Skill Judge

This evaluates your SKILL.md files against official specs and patterns from 17+ reference examples. It scores across dimensions like knowledge delta (does this add expert-only knowledge or just explain what Claude already knows?), thinking patterns versus generic procedures, and anti-pattern quality. The philosophy here is sharp: skills are knowledge externalization, not tutorials, and your job is maximizing expert content while ruthlessly cutting redundancy. Use it when you're writing or reviewing skills and want structured feedback on whether you're actually adding value or just burning tokens on basics. It's opinionated about the difference between educating an AI and wasting context window.

skills.sh installs: 310
GitHub stars: 33.2K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add davila7/claude-code-templates --skill skill-judge --agent claude-code

Installs into .claude/skills of the current project.

Files

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.