freemcplab / Diretório / Playground / skill-optimizer

● Comunidade hqhq1025 ⚡ Instantâneo

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).

▶ Ver demo 📦 Instalar 💡 Casos de uso

Por que usar

Principais recursos

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

Demo ao vivo

Como fica na prática

skill-optimizer-skill.replay ▶ pronto

0/0

Instalação

Repositório do autor · Documentação oficial de Skills do Claude

Casos de uso

Usos do mundo real: skill-optimizer

How to diagnose and fix one underperforming skill

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

Quando usar: You notice one skill never activates, or activates wrongly.

Fluxo

Review the patch

Show me the proposed SKILL.md diff.✓ Copiado

→ Minimal, reviewable diff
Apply and validate

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

→ Validation checklist

Resultado: A targeted improvement with an accountability plan.

Armadilhas

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

Combine com: skillcompass-skill

Polish your first SKILL.md before publishing

👤 First-time skill authors ⏱ ~20 min beginner

Quando usar: You wrote a SKILL.md and want expert review before shipping.

Fluxo

Ask for a review

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

→ Checklist with pass/fail + rationale
Fix issues

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

→ Clean SKILL.md

Resultado: A ship-ready SKILL.md.

Armadilhas

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

Combinações

Combine com outros MCPs para 10× de alavancagem

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.✓ Copiado

skill-optimizer-skill + filesystem

Apply SKILL.md patches directly

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

Ferramentas

O que este MCP expõe

Ferramenta	Entradas	Quando chamar
static-analysis	SKILL.md path	Before publishing or during iteration
log-based-analysis	logs + skill path	Post-use tuning
patch-generation	findings	After analysis

Custo e limites

O que custa rodar

Cota de API: none beyond LLM
Tokens por chamada: 2–10k per skill analysis
Monetário: free
Dica: Static analysis is nearly free; log analysis costs more — run it only when iterating

Segurança

Permissões, segredos, alcance

Armazenamento de credenciais: none; logs may contain sensitive prompts — treat their path carefully

Saída de dados: none

Session logs can contain secrets — redact before sharing

Solução de problemas

Erros comuns e correções

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

Alternativas

skill-optimizer vs. outros

Alternativa	Quando usar	Troca
skillcompass-skill	You need bundle-level ranking, not single-skill depth	Breadth over depth

Mais

Recursos

📖 Leia o README oficial no GitHub

🐙 Ver issues abertas

🔍 Ver todos os 400+ servidores MCP e Skills