codebase-analysis
Produce a structured codebase analysis report with architecture overview, critical files, patterns, and actionable recommendations. Use when asked to "analyze codebase", "explore codebase", "understand this codebase", "map the codebase", "give me an overview of this project", "what does this codebase do", "codebase report", "project analysis", "audit this codebase", or "how is this project structured".
npx skills add majiayu000/claude-skill-registry --skill codebase-analysis-sequenzia-agent-alchemy-2 --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Produces a structured codebase analysis report with architecture overview, critical files, patterns, and actionable recommendations. Invoked when users ask to analyze, explore, understand, map, or audit a codebase. Utilizes a 3-phase workflow (Deep Analysis, Reporting, Post-Analysis) and relies on the deep-analysis and technical-diagrams skills; results are cached with optional retrieval of cached synthesis.
How it works
- Phase 1: Deep Analysis
- Determine analysis context from user input or default to general codebase understanding.
- Check for an exploration cache at .claude/sessions/exploration-cache/manifest.md; if valid, offer to use cached results or run fresh analysis.
- If no valid cache or user chooses fresh, run the deep-analysis workflow using the provided context to explore, plan, and synthesize findings; set CACHE_TIMESTAMP = null after completion.
- Verify results and fill gaps by inspecting files if needed; record metadata: CACHE_HIT, CACHE_TIMESTAMP, and number of explorer agents used.
- Phase 2: Reporting
- Use Mermaid diagrams via the technical-diagrams skill for Architecture Overview and Relationship Map.
- Present the analysis using a predefined template with sections: Executive Summary, Architecture Overview, Tech Stack, Critical Files, Patterns & Conventions, Relationship Map, Challenges & Risks, Recommendations, Analysis Methodology.
- Phase 3 is triggered after Phase 2 completes.
- Phase 3: Post-Analysis Actions
- Allow the user to Save Codebase Analysis Report, Save a custom report, Update project documentation, and Keep a condensed summary in memory.
- If saving reports, determine file locations (prefer internal/docs/ when present) and confirm saves; support updates to README.md, CLAUDE.md, and AGENTS.md with guided drafts.
- Optional: Keep quick reference in memory and expose a condensed Codebase Quick Reference.
What it can touch
- Tools: claude-code is declared for use in analysis workflows.
- Configs/files to read/write during reporting and post-analysis actions (e.g., internal/docs/, codebase-analysis-report-*.md).
Caveats
- Requires: deep-analysis and technical-diagrams for full phase execution.
- Output depends on actual codebase data and user inputs; no outcomes are promised beyond the described steps.
- License: MIT
# Codebase Analysis Workflow Execute a structured 3-phase codebase analysis workflow to gather insights. ## Phase Overview 1. **Deep Analysis** -- Explore and synthesize codebase findings via the deep-analysis skill 2. **Reporting** -- Present structured analysis to the user 3. **Post-Analysis Actions** -- Save, document, or retain analysis insights --- ## Phase 1: Deep Analysis **Goal:** Explore the codebase and synthesize findings. 1. **Determine analysis context:** - Accept the following inputs: an analysis context or feature description - If no inputs, set context to "general codebase understanding" 2. **Check for cached results:** - Check if `.claude/sessions/exploration-cache/manifest.md` exists - If found, read the manifest and verify: `codebase_path` matches the current working directory, and `timestamp` is within the configured cache TTL (default 24 hours) - **If cache is valid**, prompt the user to choose: - **Use cached results** (show the formatted cache date) -- Read cached synthesis from `.claude/sessions/exploration-cache/synthesis.md` and recon from `recon_summary.md`. Set `CACHE_HIT = true` and `CACHE_TIMESTAMP` to the cache's timestamp. Skip step 3 and proceed dir
- Phase Overview
- Phase 1: Deep Analysis
- Phase 2: Reporting
- Report Template
- Section Guidelines
- Adapting the Template
- Phase 3: Post-Analysis Actions
- Step 1: Select actions
- Step 2: Execute selected actions
- Step 3: Actionable Insights Follow-up
- Actionable Insights Template
- Item List Format
- Severity Assignment Guidelines
- Complexity Assessment Criteria
What does the codebase-analysis skill do?
Produce a structured codebase analysis report with architecture overview, critical files, patterns, and actionable recommendations. Use when asked to "analyze codebase", "explore codebase", "understand this codebase", "map the codebase", "give me an overview of this project", "what does this codebase do", "codebase report", "project analysis", "audit this codebase", or "how is this project structured".
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill codebase-analysis-sequenzia-agent-alchemy-2 --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.