Skill Judge

If you're building or reviewing Agent Skills, this gives you a scoring rubric based on 17+ official examples. It evaluates across dimensions like knowledge delta (does this teach Claude something it doesn't already know?), mindset transfer (does it share expert thinking patterns?), and anti-pattern quality (does it have specific NEVER lists?). The core insight is solid: a good skill is expert-only knowledge minus what Claude already knows, because context window is expensive. Useful for catching skills that waste tokens explaining basics like "what is a PDF" or generic advice like "write clean code". Treats skill design as knowledge engineering, not tutorial writing.

skills.sh installs: 4.3K
GitHub stars: 2.7K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add softaworks/agent-toolkit --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.