api-documentation-writer
Generate comprehensive API documentation including endpoint descriptions, request/response examples, authentication guides, error codes, and SDKs. Creates OpenAPI/Swagger specs, REST API docs, and developer-friendly reference materials. Use when users need to document APIs, create technical references, or write developer documentation.
Works with
--- name: api-documentation-writer description: Generate comprehensive API documentation including endpoint descriptions, request/response examples, authentication guides, error codes, and SDKs. Creates OpenAPI/Swagger specs, REST API docs, and developer-friendly reference materials. Use when users need to document APIs, create technical references, or write developer documentation. license: MIT --- # API Documentation Writer Generate comprehensive, developer-friendly API documentation. ## Contents - `references/documentation-structure.md` — every section to cover (overview, auth, endpoints, errors, rate limits, SDKs, webhooks, GraphQL) - `references/output-template.md` — canonical REST Markdown template with worked examples - `references/best-practices.md` — best practices, developer-experience tips, and the output quality checklist ## Workflow 1. Gather API information. Determine the API type (REST, GraphQL, WebSocket, gRPC), authentication method (API key, OAuth, JWT), base URL and versioning strategy, available endpoints and their purposes, request/response formats, and any rate limiting or usage restrictions. 2. Build the documentation structure. Cover every section in `references/documentation-structure.md`, ordering the most common operations first. 3. Generate the output. Follow `references/output-template.md` for REST APIs; adapt to schema, query, mutation, and subscription examples for GraphQL. Replace all placeholders with realistic example data and show both request and response. 4. Document errors and rate limits. Include the standard error response format, common error codes, troubleshooting guidance, limits, headers to check, and how to handle `429` responses. 5. Provide code samples in multiple languages (curl, JavaScript, Python) and link SDKs, Postman collections, or OpenAPI specs where available. 6. Verify quality against the checklist in `references/best-practices.md` before delivering. ## Example Triggers - "Write API documentation for my REST endpoints" - "Create OpenAPI spec for my API" - "Document this GraphQL schema" - "Generate developer docs for my webhook API" - "Write authentication guide for API"
More Writing & Documentation skills
paper-context-resolver
lllllllama/rigorpilot-skills
Rigor Paper Context helper for README-first deep learning repo reproduction. Use only when the README and repository files leave a narrow reproduction-critical gap and the task is to resolve a specific paper detail such as dataset split, preprocessing, evaluation protocol, checkpoint mapping, or runtime assumption from primary paper sources while recording conflicts. Do not use for general paper summary, repo scanning, environment setup, command execution, title-only paper lookup, or replacing README guidance by default.
repo-intake-and-plan
lllllllama/rigorpilot-skills
Rigor Intake helper for README-first deep learning repo reproduction. Use when the task is specifically to scan a repository, read the README and common project files, extract documented commands, classify inference, evaluation, and training candidates, and return the smallest trustworthy reproduction plan to the main orchestrator. Do not use for environment setup, asset download, command execution, final reporting, paper lookup, or end-to-end orchestration.
minimal-run-and-audit
lllllllama/rigorpilot-skills
Rigor Run skill for README-first deep learning repo reproduction. Use when the task is specifically to capture or normalize evidence from the selected smoke test or documented inference or evaluation command and write standardized `repro_outputs/` files, including patch notes when repository files changed. Do not use for training execution, initial repo intake, generic environment setup, paper lookup, target selection, hidden scientific-meaning changes, or end-to-end orchestration by itself.
