Project overview
Run SkillCheck against an Agent Skill before distributing it or after a regression. Quick mode covers structure, syntax, integrity, security, and best practices; Standard adds script execution, I/O checks, and eval regression; Deep adds malformed inputs, edge cases, and end-to-end workflows. The result is a targeted report with pass rates, findings, and an overall health verdict.
Repository facts
- Primary language
- Python
- License
- MIT
- Repository updated
- Jun 12, 2026
- Default branch
- main
Resource types
General skill
Use cases
Testing and debuggingSecurity and privacy
Platforms
Claude Code, Codex, and more
Capabilities
Verification and evals