skills.rest
wpank
wpankCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

skill-judge

Evaluate AI skills across eight dimensions and score them out of 120.

11|4|Updated Feb 9, 2026
Search Tags:#skill development#best practices#auditing#ai quality#SKILL.md#skill evaluation
One-click install
npx skills add https://github.com/wpank/ai --skill skill-judge-wpank
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-judge
Source: https://github.com/wpank/ai/tree/main/skills/tools/skill-judge
Command: npx skills add https://github.com/wpank/ai --skill skill-judge-wpank

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill provides a rigorous, objective evaluation of AI skills, ensuring they meet high standards for quality, usefulness, and adherence to best practices. It helps identify weaknesses and guides improvements.

Core Features & Use Cases

  • Objective Scoring: Evaluates skills across 8 critical dimensions, totaling 120 points.
  • Actionable Feedback: Provides specific, data-driven suggestions for improvement.
  • Use Case: Before deploying a new AI skill, use this Skill to audit its SKILL.md file, ensuring it's well-defined, efficient, and aligned with ecosystem standards.

Quick Start

Use the skill-judge to evaluate the quality of the 'api-design' skill.

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 skill quality against best practices?▼

AI skill evaluation works by analyzing the SKILL.md file across eight dimensions including Knowledge Delta, Specification Compliance, and Practical Usability. It generates a 120-point score and actionable feedback to identify weaknesses and guide improvements.

When should I audit a SKILL.md file before deployment?▼

You should audit a SKILL.md file before deploying a new AI skill to ensure it is well-defined, efficient, and aligned with ecosystem standards. This process identifies anti-patterns and specification compliance issues before integration.

What dimensions are analyzed during an AI skill evaluation?▼

AI skill evaluation analyzes eight dimensions: Knowledge Delta, Mindset + Procedures, Anti-Pattern Quality, Specification Compliance, Progressive Disclosure, Freedom Calibration, Pattern Recognition, and Practical Usability. These dimensions total 120 points for objective scoring.

Does skill evaluation require specific dependencies or components?▼

Skill evaluation requires no external dependencies. It operates using internal scripts and references to analyze the SKILL.md specification, making it accessible for auditing AI quality without complex environment setup.

What is the best way to improve a skill's specification compliance?▼

The best way to improve specification compliance is to run an audit that provides actionable, data-driven suggestions targeting specific weaknesses. It scores the skill out of 120 points and highlights anti-pattern quality and progressive disclosure issues.

Related Skills

Explore More Software Engineering Skills→
prashsubprashsub
1

create-agent-skill

Creates new Agent Skills following the AgentSkills.io specification.

Community
Intermediate
opencodosopencodos
14

skill-judge

Evaluate AI skills across an 8-dimension rubric and return structured scores.

Official
Advanced
DifanaDAPDifanaDAP

hermes-agent-skill-authoring

Guide creation and validation of Hermes-Agent SKILL.md files.

Community
Intermediate
Shana-AEShana-AE
2

skill-judge

Assess SKILL.md design quality against a formal specification framework.

Community
Advanced