/ Directory / Playground / SkillCompass
← All servers ↗ GitHub
● Community Evol-ai ⚡ Instant

SkillCompass

by 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.

▶ Watch demo 📦 Install 💡 Use Cases

Why use it

Key features

Live Demo

What it looks like in practice

skillcompass-skill.replay ▶ ready
0/0

Install

Author repository · Claude Skills documentation

Use Cases

Real-world ways to use SkillCompass

Find the skill pulling your agent's performance down

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

When to use: You feel the agent has gotten worse, not better, as you added skills.

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

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

Pitfalls
  • Gaming the eval metric instead of helping real tasks — Include task-level downstream metrics (actual agent outcomes), not just text-level
Combine with: skill-optimizer-skill · filesystem

Review a new skill before you publish it

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

When to use: Before pushing to GitHub and telling the world about your skill.

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

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

Pitfalls
  • Chasing a perfect score — Ship when scores plateau — diminishing returns

Combinations

Pair with other MCPs for X10 leverage

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.✓ Copied
skillcompass-skill + filesystem

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

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

Tools

What this MCP exposes

ToolInputsWhen to callCost
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

Cost & Limits

What this costs to run

API quota
none beyond your LLM provider (evals use LLM calls)
Tokens per call
evals can be heavy — budget 20–100k tokens for a full bundle scan
Monetary
free, MIT
Tip
Run on one skill at a time during iteration; bundle runs only for audits

Security

Permissions, secrets, blast radius

Credential storage: none at skill level
Data egress: none beyond your LLM provider

Troubleshooting

Common errors and fixes

Node errors on install

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

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

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

Alternatives

SkillCompass vs others

AlternativeWhen to use it insteadTradeoff
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

More

Resources

📖 Read the official README on GitHub

🐙 Browse open issues

🔍 Browse all 400+ MCP servers and Skills

Continue exploring

Related tools and workflows

Choose another guide for your workflow, or explore a collection.

Shared context · evaluate

MLflow Agent Skills

Instrument, debug, and evaluate GenAI applications using MLflow’s tracing and evaluation skills.

Skill

Browse all topic collections → · See 29 new official additions →