doc-writing
The doc-writing skill generates structured API documentation in markdown format from a route manifest by reading source code to extract request parameters, response formats, and error handling information. Use this skill after discovering API routes to automatically produce organized endpoint documentation grouped by source file, which can then be validated by downstream quality-checking processes.
git clone --depth 1 https://github.com/huangjia2019/claude-code-engineering /tmp/doc-writing && cp -r /tmp/doc-writing/04-Skills/projects/08-skill-pipeline/.claude/skills/doc-writing ~/.claude/skills/doc-writingSKILL.md
# Doc Writing Skill
Generate structured API documentation from a route manifest.
## Input
You will receive a route manifest (JSON array) from the previous pipeline stage.
Each entry contains: method, path, file, line, middleware, type.
## Process
### Step 1: Read Source Code
For each route in the manifest, read the source file to understand:
- Request parameters (path, query, body)
- Response format
- Error handling
- Business logic summary
### Step 2: Generate Documentation
Use the template at `templates/endpoint-doc.md` for each route group.
Group routes by their source file (e.g., all product routes together).
### Step 3: Write Files
Write one markdown file per route group to the `docs/` directory:
- `docs/products-api.md`
- `docs/categories-api.md`
- etc.
## Output
Return a manifest of generated documentation files:
```json
{
"files_generated": ["docs/products-api.md", "docs/categories-api.md"],
"routes_documented": 8,
"routes_skipped": [],
"warnings": []
}
```
This manifest will be consumed by the next pipeline stage (quality-checking).Review code changes for quality, security, and best practices. Proactively use this after code modifications.
Run tests and report results concisely. Use this after code changes to verify everything works.
Analyze log files and extract actionable insights. Use when troubleshooting issues or investigating incidents.
Explore and analyze API-related code. Use when investigating endpoints, routing, or HTTP handling.
Explore and analyze authentication-related code. Use when investigating auth flows, session management, or security.
Explore and analyze database-related code. Use when investigating data models, queries, or persistence.
Analyze root cause of bugs after location is identified. Second step in bug investigation.
Implement bug fixes after analysis is complete. Third step in bug fix pipeline.