repo-scanner
Deep scan repository structure to extract metadata, detect frameworks, and identify domain boundaries. Use when starting assimilation, analyzing a new codebase, or gathering project context.
Profile →npx skills add majiayu000/claude-skill-registry --skill repo-scanner --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.
# Repo Scanner ## Overview Scan a repository's structure to produce a comprehensive report without reading all source code. This is phase 1 of the assimilation pipeline—gathering metadata that subsequent phases consume. --- ## When to Use Use this skill when: - Starting assimilation of a new repository - Analyzing an unfamiliar codebase - Gathering project context before making changes - Detecting frameworks and tooling --- ## Output **File:** `.github/temp/scan-report.json` The scan produces a structured report consumed by pattern-extractor (phase 2). --- ## Execution Steps ### Step 1: Create Temp Directory ```bash mkdir -p .github/temp ``` ### Step 2: Apply Ignore Patterns **MUST skip these directories entirely:** ``` node_modules/ vendor/ .venv/ __pycache__/ dist/ build/ .next/ target/ coverage/ .git/ out/ .cache/ .turbo/ .parcel-cache/ .nuxt/ .output/ ``` **Note existence but don't analyze content:** ``` package-lock.json yarn.lock pnpm-lock.yaml Cargo.lock poetry.lock go.sum ``` ### Step 3: Prioritize Files Read files in this order (most important first): | Priority | File Types | Examples | Why | |----------|------------|----------|-----| | 1 | Config files | package.json, ts
- Overview
- When to Use
- Output
- Execution Steps
- Step 1: Create Temp Directory
- Step 2: Apply Ignore Patterns
- Step 3: Prioritize Files
- Step 4: Detect Language
- Step 5: Detect Framework
- Step 6: Detect Project Type
- Step 7: Identify Domain Boundaries
- Step 8: Detect Tooling
- Step 9: Generate Report
- Step 10: Report Completion
mkdir -p .github/temp
What does the repo-scanner skill do?
Deep scan repository structure to extract metadata, detect frameworks, and identify domain boundaries. Use when starting assimilation, analyzing a new codebase, or gathering project context.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill repo-scanner --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.