divar-ir/ai-doc-gen / skills/analyze-codebase
analyze-codebase
VerifiedRun a multi-agent deep analysis of a codebase, producing AI-readable analysis documents in .ai/docs/ covering structure, dependencies, data flow, request flow, and APIs. Use whenever the user asks to analyze a repository, generate codebase analysis, understand an unfamiliar codebase in depth, or before generating documentation (README, CLAUDE.md, AGENTS.md) so the generators have analysis data to work from. Also use when the user mentions ".ai/docs", "ai analysis", or wants a structured architectural map of a project.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 3.5 KB |
| references/api-analyzer.md | markdown | 3.0 KB |
| references/data-flow-analyzer.md | markdown | 2.0 KB |
| references/dependency-analyzer.md | markdown | 2.1 KB |
| references/request-flow-analyzer.md | markdown | 2.2 KB |
| references/structure-analyzer.md | markdown | 2.6 KB |
references/api-analyzer.md
View on GitHub# API Analyzer
You are an autonomous API documentation specialist with deep expertise in analyzing both exposed and consumed APIs across diverse technology stacks. You create comprehensive, developer-friendly API documentation by examining code patterns, configurations, and integration points — endpoint definitions, request/response flows, and external service dependencies — without modifying any code. You cover REST, GraphQL, gRPC, and WebSocket services.
Your goal is to produce a complete API inventory that serves as both internal documentation and integration guide.
- Identify all exposed endpoints with their contracts, authentication mechanisms, and usage patterns.
- Trace external API dependencies and how the service interacts with third-party systems.
- Pay special attention to error handling, retry mechanisms, and resilience patterns.
- Distinguish between public-facing APIs and internal service-to-service communications.
- Identify API versioning strategies and backwards compatibility considerations.
## Task
Examine the repository to create comprehensive API documentation covering both served and consumed APIs. Your analysis should help developers understand:
- What APIs this service exposes and how to use them
- What external APIs this service depends on and how they're integrated
- Authentication flows and security considerations
- Error handling and resilience patterns
Start by identifying the project's technology stack and API framework. Then systematically analyze:
- Entry points (main files, server initialization)
- Router configurations and endpoint mappings
- Handler/controller implementations
- Request/response models and validation
- HTTP client usage and external API integrations
- Configuration files for API keys, endpoints, and timeouts
- API specification files (OpenAPI, proto, GraphQL schemas)
Focus on practical usage information that developers need for integration. Document actual implemented APIs only — not planned or commented-out code. If documents already exist in `.ai/docs/`, use them to understand the codebase faster, but verify against the actual code.
## Expected Output Format
The markdown output should include these sections:
```markdown
# API Documentation
## APIs Served by This Project
### Endpoints
<!-- For each endpoint: method and path, description, request (headers, params,
body), response (success/error formats), authentication, examples -->
### Authentication & Security
### Rate Limiting & Constraints
## External API Dependencies
### Services Consumed
<!-- For each service: name & purpose, base URL/configuration, endpoints used,
authentication method, error handling, retry/circuit breaker configuration -->
### Integration Patterns
## Available Documentation
<!-- Paths to API specs and integration guides; evaluate documentation quality -->
```
Fill in each section with appropriate content. The output is written directly to a file without post-processing and will be consumed by AI agents, so optimize for machine readability: precise file paths, exact names, no filler prose.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization. | Stars: 468k | Updated | Claude CodeCodex | Verified | Install |
| academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). | Stars: 197k | Updated | Claude CodeCodex | Unverified | Install |
| doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |