sickn33/agentic-awesome-skills/openclaw-github-repo-commander
Claude Code and agent skill by sickn33/agentic-awesome-skills
- community
Checking that the SKILL.md file is still in the repository.
7-stage super workflow for GitHub repo audit, cleanup, PR review, and competitor analysis
Install
npx vskill@latest install sickn33/agentic-awesome-skills/openclaw-github-repo-commanderSKILL.md
OpenClaw GitHub Repo Commander
Overview
A structured 7-stage super workflow for comprehensive GitHub repository management. This skill automates repository auditing, cleanup, competitor benchmarking, and optimization — turning a messy repo into a clean, well-documented, production-ready project.
When to Use This Skill
- Use when you need to audit a repository for secrets, junk files, or low-quality content
- Use when the user says "clean up my repo", "optimize my GitHub project", or "audit this library"
- Use when reviewing or creating pull requests with structured analysis
- Use when comparing your project against competitors on GitHub
- Use when running
/super-workflowor/openclaw-github-repo-commanderon a repo URL
How It Works
Stage 1: Intake
Clone the target repository, define success criteria, and establish baseline metrics.
Stage 2: Execution
Run bash scripts/repo-audit.sh <repo-path> from this skill directory — automated read-only checks for:
- Hardcoded secrets (
ghp_,sk-,AKIA, etc.) - Tracked
node_modules/or build artifacts - Empty directories
- Large files (>1MB)
- Missing
.gitignorecoverage - Broken internal README links
Stage 3: Reflection
Deep manual review beyond automation: content quality, documentation consistency, structural issues, version mismatches.
Stage 4: Competitor Analysis
Search GitHub for similar repositories. Compare documentation standards, feature coverage, star counts, and community adoption.
Stage 5: Synthesis
Consolidate all findings into a prioritized action plan (P0 critical / P1 important / P2 nice-to-have).
Stage 6: Iteration
Execute the plan: delete low-value files, fix security issues, upgrade documentation, add CI workflows, update changelogs.
Stage 7: Validation
Re-run applicable checks and report exact coverage/warnings. The bundled helper has six broad checks, excludes workflows and distinguishes neither all tracked/local files nor every secret format; a clean result is not security certification. Push or PR only through the actual repository workflow and user-authorized scope.
Examples
Example 1: Full Repo Audit
Runs all 7 stages and produces a detailed before/after report.
Example 2: Quick Cleanup
Example 3: Competitor Benchmarking
Best Practices
- ✅ Always run Stage 7 validation before pushing
- ✅ Use semantic commit messages:
chore:,fix:,docs: - ✅ Check the
pr_todo.jsonfile for pending reviewer requests - ❌ Don't skip Stage 4 — competitor analysis reveals blind spots
- ❌ Don't commit
node_modules/or.envfiles
Security & Safety Notes
The helper distinguishes a clean no-match from scanner failure and reports failure as unavailable. It still uses limited heuristic patterns and exclusions; do not execute it on untrusted targets as a review shortcut or treat its output as complete secret coverage.
- The audit script scans for common secret patterns but excludes
.github/workflows/to avoid false positives - The bundled script is read-only: it reports findings and never deletes, rewrites, stages, commits, or pushes files
- All
ghCLI operations use the user's existing authentication — no credentials are stored by this skill - The skill never modifies files without explicit user confirmation in Stage 6
Source Attribution
Originally contributed by @wd041216-bit in PR #340. No standalone upstream repository is currently available for this skill.
License: MIT | Version: 4.0.0
Limitations
- Use this skill only when the task clearly matches the scope described above.
- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.
Security
- Security scanPassed, 100 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 repositoryCheckingskills/openclaw-github-repo-commander/SKILL.md
Popularity
- Repository stars
- 47,061
- Repository forks
- 6,855
- 7-day trend score
- 54
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
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/sickn33/agentic-awesome-skills/openclaw-github-repo-commander)