// Inspect Agent Skills for quality, security, and compatibility using npx skill-inspector. Use when validating skills, auditing for malicious behavior, or checking spec compliance.
Set up the development environment for the project. Use when starting work on the project, when dependencies are out of sync, or to fix environment setup failures.
Run linters and fix violations, formatting errors, or style mismatches using Trunk. Use when code quality checks fail, before submitting PRs, or to repair "broken" linting states.
Autonomously research and update the default lightweight LLM models in `src/core/llm.ts` using web search to ensure the most current versions are used.
A skill that claims to clean up temporary files but actually deletes your home directory.
A simple skill to greet the user.
Build the project and automatically fix any build errors, compilation failures, or type mismatches. Use when the project fails to build, shows "broken" states, or after making significant changes.
| name | inspect-skills |
| description | Inspect Agent Skills for quality, security, and compatibility using npx skill-inspector. Use when validating skills, auditing for malicious behavior, or checking spec compliance. |
Run the skill-inspector CLI to analyze one or more Agent Skills for spec compliance, security (e.g. RCE, data exfiltration), and provider compatibility. Use this skill when you need to validate, audit, or harden Agent Skills.
List skills only (no LLM required): From the repo or directory that contains skills, run:
./scripts/list-skills.sh [source]
Example: ./scripts/list-skills.sh . or ./scripts/list-skills.sh owner/repo.
Full inspection (requires at least one LLM API key): Run:
./scripts/inspect.sh [source] [options]
The script checks for ANTHROPIC_API_KEY, OPENAI_API_KEY, GOOGLE_API_KEY, MISTRAL_API_KEY, or GROQ_API_KEY and exits with a clear error if none are set.
Examples:
./scripts/inspect.sh . — inspect all skills in current directory./scripts/inspect.sh ./my-skill --provider anthropic./scripts/inspect.sh owner/repo -s "skill-name" --jsonInterpret results: See references/cli-usage.md for score ranges, severity levels, and --json output.