05 Api GeneratorSAFE
This repository demonstrates how to use Claude Code to do real engineering work, not just writing code. 本项目是极客时间专栏 《Claude Code 工程化实战》 的官方配套示例仓库,目标就是: 👉 把 Claude Code 从“对话式编码工具”,变成 可设计、可复用、可治理的工程系统。
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
A production-ready skill for generating API documentation from source code.
Features
- Multi-framework support: Express.js, FastAPI, Spring Boot, Go (Gin/Echo)
- Multiple output formats: Markdown, OpenAPI 3.0
- Automated route detection: Python script for batch processing
- Validation tools: OpenAPI spec validation
Structure
04-api-generator/ ├── SKILL.md # Main skill file ├── PATTERNS.md # Framework detection patterns ├── STANDARDS.md # Documentation standards ├── EXAMPLES.md # Input/output examples ├── templates/ │ ├── index.md # API index template │ ├── endpoint.md # Endpoint documentation template │ └── openapi.yaml # OpenAPI spec template └── scripts/ ├── detect_routes.py # Route detection script └── validate_openapi.sh # OpenAPI validation script
Usage Examples
Single Endpoint Documentation
Ask Claude to document a specific endpoint:
Please document this Express route:
router.get('/users/:id', userController.getUser);Batch Documentation
Scan an entire directory:
Scan the src/routes directory and generate API documentation for all endpoints.
OpenAPI Generation
Generate an OpenAPI specification:
Generate an OpenAPI 3.0 spec for the API defined in src/api.
Scripts
Route Detection
# Detect all routes python scripts/detect_routes.py src/ # Detect Express routes only python scripts/detect_routes.py src/ --framework express # Save to file python scripts/detect_routes.py src/ -o routes.json
OpenAPI Validation
# Validate an OpenAPI spec ./scripts/validate_openapi.sh api-spec.yaml
allowed-tools Configuration
This skill uses:
Read- Read source filesGrep- Search for route patternsGlob- Find filesWrite- Create documentation filesBash(python:*)- Run Python scrip
f28f37d82954OBSERVED · 2026-10-12What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
--- name: api-generating description: Generate API endpoint code and documentation from specifications. Use when the user wants to create new API endpoints, generate route handlers, scaffold REST APIs, or produce OpenAPI/Swagger specs from code. allowed-tools: - Read - Grep - Glob - Write - Bash(python:*) - Bash(./scripts/*:*) --- # API Documentation Generator Generate comprehensive API documentation from source code. ## Quick Reference | Task | Resource | |------|----------| | Identify framework | See `PATTERNS.md` | | Documentation standards | See `STANDARDS.md` | | Example outputs | See `EXAMPLES.md` | ## Process ### Step 1: Identify API Endpoints Look for route definitions. For framework-specific patterns, see `PATTERNS.md`. ### Step 2: Extract Information For each endpoint, extract: - HTTP method (GET, POST, PUT, DELETE, etc.) - Path/route - Parameters (path, query, body) - Request/response schemas - Authentication requirements ### Step 3: Generate Documentation Use the template in `templates/endpoint.md` for each endpoint. ### Step 4: Create Overview Generate an index using `templates/index.md`. ## Output Formats ### Markdown (Default) Generate markdown suitable for README or docs site. ### OpenAPI/Swagger If requested, generate OpenAPI 3.0 spec. See `templates/openapi.yaml`. ## Automation To auto-detect routes: ```bash python scripts/detect_routes.py <source_directory> ``` To validate OpenAPI spec: ```bash ./scripts/validate_openapi.sh <spec_file> ```
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (1)
Gates applied: no_behavioural_pass, no_license.
f28f37d82954full audit observations/trust-audit/skill/huangjia2019__05-api-generator.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-12 | f28f37d82954 | SAFE | B | 89 | first audit |
Questions
What does the 05 Api Generator skill do?
This repository demonstrates how to use Claude Code to do real engineering work, not just writing code. 本项目是极客时间专栏 《Claude Code 工程化实战》 的官方配套示例仓库,目标就是: 👉 把 Claude Code 从“对话式编码工具”,变成 可设计、可复用、可治理的工程系统。
Is 05 Api Generator safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can 05 Api Generator access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (f28f37d82954), read on 2026-10-12. The repository is watched, and a new audit runs when it changes — this is the first audit.