Evaluate AI Agent Skills against official specifications with multi-dimensional scoring.
npx skills add https://github.com/Likas07/t3code-skills --skill skill-judge-likas07
Please help me install this Agent Skill. Skill: skill-judge Source: https://github.com/Likas07/t3code-skills/tree/main/skills/skill-judge Command: npx skills add https://github.com/Likas07/t3code-skills --skill skill-judge-likas07
This Skill provides a rigorous, multi-dimensional framework for evaluating the quality, effectiveness, and adherence to best practices of AI Agent Skills, ensuring they deliver maximum value and efficiency.
Evaluate the quality of the 'skill-judge' Skill using the provided SKILL.md file.
High-intent search queries and answers about installing and using this skill.
Evaluating AI agent skills involves scoring their design against official specifications and best practices across 8 dimensions. This process identifies token waste and ensures descriptions are optimized for agent activation, providing actionable improvement suggestions.
Auditing a SKILL.md file requires applying a defined evaluation protocol and scoring rubric. This objective assessment scores critical dimensions like Knowledge Delta and Anti-Patterns, totaling 120 points, to ensure maximum value and efficiency.
Yes, you can review entire skill packages by applying a multi-dimensional scoring framework. This approach objectively assesses complex tasks like code generation skills, identifying potential issues and verifying adherence to defined quality assurance protocols.
Skill evaluation identifies potential token waste by assessing the design quality and effectiveness of AI agent skills. The objective scoring highlights specific areas for improvement, ensuring the skill description is optimized for efficient agent activation.
Reviewing AI agent skills assigns scores across 8 critical dimensions, including Knowledge Delta, Mindset, and Anti-Patterns, totaling 120 points. This multi-dimensional framework ensures skills deliver maximum value and adhere to best practices.
m2ai-portfolioGenerate evaluation criteria and rubrics for knowledge-work outputs.
lhohanEvaluate Claude Code skills across eight dimensions and generate improvement reports.
devCharuzuDesign prompts and evaluation frameworks for LLM workflows.
ariesanhthuAnalyze complex software engineering problems with expert second opinions.
