Evaluate SKILL.md files against official specifications using eight dimensions.
npx skills add https://github.com/fbosch/dotfiles --skill skill-judge-fbosch
Please help me install this Agent Skill. Skill: skill-judge Source: https://github.com/fbosch/dotfiles/tree/main/.agents/skills/skill-judge Command: npx skills add https://github.com/fbosch/dotfiles --skill skill-judge-fbosch
This Skill provides a rigorous framework to evaluate Agent Skills (SKILL.md) and Skill packages against official specifications, enabling consistent quality scoring and actionable improvements.
Run a Skill Evaluation Report on the target SKILL.md to generate dimension scores and a structured improvement plan.
High-intent search queries and answers about installing and using this skill.
To audit a SKILL.md file for specification compliance, run a Skill Evaluation Report. This assesses the file against official specifications across 8 evaluation dimensions to ensure robust guidance for AI agents.
Scoring Agent Skills for quality requires a structured protocol evaluating 8 dimensions, including Knowledge Delta, Mindset, and Anti-Pattern Quality. This generates a dimensional evaluation with a final score and recommended improvements.
Yes, you can use this skill evaluation framework to calibrate skills across multiple projects. It applies a standardized scoring protocol and report template to ensure consistent activation and performance evaluation.
A documentation audit checks 8 evaluation dimensions: Knowledge Delta, Mindset, Anti-Pattern Quality, Specification Compliance, Progressive Disclosure, Freedom Calibration, Pattern Recognition, and Practical Usability.
Skill calibration requires no external dependencies or specific components. The evaluation operates directly on your target SKILL.md files and skill packages to produce a structured improvement plan.
To get actionable improvements from a skill report, the evaluation workflow outputs a structured Skill Evaluation Report. This report contains dimension scores and a recommended improvement plan based on specification compliance.
Likas07Evaluate AI Agent Skills against official specifications with multi-dimensional scoring.
DigicationAnalyze session logs to evaluate skill performance and produce improvement reports.
aifuunyes
VYRE-StudiosReview Git changes for correctness, security, performance, and maintainability.
