimum: 1
description: Quantity to purchase
- name: customerType
in: query
required: false
schema:
type: string
enum: [standard, premium]
default: standard
description: Customer tier level
responses:
'200':
description: Price calculated successfully
content:
application/json:
schema:
type: object
properties:
originalPrice:
type: number
example: 100.00
discountedPrice:
type: number
example: 80.00
discountsApplied:
type: array
items:
type: object
properties:
type:
type: string
enum: [customer, volume]
percentage:
type: number
example: 0.15
'404':
description: Product not found
README Generation:
# E-commerce API Server
[](https://travis-ci.org/org/repo)
[](https://codecov.io/gh/org/repo)
[](LICENSE)
> Production-ready REST API for e-commerce platform with advanced pricing, inventory management, and order processing.
## Features
- ✅ Dynamic pricing with customer tiers and volume discounts
- ✅ Real-time inventory tracking
- ✅ Order processing and fulfillment
- ✅ JWT authentication with role-based access
- ✅ Rate limiting and security middleware
- ✅ Comprehensive API documentation (OpenAPI 3.0)
## Quick Start
### Prerequisites
- Node.js >= 18.0.0
- PostgreSQL >= 14.0
- Redis >= 7.0 (for caching)
### Installation
```bash
# Clone repository
git clone https://github.com/org/ecommerce-api.git
cd ecommerce-api
# Install dependencies
npm install
# Configure environment
cp .env.example .env
# Edit .env with your database credentials
# Run migrations
npm run migrate
# Start server
npm start
Usage
// Example: Calculate price with discounts
const response = await fetch(
'http://localhost:3000/api/v1/products/prod-123/price?quantity=60&customerType=premium'
);
const { discountedPrice } = await response.json();
console.log(`Final price: $${discountedPrice}`);
API Documentation
Full API documentation available at:
- Interactive Docs: http://localhost:3000/api-docs (Swagger UI)
- OpenAPI Spec: docs/API.md
Key Endpoints
| Method | Endpoint | Description |
|---|---|---|
| GET | /api/v1/products | List all products |
| GET | /api/v1/products/{id} | Get product details |
| GET | /api/v1/products/{id}/price | Calculate price with discounts |
| POST | /api/v1/orders | Create new order |
| GET | /api/v1/orders/{id} | Get order status |
Architecture
See ARCHITECTURE.md for detailed system design.
Configuration
| Variable | Description | Default |
|---|---|---|
PORT | Server port | 3000 |
DATABASE_URL | PostgreSQL connection | - |
REDIS_URL | Redis connection | - |
JWT_SECRET | Authentication secret | - |
Testing
# Run all tests
npm test
# Run with coverage
npm run test:coverage
# Run integration tests
npm run test:integration
Contributing
See CONTRIBUTING.md for contribution guidelines.
License
MIT © 2025 Your Organization
### Phase 5: COMPLETION - Integrate and Maintain Documentation
**Objective**: Ensure documentation stays synchronized with code
**Actions**:
1. Integrate documentation into build pipeline
2. Set up automated documentation updates
3. Configure pre-commit hooks for comment validation
4. Establish documentation review process
5. Create documentation maintenance schedule
**Deliverables**:
- CI/CD integration
- Git hooks for documentation
- Maintenance schedule
- Documentation metrics dashboard
**Integration Strategy**:
```yaml
# .github/workflows/docs.yml
name: Documentation
on:
push:
branches: [main, develop]
pull_request:
jobs:
generate-docs:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v3
- name: Setup Node.js
uses: actions/setup-node@v3
with:
node-version: '18'
- name: Install dependencies
run: npm ci
- name: Generate API documentation
run: npm run docs:api
- name: Generate diagrams
run: npm run docs:diagrams
- name: Validate documentation
run: npm run docs:validate
- name: Check comment coverage
run: npm run docs:coverage
- name: Deploy to GitHub Pages
if: github.ref == 'refs/heads/main'
uses: peaceiris/actions-gh-pages@v3
with:
github_token: ${{ secrets.GITHUB_TOKEN }}
publish_dir: ./docs
Pre-commit Hook:
#!/bin/bash
# .git/hooks/pre-commit
echo "Checking documentation coverage..."
# Check for undocumented functions
undocumented=$(npm run --silent docs:check-coverage)
if [ $? -ne 0 ]; then
echo "❌ Documentation coverage below threshold"
echo "$undocumented"
echo ""
echo "Please add documentation to new functions before committing."
exit 1
fi
echo "✅ Documentation coverage acceptable"
Usage Patterns
Basic Documentation Generation
# Generate all documentation
/doc-generate
# Generate specific documentation type
/doc-api # API documentation only
/doc-readme # README generation only
/doc-inline # Add inline comments only
/doc-diagrams # Generate diagrams only
Advanced Usage
# Generate with specific output format
npx claude-flow docs generate --format openapi --output docs/api.yml
# Generate for specific files
npx claude-flow docs generate --files "src/**/*.js" --type jsdoc
# Generate with custom templates
npx claude-flow docs generate --template custom-readme.hbs
# Update existing documentation
npx claude-flow docs update --incremental
# Validate documentation completeness
npx claude-flow docs validate --min-coverage 80
Documentation Standards
Comment Style Guide
JavaScript/TypeScript (JSDoc):
/**
* Brief description (one sentence, under 100 chars)
*
* Detailed description explaining the purpose, behavior, and any
* important considerations. This can span multiple lines.
*
* @param {Type} paramName - Description of parameter
* @param {Type} [optionalParam=defaultValue] - Optional parameter
* @returns {Type} Description of return value
* @throws {ErrorType} When error occurs
*
* @example
* // Example usage
* const result = functionName(arg1, arg2);
*
* @see {@link RelatedFunction}
* @since 1.0.0
* @deprecated Use newFunction instead
*/
Python (Google Style):
def function_name(param1: str, param2: int = 0) -> bool:
"""Brief description (one sentence).
Detailed description explaining the purpose and behavior.
Can span multiple lines with proper formatting.
Args:
param1: Description of first parameter
param2: Description of optional parameter (default: 0)
Returns:
Description of return value
Raises:
ValueError: When invalid input provided
RuntimeError: When operation fails
Example:
>>> result = function_name("test", 5)
>>> print(result)
True
Note:
Important information or limitations
"""
README Template Structure
# Project Title
> Brief description (one sentence tagline)
[Badges: Build, Coverage, License, Version]
## Features
- Key feature 1
- Key feature 2
- Key feature 3
## Quick Start
### Prerequisites
### Installation
### Basic Usage
## Documentation
- [API Reference](docs/API.md)
- [Architecture](docs/ARCHITECTURE.md)
- [Contributing](CONTRIBUTING.md)
- [Changelog](CHANGELOG.md)
## Examples
### Basic Example
### Advanced Example
## Configuration
## Testing
## Deployment
## Support
## License
Quality Metrics
Documentation Coverage Goals:
- Public API functions: 100% documented
- Internal functions: 80% documented
- Complex algorithms: 100% with inline comments
- Type definitions: 100% documented
- Examples: At least 1 per major feature
Validation Checks:
- ✅ All public functions have JSDoc/docstrings
- ✅ All parameters documented with types
- ✅ Return values documented
- ✅ Examples provided for complex functions
- ✅ Links valid and accessible
- ✅ No spelling errors
- ✅ Consistent formatting
Troubleshooting
Common Issues
Issue: Generated docs missing some functions
- Solution: Check function export syntax, ensure
exportkeyword used
Issue: Diagrams not rendering
- Solution: Install Graphviz:
brew install graphvizorapt install graphviz
Issue: JSDoc comments not showing in IDE
- Solution: Configure TypeScript to include JSDoc in
tsconfig.json
Issue: README badges not updating
- Solution: Check CI/CD pipeline, verify badge URLs
Best Practices
- Write documentation as you code - Don't defer to later
- Keep comments concise - Explain "why" not "what"
- Use examples liberally - Show, don't just tell
- Update diagrams regularly - Keep architecture docs current
- Validate before committing - Use pre-commit hooks
- Review documentation in PRs - Treat docs as first-class code
- Version documentation - Tag docs with release versions
- Link related concepts - Create documentation graph
- Avoid redundancy - Single source of truth
- Test examples - Ensure code samples actually work
Integration with Other Skills
- code-review-assistant: Validates documentation in PRs
- tdd-workflow: Generates test documentation
- api-design-first: Creates API docs from specs
- refactoring-assistant: Updates docs during refactoring
References
- JSDoc Documentation
- TypeDoc Documentation
- OpenAPI Specification
- Google Python Style Guide
- Markdown Guide
- Graphviz Documentation
Version: 1.0.0 Last Updated: 2025-10-30 Maintainer: Base Template Generator Status: Production Ready
GitHub 仓库
相关推荐技能
content-collections
元Content Collections 是一个 TypeScript 优先的构建工具,可将本地 Markdown/MDX 文件转换为类型安全的数据集合。它专为构建博客、文档站和内容密集型 Vite+React 应用而设计,提供基于 Zod 的自动模式验证。该工具涵盖从 Vite 插件配置、MDX 编译到生产环境部署的完整工作流。
sglang
元SGLang是一个专为LLM设计的高性能推理框架,特别适用于需要结构化输出的场景。它通过RadixAttention前缀缓存技术,在处理JSON、正则表达式、工具调用等具有重复前缀的复杂工作流时,能实现极速生成。如果你正在构建智能体或多轮对话系统,并追求远超vLLM的推理性能,SGLang是理想选择。
Algorithmic Art Generation
元这个Claude Skill帮助开发者使用p5.js创建算法艺术,特别适用于生成式艺术和交互式可视化项目。它支持种子随机性、流场和粒子系统等关键技术,确保艺术作品的重复性和独特性。当讨论生成艺术、算法艺术或计算美学时,该技能会自动激活,指导开发者完成从概念设计到技术实现的全过程。
cloudflare-turnstile
元这个Skill提供完整的Cloudflare Turnstile集成知识,用于在表单、登录页面和API端点中实现无验证码的机器人防护。它支持React/Next.js/Hono等框架集成,涵盖令牌验证、错误代码调试和端到端测试等场景。通过运行后台不可见挑战,在保持用户体验的同时有效阻止自动化流量和垃圾信息。
