/ 目录 / 演练场 / SkillCompass
← 全部服务器 ↗ GitHub
● 社区 Evol-ai ⚡ 即开即用

SkillCompass

作者 Evol-ai · Evol-ai/SkillCompass

Evaluate Agent Skill quality — find the weakest link, fix it, and prove the fix worked with before/after metrics.

SkillCompass scores your Agent Skills on clarity, activation rate, downstream correctness, and context cost. It highlights the skill most likely to be hurting your agent's performance, suggests a fix, and re-runs the evaluation so you can show the improvement. Useful when you have a shelf of skills and don't know which are actually earning their context weight.

▶ 观看演示 📦 安装 💡 使用场景

为什么要用

核心特性

实时演示

实际使用效果

skillcompass-skill.replay ▶ 就绪
0/0

安装

作者仓库 · Claude Skills 官方文档

使用场景

实战用法： SkillCompass

Find the skill pulling your agent's performance down

👤 Skill authors with 5+ skills installed ⏱ ~45 min advanced

何时使用： You feel the agent has gotten worse, not better, as you added skills.

步骤
  1. Diagnose the loser
    For the weakest skill, what specifically is wrong?✓ 已复制
    → Concrete critique (vague description, conflicting with other skill, etc.)
  2. Propose a fix
    Suggest a minimal edit to SKILL.md to fix it.✓ 已复制
    → Small, reviewable diff
  3. Re-evaluate
    Re-run the eval and show before/after.✓ 已复制
    → Metrics improved, with evidence

结果： A measurably better skill bundle, with a reproducible eval process.

注意事项
  • Gaming the eval metric instead of helping real tasks — Include task-level downstream metrics (actual agent outcomes), not just text-level
搭配使用： skill-optimizer-skill · filesystem

Review a new skill before you publish it

👤 Skill authors shipping their first bundle ⏱ ~20 min intermediate

何时使用： Before pushing to GitHub and telling the world about your skill.

步骤
  1. Score the draft
    Evaluate my draft skill at ./my-skill/.✓ 已复制
    → Dimension scores
  2. Fix obvious issues
    Apply the low-hanging suggestions✓ 已复制
    → Edits in SKILL.md

结果： A publication-ready skill rather than a rough draft.

注意事项
  • Chasing a perfect score — Ship when scores plateau — diminishing returns

组合

与其他 MCP 搭配，撬动十倍杠杆

skillcompass-skill + skill-optimizer-skill

Two complementary tools: SkillCompass ranks, skill-optimizer drills into SKILL.md patterns

Use SkillCompass to pick the worst skill; use skill-optimizer to deeply analyze its SKILL.md.✓ 已复制
skillcompass-skill + filesystem

Operate across the full ~/.claude/skills/ directory

Evaluate every skill in ~/.claude/skills/ and give me a CSV.✓ 已复制

工具

此 MCP 暴露的能力

工具输入参数何时调用成本
skill-scoring skill path(s) Periodic audits eval compute
weakest-link-id bundle scores After scoring 0
fix-suggestion weak skill + critique Before editing 0
before-after-eval pre/post SKILL.md After applying fixes eval compute

成本与限制

运行它的成本

API 配额
none beyond your LLM provider (evals use LLM calls)
每次调用 Token 数
evals can be heavy — budget 20–100k tokens for a full bundle scan
费用
free, MIT
提示
Run on one skill at a time during iteration; bundle runs only for audits

安全

权限、密钥、影响范围

凭据存储： none at skill level
数据出站： none beyond your LLM provider

故障排查

常见错误与修复

Node errors on install

Ensure Node 20+; npm i inside the skill directory.

验证： node -v
Evals are inconsistent run-to-run

Fix the task seed and use a non-stochastic sample; record provider+model.

替代方案

SkillCompass 对比其他方案

替代方案何时用它替代权衡
skill-optimizer-skillYou want a single skill analyzed deeply rather than a bundle rankedDepth over breadth
manual reviewYou have 1–2 skills totalDoesn't scale

更多

资源

📖 阅读 GitHub 上的官方 README

🐙 查看未解决的 issue

🔍 浏览全部 400+ MCP 服务器和 Skills