If you're building or reviewing Agent Skills, this gives you a scoring rubric based on 17+ official examples. It evaluates across dimensions like knowledge delta (does this teach Claude something it doesn't already know?), mindset transfer (does it share expert thinking patterns?), and anti-pattern quality (does it have specific NEVER lists?). The core insight is solid: a good skill is expert-only knowledge minus what Claude already knows, because context window is expensive. Useful for catching skills that waste tokens explaining basics like "what is a PDF" or generic advice like "write clean code". Treats skill design as knowledge engineering, not tutorial writing.
npx skills add https://github.com/softaworks/agent-toolkit --skill skill-judge