skills.rest
jjmartres
jjmartresCOMMUNITY
Explore all skills by this author →
GitHub

skill-judge

Evaluate Skill design quality against official specifications and best practices.

40|4|Updated Apr 19, 2026
Search Tags:#documentation#quality#pattern#skill#frontmatter#loading#evaluate
One-click install
npx skills add https://github.com/jjmartres/ai-coding-agents --skill skill-judge-jjmartres
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-judge
Source: https://github.com/jjmartres/ai-coding-agents/tree/main/shared/.ai-agents/skills/skill-judge
Command: npx skills add https://github.com/jjmartres/ai-coding-agents --skill skill-judge-jjmartres

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill evaluates Skill design quality against official specifications and best practices, helping maintain high-value, battle-tested SKILLs.

Core Features & Use Cases

  • Structured evaluation across knowledge delta, patterns, loading triggers, and usability.
  • Generates a detailed Scorecard and improvement recommendations for SKILL.md based units.
  • Useful for auditors, editors, and teams maintaining Skill libraries.

Quick Start

Run the Skill evaluation workflow to generate a structured report for the Skill under review.

Frequently Asked Questions about skill-judge

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I evaluate SKILL.md quality and frontmatter validity?▼

Evaluating SKILL.md quality involves scoring Skill design against official specifications and best practices, enforcing frontmatter validity, description quality, progressive disclosure, and anti-patterns to generate a detailed Scorecard with improvement recommendations.

What is structured Skill evaluation and how does it work?▼

Structured Skill evaluation assesses design quality across knowledge delta, patterns, loading triggers, and usability dimensions, producing a detailed Scorecard and actionable improvement recommendations for SKILL.md packages.

How do I audit a Skill library for loading practices and anti-patterns?▼

Auditing a Skill library for loading practices and anti-patterns involves scoring each SKILL.md package against official specifications, checking frontmatter validity, progressive disclosure, and structured evaluation dimensions to identify improvements.

Can I use this to review Skill documentation for progressive disclosure?▼

Yes, reviewing Skill documentation for progressive disclosure is supported by running the Skill evaluation workflow, which scores loading triggers and enforces progressive disclosure rules to generate a structured report for the Skill under review.

What's the best way to score Skill design quality against best practices?▼

Scoring Skill design quality against best practices is best achieved through structured evaluation across knowledge delta, patterns, loading triggers, and usability, generating a Scorecard with improvement recommendations for SKILL.md units.

Why does my Skill evaluation report show frontmatter validity errors?▼

Skill evaluation reports show frontmatter validity errors when SKILL.md metadata does not conform to official specifications, as the evaluation enforces frontmatter validity as a core structured evaluation dimension.

Related Skills

Explore More Design & Creative Skills→
Likas07Likas07

skill-judge

Evaluate AI Agent Skills against official specifications with multi-dimensional scoring.

Community
Advanced
pianzhupianzhu
1

skill-judge

Evaluates submitted ML models and returns structured JSON with predictions, confidence scores, and metadata.

Community
Advanced
AlphaLab-USTCAlphaLab-USTC
131

writing-skills

Create, edit, and verify SKILL.md documentation with RED-GREEN-REFACTOR validation.

Community
Advanced
ayehiaaayehiaa

code-maturity-assessor

Assess code maturity across nine Trail of Bits security categories.

Community
Advanced