freemcplab / 디렉터리 / 플레이그라운드 / SkillCompass

● 커뮤니티 Evol-ai ⚡ 바로 사용

SkillCompass

Name: SkillCompass (Claude Skill)
Author: Evol-ai

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.

▶ 데모 보기 📦 설치 💡 사용 사례

왜 쓰나요

핵심 기능

Multi-dimensional skill scoring (clarity, activation, correctness, cost)
'Weakest link' identification across a bundle
Suggests concrete SKILL.md edits
Before/after eval harness
JavaScript tooling — runs locally

라이브 데모

실제 사용 모습

skillcompass-skill.replay ▶ 준비됨

0/0

설치

작성자 저장소 · Claude Skills 공식 문서

사용 사례

실전 활용법: SkillCompass

Find the skill pulling your agent's performance down

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

언제 쓸까: You feel the agent has gotten worse, not better, as you added skills.

흐름

Diagnose the loser

For the weakest skill, what specifically is wrong?✓ 복사됨

→ Concrete critique (vague description, conflicting with other skill, etc.)
Propose a fix

Suggest a minimal edit to SKILL.md to fix it.✓ 복사됨

→ Small, reviewable diff
Re-evaluate

Re-run the eval and show before/after.✓ 복사됨

→ Metrics improved, with evidence

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

함정

Gaming the eval metric instead of helping real tasks — Include task-level downstream metrics (actual agent outcomes), not just text-level

함께 쓰기: skill-optimizer-skill · filesystem

Review a new skill before you publish it

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

언제 쓸까: Before pushing to GitHub and telling the world about your skill.

흐름

Score the draft

Evaluate my draft skill at ./my-skill/.✓ 복사됨

→ Dimension scores
Fix obvious issues

Apply the low-hanging suggestions✓ 복사됨

→ Edits in SKILL.md

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

함정

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

조합

다른 MCP와 조합해 10배 효율

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.✓ 복사됨

skillcompass-skill + filesystem

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

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

도구

이 MCP가 노출하는 것

도구	입력	언제 호출	비용
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

비용 및 제한

운영 비용

API 쿼터: none beyond your LLM provider (evals use LLM calls)
호출당 토큰: evals can be heavy — budget 20–100k tokens for a full bundle scan
금액: free, MIT
팁: Run on one skill at a time during iteration; bundle runs only for audits

보안

권한, 시크릿, 파급범위

자격 증명 저장: none at skill level

데이터 외부 송신: none beyond your LLM provider

문제 해결

자주 발생하는 오류와 해결

Node errors on install

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

확인: node -v

Evals are inconsistent run-to-run

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

대안

SkillCompass 다른 것과 비교

대안	언제 쓰나	단점/장점
skill-optimizer-skill	You want a single skill analyzed deeply rather than a bundle ranked	Depth over breadth
manual review	You have 1–2 skills total	Doesn't scale