Agent skill · Security

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".

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill codebase-analysis-sequenzia-agent-alchemy-3 --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 19 KB
Bundled scripts: none
Requires: - deep-analysis - technical-diagrams
Path: skills/analysis/codebase-analysis-sequenzia-agent-alchemy-3/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

Review
written from the skill's own SKILL.md · Aug 5, 2026

What it does

The skill defines a three-phase workflow to analyze a codebase: Phase 1 Deep Analysis to explore the codebase and synthesize findings, Phase 2 Reporting to present a structured analysis with an architecture overview, tech stack, critical files, patterns, relationship map, risks, and recommendations, and Phase 3 Post-Analysis Actions to save reports, update documentation, or keep memory of insights. It supports caching of results and can load cached synthesis to skip repeated analysis. It relies on the deep-analysis skill for reconnaissance and synthesis and on the technical-diagrams skill for Mermaid diagrams in architecture-related sections. It requires inputs that set the analysis context (defaulting to general codebase understanding) and yields Phase 2 findings that include an analysis methodology and cache metadata such as whether results were cached and the cache timestamp. The workflow enforces a fixed sequence: check cache, run deep-analysis if needed, verify results, then present the report and proceed to post-analysis actions.

How it works

  • Phase 1: Deep Analysis
    • Determine analysis context from inputs or default to general codebase understanding.
    • Check for and validate a cache manifest at .agents/sessions/exploration-cache/manifest.md; if valid, offer to use cached results or run a fresh analysis.
    • If no valid cache or user chooses fresh, invoke the deep-analysis skill with the provided context to perform reconnaissance, team planning, and synthesis; set CACHE_TIMESTAMP to null for fresh results.
    • Validate synthesis coverage and fill gaps by searching files if needed; record metadata including CACHE_HIT, CACHE_TIMESTAMP, and number of exploration workers.
  • Phase 2: Reporting
    • Load diagram guidance from technical-diagrams for Mermaid syntax.
    • Use the provided report template to structure the output: Executive Summary, Architecture Overview, Tech Stack, Critical Files, Patterns & Conventions, Relationship Map, Challenges & Risks, Recommendations, and Analysis Methodology.
    • Proceed to Phase 3 after presentation.
  • Phase 3: Post-Analysis Actions
    • Prompt for actions: Save Codebase Analysis Report, Save a custom report, Update project documentation, Keep a condensed summary in memory.
    • For Save Codebase Analysis Report, determine file location under internal/docs/ or project root, generate and save the full report, and confirm.
    • Optional steps for custom reports and documentation updates follow detailed prompts and drafts, with a structured approval flow.
  • Error handling and coordination rules are described for failures, delegation to specialists, and memory of insights.

When to use it

Use when asked to analyze or audit a codebase, understand project structure, map relationships, or generate a formal codebase report; the skill explicitly lists trigger phrases such as "analyze codebase", "explore codebase", "understand this codebase", "map the codebase", "give me an overview of this project", or "codebase report".

What it can touch

  • Tools: claude-code (as declared under requires)
  • It references the deep-analysis and technical-diagrams skills for broader workflow steps and diagram rendering.

Caveats

  • The workflow depends on the availability and correct execution of the deep-analysis and technical-diagrams skills.
  • Cache-based optimizations require a valid manifest and TTL (default 24 hours) and could bypass fresh analysis if not refreshed.
  • The Phase 2 report structure is template-driven and will be populated with findings from Phase 2; exact content depends on the codebase analyzed.
From the SKILL.md

# 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 provided, set context to "general codebase understanding" 2. **Check for cached results:** - Check if `.agents/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 `.agents/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 pr

What's inside
Steps it walks through
  1. Phase Overview
  2. Phase 1: Deep Analysis
  3. Phase 2: Reporting
  4. Phase 3: Post-Analysis Actions
  5. Step 1: Select actions
  6. Step 2: Execute selected actions
  7. Step 3: Actionable Insights Follow-up
  8. Step 4: Complete the workflow
  9. Error Handling
  10. General
  11. Documentation Update Failures (Step 2c)
  12. Specialist Delegation Failures (Step 3c)
  13. Coordination
  14. Report Template
Ships with 1 file
  • metadata.json
More from claude-skill-registry
All skills →
About this skill
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-3 --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.

Keep going