Evaluates and audits AI Agent Skill design quality against official specifications and expert best practices.
关于
Skill Judge is a specialized diagnostic tool designed to review, score, and improve SKILL.md files for AI coding agents. It utilizes a 120-point multi-dimensional framework to assess the 'Knowledge Delta'—ensuring skills provide high-value expert insights rather than redundant tutorials. By identifying anti-patterns and auditing activation descriptions, it helps developers eliminate token waste and refine agent thinking patterns for maximum performance.
主要功能
Knowledge Delta analysis to minimize redundant token usage
Comprehensive frontmatter and trigger description auditing
Anti-pattern identification and 'NEVER' list optimization
Expert mindset and domain-specific procedure validation
Multi-dimensional 120-point scoring system for skill quality
347 GitHub stars
使用场景
Auditing new agent skills before deployment to a production toolkit
Refining existing skill packages to reduce context window consumption
Standardizing documentation for team-based AI agent development
