# Skill Judge

Evaluate Agent Skill design quality against official specifications and best practices.

- Repository: https://github.com/shareAI-lab/Kode-CLI (5235 stars)
- Category: Design
- License: Apache-2.0
- Last updated: 2026-10-29
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add shareAI-lab/Kode-CLI --skill skill-judge -g -a claude-code -y`
Codex: `npx skills add shareAI-lab/Kode-CLI --skill skill-judge -g -a codex -y`
Cursor: `npx skills add shareAI-lab/Kode-CLI --skill skill-judge -g -a cursor -y`
Gemini CLI: `npx skills add shareAI-lab/Kode-CLI --skill skill-judge -g -a gemini-cli -y`

## Description

Evaluate Agent Skill design quality against official specifications and best practices. Use when reviewing, auditing, or improving SKILL.md files and skill packages. Provides multi-dimensional scoring and actionable improvement suggestions.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Skill Judge

Evaluate Agent Skills against official specifications and patterns derived from 17+ official examples.

---

## Core Philosophy

### What is a Skill?

A Skill is NOT a tutorial. A Skill is a **knowledge externalization mechanism**.

Traditional AI knowledge is locked in model parameters. To teach new capabilities:
```
Traditional: Collect data → GPU cluster → Train → Deploy new version
Cost: $10,000 - $1,000,000+
Timeline: Weeks to months
```

Skills change this:
```
Skill: Edit SKILL.md → Save → Takes effect on next invocation
Cost: $0
Timeline: Instant
```

This is the paradigm shift from "training AI" to "educating AI", like a hot-swappable LoRA adapter that requires no training. You edit a Markdown file in natural language, and the model's behavior changes.

### The Core Formula

> **Good Skill = Expert-only Knowledge − What the Base Model Already Knows**

A Skill's value is measured by its **knowledge delta**, the gap between what it provides and what the model already knows.

- **Expert-only knowledge**: Decision trees, trade-offs, edge cases, anti-patterns, domain-specific thinking frameworks, things that take years of experience to accumulate
- **What the base model already knows**: Basic concepts, standard library usage, common programming patterns, general best practices

When a Skill explains "what is PDF" or "how to write a for-loop", it's compressing knowledge the base model already has. This is **token waste**, context window is a public resource shared with system prompts, conversation history, other Skills, and user requests.

### Tool vs Skill

| Concept | Essence | Function | Example |
|---------|---------|----------|---------|
| **Tool** | What model CAN do | Execute actions | bash, read_file, write_file, WebSearch |
| **Skill** | What model KNOWS how to do | Guide decisions | PDF processing, MCP building, frontend design |

The rest: https://github.com/shareAI-lab/Kode-CLI/blob/HEAD/packages/builtin-skills/skills/skill-judge/SKILL.md