Claude Skill
Evol-ai/SkillCompass
SkillCompass is an open-source tool to evaluate agent skill quality, find the weakest link, fix it, and prove it worked. Supports Claude Code and OpenClaw skills.
Overview
Repository
Install this Skill
npx skills add Evol-ai/SkillCompassRegistry
npx skills add Evol-ai/SkillCompassgit clone https://github.com/Evol-ai/SkillCompass.git
Summary
SkillCompass is an open-source tool for evaluating and improving agent skill quality. It helps identify the weakest link in your skill set, fix it, and prove the improvement worked.
评估代理技能质量。找出最薄弱环节。修复它。证明其有效。
Key features
- Skill quality evaluation for AI agents
- Identify weakest skill links
- Track and prove improvement
- Supports Claude Code skills and OpenClaw skills
- Built with JavaScript for easy integration
Use cases
- Evaluate agent skill quality in production
- Debug and improve skill performance
- Benchmark skills before deployment
- Continuous skill improvement pipeline
README excerpt
<h1 align="center">SkillCompass</h1> <p align="center"> <strong>Evaluate quality. Find the weakest link. Fix it. Prove it worked. Repeat.</strong> </p> <p align="center"> <a href="https://github.com/Evol-ai/SkillCompass">GitHub</a> · <a href="SKILL.md">SKILL.md</a> · <a href="schemas/">Schemas</a> · <a href="CHANGELOG.md">Changelog</a> </p> <p align="center"> <a href="https://linux.do/"><img src="https://img.shields.io/badge/Community-LINUX%20DO-blue.svg" alt="LINUX DO Community" /></a> <img src="https://img.shields.io/badge/license-MIT-blue.svg" alt="MIT License" /> <img src="https://img.shields.io/badge/node-%3E%3D18-brightgreen.svg" alt="Node >= 18" /> <img src="https://img.shields.io/badge/model-Claude%20Opus%204.6%20%2F%204.7-purple.svg" alt="Claude Opus 4.6 / 4.7" /> </p> --- | | | |--|--| | **What it is** | A local-first skill quality evaluator and management tool for Claude Code / OpenClaw. Six-dimension scoring, usage-driven suggestions, guided improvement, version tracking. | | **Pain it solves** | Turns "tweak and hope" into diagnose → targeted fix → verified improvement. Turns "install and forget" into ongoing visibility over what's working, what's stale, and what's risky. | | **Use in 30 seconds** | `/skillcompass` — see your skill health at a glance. `/eval-skill {path}` — instant quality report showing exactly what's weakest and what to improve next. | > **Evaluate → find weakest link → fix it → prove it worked → next weakness → repeat.** > **Meanwhile, Skill Inbox watches your usage and tells you what needs attention.** --- ## Who This Is For <table> <tr><td width="50%"> **For** - Anyone maintaining agent skills and wanting measurable quality - Developers who want directed improvement — not guesswork, bu