jmagly/aiwg/repo-analyzer
Claude Code and agent skill by jmagly/aiwg
- community
Checking that the SKILL.md file is still in the repository.
Analyze GitHub repositories for structure, documentation, dependencies, and contribution patterns. Use for codebase understanding and health assessment.
Install
npx vskill@latest install jmagly/aiwg/repo-analyzerSKILL.md
Repository Analyzer Skill
Purpose
Single responsibility: Analyze GitHub repository structure, documentation quality, and contribution patterns for codebase understanding. (BP-4)
Grounding Checkpoint (Archetype 1 Mitigation)
Before executing, VERIFY:
- [ ] gh CLI is installed and authenticated
- [ ] Repository URL or local clone exists
- [ ] Access permissions verified (public or authenticated)
- [ ] Analysis scope defined (structure, docs, deps, or all)
DO NOT analyze without confirming repository access.
Uncertainty Escalation (Archetype 2 Mitigation)
ASK USER instead of guessing when:
- Multiple repositories to analyze - which first?
- Private repo requires different auth
- Analysis depth unclear (quick vs deep)
- Specific aspects to focus on
NEVER scrape repository data without user intent.
Context Scope (Archetype 3 Mitigation)
| Context Type | Included | Excluded | |
|---|---|---|---|
| RELEVANT | Repo structure, README, package files | Source code details | |
| PERIPHERAL | Contribution stats, issue patterns | PR content | |
| DISTRACTOR | Fork network | Unrelated repos |
Workflow Steps
Step 1: Verify Access (Grounding)
Step 2: Analyze Structure
Step 3: Documentation Analysis
Step 4: Dependency Analysis
Step 5: Contribution Analysis
Recovery Protocol (Archetype 4 Mitigation)
On error:
- PAUSE - Note what data was collected
- DIAGNOSE - Check error type:
404→ Check repo name, visibility401→ Re-authenticate with gh auth login403→ Check rate limits or permissionsAPI error→ Fall back to local clone analysis
- ADAPT - Use alternative data sources
- RETRY - With different approach (max 3 attempts)
- ESCALATE - Report partial analysis
Checkpoint Support
State saved to: .aiwg/working/checkpoints/repo-analyzer/
Output Format
Common Analysis Queries
| Query | Purpose | |
|---|---|---|
gh repo view | Basic info | |
gh api /repos/{}/languages | Language breakdown | |
gh api /repos/{}/contributors | Contributor list | |
gh api /repos/{}/commits | Recent commits | |
gh api /repos/{}/releases | Release history | |
gh api /repos/{}/pulls | Open PRs |
References
- GitHub CLI: https://cli.github.com/
- GitHub API: https://docs.github.com/en/rest
- REF-001: Production-Grade Agentic Workflows (BP-4)
- REF-002: LLM Failure Modes (Archetype 1 grounding)
Security
- Security scanPassed, 96 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingagentic/code/frameworks/sdlc-complete/extensions/github/skills/repo-analyzer/SKILL.md
Popularity
- Repository stars
- 101
- Repository forks
- 15
- Repository npm downloads, 7 days
- 4,137
- 7-day trend score
- 42
Stars and forks are for the whole GitHub repository, not this skill alone. Downloads are for the repository's npm package. Refreshed 25 Mar 2026, 7 months ago.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/jmagly/aiwg/repo-analyzer)