freemcplab / Verzeichnis / Playground / skill-optimizer

● Community hqhq1025 ⚡ Sofort

skill-optimizer

Name: skill-optimizer (Claude Skill)
Author: hqhq1025

Audit a single SKILL.md using real session data plus static analysis — tells you exactly what to change.

skill-optimizer looks at a SKILL.md through two lenses: (1) session logs — did it activate when expected, was the output useful — and (2) static analysis — is the frontmatter clean, is the description properly intent-scoped, are examples calibrated. It outputs concrete edits you can apply. Pairs well with SkillCompass (which does bundle-level ranking).

▶ Demo ansehen 📦 Installieren 💡 Anwendungsfälle

Warum nutzen

Hauptfunktionen

Combines runtime evidence with static checks
Works on Claude Code, Codex, and any skill-compatible agent
Outputs a SKILL.md patch, not vague advice
Flags over-eager descriptions that cause mis-activation
Calls out duplicated capability across multiple skills

Live-Demo

In der Praxis

skill-optimizer-skill.replay ▶ bereit

0/0

Installation

Repository des Autors · Offizielle Dokumentation zu Claude Skills

Anwendungsfälle

Praxisnahe Nutzung: skill-optimizer

How to diagnose and fix one underperforming skill

👤 Skill authors iterating on a specific skill ⏱ ~30 min intermediate

Wann einsetzen: You notice one skill never activates, or activates wrongly.

Ablauf

Review the patch

Show me the proposed SKILL.md diff.✓ Kopiert

→ Minimal, reviewable diff
Apply and validate

Apply the patch and tell me what to watch for this week.✓ Kopiert

→ Validation checklist

Ergebnis: A targeted improvement with an accountability plan.

Fallstricke

Optimizing for activation rate but breaking scope — Include a 'false positive rate' acceptance metric

Kombinieren mit: skillcompass-skill

Polish your first SKILL.md before publishing

👤 First-time skill authors ⏱ ~20 min beginner

Wann einsetzen: You wrote a SKILL.md and want expert review before shipping.

Ablauf

Ask for a review

Review my SKILL.md against skill-optimizer's static checks.✓ Kopiert

→ Checklist with pass/fail + rationale
Fix issues

Apply the fixes and show me the final version.✓ Kopiert

→ Clean SKILL.md

Ergebnis: A ship-ready SKILL.md.

Fallstricke

Over-promising in the description — Be specific about what the skill does; Claude uses it to decide activation

Kombinationen

Mit anderen MCPs für 10-fache Wirkung

skill-optimizer-skill + skillcompass-skill

SkillCompass ranks the bundle; skill-optimizer dives into the worst offender

Use SkillCompass to pick the weakest skill, then optimize its SKILL.md.✓ Kopiert

skill-optimizer-skill + filesystem

Apply SKILL.md patches directly

Apply the proposed diff to ~/.claude/skills/my-skill/SKILL.md.✓ Kopiert

Werkzeuge

Was dieses MCP bereitstellt

Werkzeug	Eingaben	Wann aufrufen
static-analysis	SKILL.md path	Before publishing or during iteration
log-based-analysis	logs + skill path	Post-use tuning
patch-generation	findings	After analysis

Kosten & Limits

Was der Betrieb kostet

API-Kontingent: none beyond LLM
Tokens pro Aufruf: 2–10k per skill analysis
Kosten in €: free
Tipp: Static analysis is nearly free; log analysis costs more — run it only when iterating

Sicherheit

Rechte, Secrets, Reichweite

Credential-Speicherung: none; logs may contain sensitive prompts — treat their path carefully

Datenabfluss: none

Session logs can contain secrets — redact before sharing

Fehlerbehebung

Häufige Fehler und Lösungen

No logs found

Confirm Claude Code trace path; pass the path explicitly if non-default.

Suggestions conflict with intended scope

Tell the optimizer your scope constraints; it can respect non-goals

Alternativen

skill-optimizer vs. andere

Alternative	Wann stattdessen	Kompromiss
skillcompass-skill	You need bundle-level ranking, not single-skill depth	Breadth over depth

Mehr

Ressourcen

📖 Offizielle README auf GitHub lesen

🐙 Offene Issues ansehen

🔍 Alle 400+ MCP-Server und Skills durchsuchen