skills.rest
imMamdouhaboammar
imMamdouhaboammarCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

skill-judge

Evaluate SKILL.md files against official specifications and best practices.

Updated Jul 24, 2026
Search Tags:#optimization#audit#evaluation#quality-assurance#agent-development#skill-design
One-click install
npx skills add https://github.com/imMamdouhaboammar/kaku-chatgpt-harness --skill skill-judge-immamdouhaboammar
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-judge
Source: https://github.com/imMamdouhaboammar/kaku-chatgpt-harness/tree/main/.agents/skills/skill-judge
Command: npx skills add https://github.com/imMamdouhaboammar/kaku-chatgpt-harness --skill skill-judge-immamdouhaboammar

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill solves the problem of token waste and ineffective agent behavior by identifying redundant content and structural flaws in Skill definitions, ensuring your Skills provide genuine expert value rather than basic tutorials.

Core Features & Use Cases

  • Knowledge Delta Analysis: Categorizes content into Expert, Activation, and Redundant to maximize value-add.
  • Multi-dimensional Scoring: Evaluates Skills against 8 core dimensions including Specification Compliance, Progressive Disclosure, and Freedom Calibration.
  • Use Case: Use this Skill to audit a new internal tool definition before deployment to ensure it follows official design patterns and provides actionable, expert-level guidance to the Agent.

Quick Start

Evaluate the skill definition located at skills/my-new-skill/SKILL.md to receive a comprehensive quality report and improvement suggestions.

Frequently Asked Questions about skill-judge

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

FAQPage Schema
How do I audit an Agent Skill definition for specification compliance?▼

Auditing an Agent Skill definition involves evaluating its SKILL.md file and package structure against official specifications to identify structural flaws, measure knowledge density, and generate actionable improvement feedback.

What is knowledge delta analysis in agent development?▼

Knowledge delta analysis in agent development categorizes Skill content into Expert, Activation, and Redundant tiers to maximize value-add and eliminate basic tutorial-level token waste.

How do I evaluate Agent Skill quality using multi-dimensional scoring?▼

Evaluating Agent Skill quality requires scoring the definition across eight dimensions including specification compliance, progressive disclosure, and freedom calibration to ensure expert-level guidance.

Why does my Agent Skill cause token waste and ineffective behavior?▼

Agent Skills cause token waste and ineffective behavior when definitions contain redundant content and structural flaws, failing to provide genuine expert value rather than basic tutorial instructions.

Can I review a new internal tool definition before deployment using skill design patterns?▼

Yes, you can review a new internal tool definition before deployment to ensure it follows official design patterns and provides actionable, expert-level guidance to the Agent.

What's the best way to optimize a SKILL.md file for iterative improvement?▼

Optimizing a SKILL.md file for iterative improvement involves running pattern recognition against official specifications to generate a comprehensive quality report with actionable feedback.

Related Skills

Explore More Software Engineering Skills→
masa-codehubmasa-codehub

planning-specs

Analyze design docs and ADRs to create PR-ready specification plans.

Community
Advanced
irwinsirwins

skill-judge

Score SKILL.md files across eight dimensions and generate a structured evaluation report.

Community
Advanced
webreactiva-devswebreactiva-devs
4

skill-best-practices

Guide AI agent skill design, review, and improvement with best practices.

Official
Advanced
matchojeckimatchojecki
1

implement-spec

Coordinate subagents to implement phases of a target specification with code-review gating.

Community
Advanced