skills.rest
karrtik159
karrtik159COMMUNITY
Explore all skills by this author →
GitHub

skill-judge

Evaluate Agent Skills on 8 quality dimensions and generate a detailed report.

1|Updated Mar 7, 2026
Search Tags:#quality assurance#best practices#ai skills#skill evaluation#skills development
One-click install
npx skills add https://github.com/karrtik159/ContextFlow --skill skill-judge-karrtik159
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-judge
Source: https://github.com/karrtik159/ContextFlow/tree/main/.agents/skills/skill-judge
Command: npx skills add https://github.com/karrtik159/ContextFlow --skill skill-judge-karrtik159

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill helps you assess and enhance the quality of Agent Skills against official specifications and best practices. It identifies areas for improvement and provides a comprehensive evaluation report.

Core Features & Use Cases

  • Multi-Dimensional Scoring: Evaluate Skills on eight dimensions for a thorough review.
  • Actionable Suggestions: Get specific recommendations for improving your Skills.
  • Comparison Analysis: Compare the quality of multiple Skills using consistent criteria.

Quick Start

Evaluate the quality of your skill at /skills/your-skill-path/SKILL.md.

Frequently Asked Questions about skill-judge

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

FAQPage Schema
How do I evaluate AI skills for specification compliance and best practices?▼

To evaluate AI skills for specification compliance, you can use an automated evaluation to score your skills across eight dimensions. This generates a detailed report with actionable advice to ensure content quality and adherence to official specifications.

What is multi-dimensional scoring in skill evaluation?▼

Multi-dimensional scoring in skill evaluation assesses content quality across eight specific dimensions, including knowledge delta, anti-patterns, and progressive disclosure. This mechanism provides a thorough review by measuring practical usability and pattern recognition.

How do I compare the quality of multiple AI skills using consistent criteria?▼

You can compare the quality of multiple AI skills by running an evaluation that applies consistent criteria across all targets. This comparison analysis scores each skill on the same eight dimensions to identify relative strengths and areas for improvement.

Do I need external dependencies to assess and improve my Agent Skills?▼

You do not need external dependencies to assess and improve your Agent Skills. The evaluation operates entirely without external requirements, using internal scripts and references to generate precise scoring and actionable suggestions.

What is the best way to get actionable suggestions for skill development?▼

The best way to get actionable suggestions for skill development is to run a comprehensive evaluation on your skill path. This process identifies specific areas for improvement and provides a detailed report based on best practices and specification compliance.

Related Skills

Explore More Product & Management Skills→
avibebuilderavibebuilder
113

skill-creator

Create testable Claude Code SKILL.md files with frontmatter and evaluation benchmarks.

Official
Advanced
thktthkt
11

formatting-audits

Audit SOW/Spec documents against a 100-point scoring framework.

Community
Advanced
WladimirfnWladimirfn

skill-check

Validate SKILL.md files against the agentskills specification and best practices.

Community
Advanced
viniruggeriviniruggeri

scholar-evaluation

Assess scholarly work across eight ScholarEval dimensions with scoring and feedback.

Community
Advanced