Skip to content

divar-ir/ai-doc-gen / skills/analyze-codebase

analyze-codebase

Unverified

Run 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.

Analyze Codebase

Produce five AI-readable analysis documents by running specialized analyzers in parallel, each writing to .ai/docs/ in the target repository. These documents are the input for the generate-readme and generate-ai-rules skills, and are valuable on their own as machine-readable architecture maps.

Workflow

1. Determine scope

  • Target repository: the current working directory unless the user names another path.
  • Which analyses to run: all five by default. The user may exclude some (e.g., "skip the data flow analysis"). For projects with no meaningful API surface or request handling (pure libraries, simple scripts), suggest skipping the API and request-flow analyzers, but let the user decide.
AnalyzerReference fileOutput file
Structurereferences/structure-analyzer.md.ai/docs/structure_analysis.md
Dependenciesreferences/dependency-analyzer.md.ai/docs/dependency_analysis.md
Data flowreferences/data-flow-analyzer.md.ai/docs/data_flow_analysis.md
Request flowreferences/request-flow-analyzer.md.ai/docs/request_flow_analysis.md
APIreferences/api-analyzer.md.ai/docs/api_analysis.md

2. Run the analyzers in parallel

Create .ai/docs/ in the target repo if it doesn't exist. Then spawn one subagent per selected analyzer, all in a single message so they run concurrently. Each subagent prompt should say:

Read the instructions at <absolute path to this skill's references/<analyzer>.md> and follow them exactly for the repository at <absolute repo path>. Explore the codebase with your file tools as needed. Write your complete analysis to <absolute repo path>/.ai/docs/<output file>, following the exact output format in the instructions. In the written file, refer to files by repo-relative paths (e.g. src/main.py, not absolute paths) so the document is portable. Return a one-paragraph summary of what you found.

Failures are isolated: if one analyzer fails, the others' results still count. Retry a failed analyzer once; if it fails again, note it in the final report and move on. Only treat the run as failed if every analyzer fails.

3. Verify and report

After all subagents finish:

  1. Confirm each expected output file exists and is non-trivial (has content under its section headings, not just the skeleton).
  2. Check that no absolute local paths leaked into the documents; replace any with repo-relative paths.
  3. Report to the user: which analyses succeeded, where the files are, and a short synthesis of the most important findings. Suggest generate-readme or generate-ai-rules as natural next steps.

Notes

  • Analysis documents are optimized for AI consumption, not human reading — that's intentional. Human-facing output comes from the generator skills.
  • Recommend adding .ai/docs/ to the repo (committed, not ignored) so future AI sessions and teammates benefit; but respect the project's existing convention if .ai/ is gitignored.
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: 464kUpdated Claude CodeCodexVerifiedInstall
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: 196kUpdated Claude CodeCodexVerifiedInstall
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: 196kUpdated Claude CodeCodexUnverifiedInstall
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: 196kUpdated Claude CodeCodexVerifiedInstall