agent-toolkit/skill-judge
CommunityAudit SKILL quality with expert scoring.
Software Engineering#markdown#token efficiency#spec compliance#yaml frontmatter#skill evaluation#anti-pattern detection#workflow usability
Authoredupazogle
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Skill Judge evaluates whether a skill package actually adds expert value or wastes tokens by duplicating knowledge that the model already has, while also checking structural compliance with the SKILL specification.
Core Features & Use Cases
- Multi-dimensional skill scoring (120 points): Assesses knowledge delta, procedures, anti-pattern quality, specification compliance, progressive disclosure, freedom calibration, pattern recognition, and practical usability.
- Actionable improvement guidance: Flags critical issues and provides prioritized fixes to make skills more usable and activation-ready.
- Knowledge delta classification: Categorizes sections into Expert / Activation / Redundant to pinpoint what to keep, refine, or remove.
Quick Start
Ask the Skill Judge to evaluate the target skill’s SKILL.md and produce a structured report with a grade and concrete improvement recommendations.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: agent-toolkit/skill-judge Download link: https://github.com/edupazogle/agentic_cockpit/archive/main.zip#agent-toolkit-skill-judge Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.