freemcplab / Annuaire / Playground / SkillCompass

● Communauté Evol-ai ⚡ Instantané

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.

▶ Voir la démo 📦 Installer 💡 Cas d'usage

Pourquoi l'utiliser

Fonctionnalités clés

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

Démo en direct

Aperçu en pratique

skillcompass-skill.replay ▶ prêt

0/0

Installation

Dépôt de l’auteur · Documentation officielle des Skills Claude

Cas d'usage

Usages concrets : SkillCompass

Find the skill pulling your agent's performance down

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

Quand l'utiliser : You feel the agent has gotten worse, not better, as you added skills.

Déroulement

Diagnose the loser

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

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

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

→ Small, reviewable diff
Re-evaluate

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

→ Metrics improved, with evidence

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

Pièges

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

Combiner avec : skill-optimizer-skill · filesystem

Review a new skill before you publish it

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

Quand l'utiliser : Before pushing to GitHub and telling the world about your skill.

Déroulement

Score the draft

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

→ Dimension scores
Fix obvious issues

Apply the low-hanging suggestions✓ Copié

→ Edits in SKILL.md

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

Pièges

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

Combinaisons

Associez-le à d'autres MCPs pour un effet X10

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.✓ Copié

skillcompass-skill + filesystem

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

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

Outils

Ce que ce MCP expose

Outil	Entrées	Quand appeler	Coût
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

Coût et limites

Coût d'exécution

Quota d'API: none beyond your LLM provider (evals use LLM calls)
Tokens par appel: evals can be heavy — budget 20–100k tokens for a full bundle scan
Monétaire: free, MIT
Astuce: Run on one skill at a time during iteration; bundle runs only for audits

Sécurité

Permissions, secrets, portée

Stockage des identifiants : none at skill level

Sortie de données : none beyond your LLM provider

Dépannage

Erreurs courantes et correctifs

Node errors on install

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

Vérifier : node -v

Evals are inconsistent run-to-run

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

Alternatives

SkillCompass vs autres

Alternative	Quand l'utiliser	Compromis
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

Plus

Ressources

📖 Lire le README officiel sur GitHub

🐙 Voir les issues ouvertes

🔍 Parcourir les 400+ serveurs MCP et Skills