Menu
Fetch GitHub starred repos, analyze one with LLM, and propose improvements via PR
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | fetch-star-repos |
| description | Fetch GitHub starred repos, analyze one with LLM, and propose improvements via PR |
| allowed-tools | Bash, Read |
| user-invocable | true |
Fetches your recently starred GitHub repos (last 30 days), then runs the research scout to analyze ONE repo and propose concrete code improvements via PR.
.env.local and fetch starred repos:set -a && source .env.local && set +a && LOOKBACK_DAYS=30 python3 scripts/fetch_github_stars.py
Required env vars in .env.local:
GITHUB_USERNAME — Your GitHub usernameOPENROUTER_API_KEY — For LLM analysiscat .claude/bookmarks.json | python3 -c "import sys,json; bm=json.load(sys.stdin); print(f'Total starred repos: {len(bm)}'); [print(f' - [{b.get(\"source\",\"?\")}] {b[\"url\"][:80]}') for b in bm[-10:]]"
set -a && source .env.local && set +a && LOOKBACK_DAYS=30 python3 scripts/run_research_scout.py
.claude/research-scout-findings.md exists), create a PR:BRANCH="research-scout/$(date +%Y-%m-%d-%H%M)"
git checkout -b "$BRANCH"
git add .claude/research-scout-state.json .claude/bookmarks.json .claude/research-scout-findings.md
git commit -m "research-scout: improvement proposal from $(date +%Y-%m-%d)"
git push -u origin "$BRANCH"
gh pr create --title "research-scout: improvement proposal $(date +%Y-%m-%d)" --body "$(cat .claude/research-scout-findings.md)" --label "research-scout"
git checkout main
Report: how many repos were fetched, which repo was analyzed, what improvements were proposed, and whether a PR was created.
Deep-dive analysis of an open-source repository. Clones the repo, explores architecture/patterns/internals, and produces up to 30 structured Markdown files in analysis/<repo-name>/. Use when analyzing a GitHub repo for learnings, comparison, or adoption roadmap.
Review code changes for quality, security, and correctness. Use this before merging PRs, after significant refactors, or when reviewing agent output.
Review and optimize LLM API costs in the orchestrator. Analyze model routing, budget tracking, prompt caching, and retry logic for cost efficiency.
Deploy services using Docker/OrbStack. Use this to build and deploy containers, run health checks, and manage deployments.
Review production code and update all documentation under docs/ to match the current codebase state.
Build and manage Docker containers via OrbStack. Use this to build images, run containers, check service health, and manage docker-compose services.