Skill comparison
Use this as a shortlist, then open the skill detail page before adopting.
Decision summary
Strongest overall
Andrej Karpathy Skills
Use this as a leading candidate, then validate the README and install path in your own agent stack.
Fastest prototype
Andrej Karpathy Skills
Best first install candidate based on install readiness and adoption.
Freshest repo
Caveman
Most recent maintenance signal among this shortlist.
| Signal | Shellcheck ShellCheck, a static analysis tool for shell scripts | Andrej Karpathy Skills A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls. | Caveman 🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman | Graphify A tool that converts codebases, SQL schemas, and other files into queryable knowledge graphs for AI coding assistants. |
|---|---|---|---|---|
| Quality | 100/100 Excellent | 100/100 Excellent | 100/100 Excellent | 100/100 Excellent |
| Decision verdict | 100/100 Production-ready Use this as a leading candidate, then validate the README and install path in your own agent stack. | 100/100 Production-ready Use this as a leading candidate, then validate the README and install path in your own agent stack. | 100/100 Production-ready Use this as a leading candidate, then validate the README and install path in your own agent stack. | 100/100 Production-ready Use this as a leading candidate, then validate the README and install path in your own agent stack. |
| Adoption | 40K stars Verified outcomes are shown on each skill page | 175K stars Verified outcomes are shown on each skill page | 97K stars |
| 92K stars Verified outcomes are shown on each skill page |
| Freshness | Jun 11, 2026 | Apr 20, 2026 | Aug 11, 2026 | Jul 20, 2026 |
| Use-case fit |
| Workflow fit |
| Platform hints | Haskell, Static Analysis, Claude Code | Claude Code | JavaScript, Claude Code | Python |
| Warnings | No OpenAgentSkill engagement data yet | No OpenAgentSkill engagement data yet | No OpenAgentSkill engagement data yet | No OpenAgentSkill engagement data yet |
| Best for | Coding agents workflows · Claude Code teams · teams that value GitHub adoption signals | Coding agents workflows · Claude Code teams · teams that value GitHub adoption signals | Coding agents workflows · Claude Code teams · teams that value GitHub adoption signals | Coding agents workflows · general agent builders · teams that value GitHub adoption signals |
| Not ideal for | teams that need a vendor-supported SLA · high-compliance environments without internal security review | teams that need a vendor-supported SLA · high-compliance environments without internal security review | teams that need a vendor-supported SLA · high-compliance environments without internal security review | teams that need a vendor-supported SLA · high-compliance environments without internal security review |
| OpenAgentSkill engagement | 0 views 0 install copies | 0 views 0 install copies | 0 views 0 install copies | 0 views 0 install copies |
| Install | $ npx skills add koalaman/shellcheck | $ npx skills add multica-ai/andrej-karpathy-skills | $ npx skills add JuliusBrussee/caveman | $ npx skills add Graphify-Labs/graphify |