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-6 --agent claude-code

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

Facts
Files in the skill folder: 2
SKILL.md size: 25 KB
Bundled scripts: none
Requires: - deep-analysis - technical-diagrams
Path: skills/analysis/codebase-analysis-sequenzia-agent-alchemy-6/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 executes a 3-phase workflow to analyze a codebase: Deep Analysis, Reporting, and Post-Analysis Actions. It accepts an optional analysis-context and uses a deep-analysis workflow to explore and synthesize findings, then presents a structured report with an Architecture Overview, Tech Stack, Critical Files, Patterns & Conventions, Relationship Map, Challenges & Risks, Recommendations, and Analysis Methodology. It can load and use a Mermaid diagram guidance from the technical-diagrams skill for architecture visuals, and it proceeds to Phase 3 actions like saving reports or updating project documentation. Phase 3 also includes an Actionable Insights workflow to extract high/medium/low severity items from the Phase 2 report, delegate fixes to code-architect or code-explorer agents when needed, and summarize results, before concluding the workflow. The skill requires dependencies: deep-analysis and technical-diagrams, and declares tools: claude-code.

How it works

  • Phase 1 Deep Analysis: Determines analysis context (defaults to general codebase understanding if not provided). Checks for an exploration cache manifest at .agents/sessions/exploration-cache/manifest.md and validates cache based on codebase_path and timestamp within a 24-hour TTL. If valid, offers Use cached results or Run fresh analysis. If no valid cache, proceeds to Run deep-analysis workflow using the provided analysis context and sets CACHE_TIMESTAMP to null after completion. After deep analysis, records metadata including whether results were cached (CACHE_HIT), cache timestamp (CACHE_TIMESTAMP), and number of explorer agents used.
  • Phase 2 Reporting: Loads diagram guidance from technical-diagrams for Mermaid diagrams. Uses the provided report template to structure the presentation with sections: Executive Summary, Architecture Overview, Tech Stack, Critical Files, Patterns & Conventions, Relationship Map, Challenges & Risks, Recommendations, and Analysis Methodology. Proceeds to Phase 3 without waiting for user input.
  • Phase 3 Post-Analysis Actions: Allows the user to Save Codebase Analysis Report, Save a Custom Report, Update Project Documentation, or Keep Insights in Memory. Each action has detailed steps for file location prompts, generation, and saving. Includes an Actionable Insights workflow (Steps 3a–3d) to extract and process items from the Phase 2 report, delegating to a code-architect or code-explorer when needed, presenting proposals, awaiting user approval, and summarizing results. Concludes with Step 4 completing the workflow.

When to use it

Use when asked to analyze, explore, understand, map, get an overview, audit, or assess how a codebase is structured. The workflow anticipates typical prompts for codebase analysis and maintains an explicit context and caching strategy to optimize repeated analyses.

What it can touch

The skill references tools: claude-code and relies on the deep-analysis and technical-diagrams capabilities for exploration, synthesis, and Mermaid diagram guidance. It interacts with the project repository paths for creating and saving reports and documentation under internal/docs or project root, generating Markdown files as outputs.

Caveats

  • Requires dependencies: deep-analysis and technical-diagrams.
  • Uses caching with a default TTL of 24 hours; behavior depends on cache validity.
  • Post-Analysis Actions may prompt for file paths and may create or modify files under the project root or internal/docs depending on user choices.
  • Actionable Insights processing may delegate to code-architect or code-explorer agents; fallback is direct investigation if delegation fails.
From the SKILL.md

# Codebase Analysis Workflow Execute a structured 3-phase codebase analysis workflow to gather insights. Accept the following inputs: - **analysis-context** (optional): What to analyze and why. Defaults to "general codebase understanding" if not provided. ## 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:** - If analysis-context input is provided, use it as the analysis context - If no input, 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/syn

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. Agent Delegation Failures (Step 3c)
  13. Agent 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-6 --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