Evaluate AI skills across an 8-dimension rubric and return structured scores.
npx skills add https://github.com/opencodos/opencodos --skill skill-judge-opencodos
Please help me install this Agent Skill. Skill: skill-judge Source: https://github.com/opencodos/opencodos/tree/main/skills/Skill%20Judge Command: npx skills add https://github.com/opencodos/opencodos --skill skill-judge-opencodos
This skill helps teams measure and improve the quality of AI agent skills by applying a structured evaluation rubric.
Evaluate a target skill using the 8-dimension rubric and return a structured assessment.
High-intent search queries and answers about installing and using this skill.
An AI skill evaluation rubric is used to identify and quantify AI skill quality across eight dimensions, surfacing expert knowledge gaps. It provides structured scores and concrete recommendations to improve existing skills during review sessions.
To evaluate AI agent skills, apply a strict eight-dimension rubric covering specification compliance, anti-patterns, and practical usability. This returns a structured assessment with graded scores, strengths, gaps, and an improvement plan.
A decision framework for reviewing AI skills should assess knowledge delta, mindset, anti-patterns, specification compliance, progressive disclosure, freedom calibration, pattern recognition, and practical usability to ensure comprehensive quality measurement.
Yes, you can use a quality assessment rubric to find expert knowledge gaps in product management skills. It identifies gaps across dimensions like mindset and pattern recognition, returning concrete recommendations to strengthen the skill.
To get actionable feedback for improving an existing AI skill, run it through an eight-dimension evaluation rubric. The process delivers concrete recommendations to address gaps and strengthen the skill for future use cycles.
yu13130122297Identify uncertainties in research framing, datasets, metrics, and baselines.
base44Validate skill directories against the Agent Skills specification.
williamzujkowskiScore code, documentation, or proposals across multiple quality dimensions.
daidongScore scholarly works across eight dimensions using a standardized rubric.
