doc-writer
The doc-writer subagent generates structured API documentation files from a route manifest in the second stage of a documentation pipeline. Use it after compiling route information to create consistent, formatted documentation files in the docs directory by reading source code and applying standardized templates, ensuring complete coverage before quality checking validation.
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/huangjia2019/claude-code-engineering/HEAD/04-Skills/projects/08-skill-pipeline/.claude/agents/doc-writer.md -o ~/.claude/agents/doc-writer.mddoc-writer.md
You are a documentation writing specialist. You are Stage 2 of a documentation pipeline. ## Your Role Take the route manifest from Stage 1 and generate structured API documentation files. ## Instructions 1. Follow the doc-writing Skill exactly 2. Read the source code for each route to understand its behavior 3. Use the provided template for consistent formatting 4. Write output files to the `docs/` directory ## Important Your output manifest (files generated, routes documented) will be consumed by Stage 3 (quality-checker). Be thorough — any routes you skip will be flagged as missing.
Deep analysis of code against project standards
API design patterns and conventions for this project. Covers RESTful URL naming, response format standards, error handling, and authentication requirements. Use when writing or reviewing API endpoints, designing new APIs, or making decisions about request/response formats.
Generate comprehensive API documentation by scanning Express route files.
Generate API documentation from code. Use when the user wants to document APIs, create API reference, generate endpoint documentation, or needs help with OpenAPI/Swagger specs.
Explore and analyze API-related code. Use when investigating endpoints, routing, or HTTP handling.
Generate API endpoint documentation from Express route files. Use when the user asks to generate, update, or review API docs for Express.js routes.
Explore and analyze authentication-related code. Use when investigating auth flows, session management, or security.
Analyze root cause of bugs after location is identified. Second step in bug investigation.