/ 디렉터리 / 플레이그라운드 / skill-optimizer
● 커뮤니티 hqhq1025 ⚡ 바로 사용

skill-optimizer

제작: hqhq1025 · hqhq1025/skill-optimizer

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).

왜 쓰나요

핵심 기능

라이브 데모

실제 사용 모습

skill-optimizer-skill.replay ▶ 준비됨
0/0

설치

클라이언트 선택

~/Library/Application Support/Claude/claude_desktop_config.json  · Windows: %APPDATA%\Claude\claude_desktop_config.json
{
  "mcpServers": {
    "skill-optimizer-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/hqhq1025/skill-optimizer",
        "~/.claude/skills/skill-optimizer"
      ],
      "_inferred": true
    }
  }
}

Claude Desktop → Settings → Developer → Edit Config 열기. 저장 후 앱 재시작.

~/.cursor/mcp.json · .cursor/mcp.json
{
  "mcpServers": {
    "skill-optimizer-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/hqhq1025/skill-optimizer",
        "~/.claude/skills/skill-optimizer"
      ],
      "_inferred": true
    }
  }
}

Cursor는 Claude Desktop과 동일한 mcpServers 스키마 사용. 프로젝트 설정이 전역보다 우선.

VS Code → Cline → MCP Servers → Edit
{
  "mcpServers": {
    "skill-optimizer-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/hqhq1025/skill-optimizer",
        "~/.claude/skills/skill-optimizer"
      ],
      "_inferred": true
    }
  }
}

Cline 사이드바의 MCP Servers 아이콘 클릭 후 "Edit Configuration" 선택.

~/.codeium/windsurf/mcp_config.json
{
  "mcpServers": {
    "skill-optimizer-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/hqhq1025/skill-optimizer",
        "~/.claude/skills/skill-optimizer"
      ],
      "_inferred": true
    }
  }
}

Claude Desktop과 같은 형식. Windsurf 재시작 후 적용.

~/.continue/config.json
{
  "mcpServers": [
    {
      "name": "skill-optimizer-skill",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/hqhq1025/skill-optimizer",
        "~/.claude/skills/skill-optimizer"
      ]
    }
  ]
}

Continue는 맵이 아닌 서버 오브젝트 배열 사용.

~/.config/zed/settings.json
{
  "context_servers": {
    "skill-optimizer-skill": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/hqhq1025/skill-optimizer",
          "~/.claude/skills/skill-optimizer"
        ]
      }
    }
  }
}

context_servers에 추가. 저장 시 Zed가 핫 리로드.

claude mcp add skill-optimizer-skill -- git clone https://github.com/hqhq1025/skill-optimizer ~/.claude/skills/skill-optimizer

한 줄 명령. claude mcp list로 확인, claude mcp remove로 제거.

사용 사례

실전 활용법: skill-optimizer

How to diagnose and fix one underperforming skill

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

언제 쓸까: You notice one skill never activates, or activates wrongly.

사전 조건
  • Session logs or transcripts — Claude Code stores traces locally; skill-optimizer reads them
  • Skill cloned — git clone https://github.com/hqhq1025/skill-optimizer ~/.claude/skills/skill-optimizer
흐름
  1. Point it at the skill
    Analyze ~/.claude/skills/my-skill/SKILL.md using my last 2 weeks of session logs.✓ 복사됨
    → Static + runtime findings
  2. Review the patch
    Show me the proposed SKILL.md diff.✓ 복사됨
    → Minimal, reviewable diff
  3. Apply and validate
    Apply the patch and tell me what to watch for this week.✓ 복사됨
    → Validation checklist

결과: A targeted improvement with an accountability plan.

함정
  • Optimizing for activation rate but breaking scope — Include a 'false positive rate' acceptance metric
함께 쓰기: skillcompass-skill

Polish your first SKILL.md before publishing

👤 First-time skill authors ⏱ ~20 min beginner

언제 쓸까: You wrote a SKILL.md and want expert review before shipping.

흐름
  1. Ask for a review
    Review my SKILL.md against skill-optimizer's static checks.✓ 복사됨
    → Checklist with pass/fail + rationale
  2. Fix issues
    Apply the fixes and show me the final version.✓ 복사됨
    → Clean SKILL.md

결과: A ship-ready SKILL.md.

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

조합

다른 MCP와 조합해 10배 효율

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.✓ 복사됨
skill-optimizer-skill + filesystem

Apply SKILL.md patches directly

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

도구

이 MCP가 노출하는 것

도구입력언제 호출비용
static-analysis SKILL.md path Before publishing or during iteration 0
log-based-analysis logs + skill path Post-use tuning 0
patch-generation findings After analysis 0

비용 및 제한

운영 비용

API 쿼터
none beyond LLM
호출당 토큰
2–10k per skill analysis
금액
free
Static analysis is nearly free; log analysis costs more — run it only when iterating

보안

권한, 시크릿, 파급범위

자격 증명 저장: none; logs may contain sensitive prompts — treat their path carefully
데이터 외부 송신: none

문제 해결

자주 발생하는 오류와 해결

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

대안

skill-optimizer 다른 것과 비교

대안언제 쓰나단점/장점
skillcompass-skillYou need bundle-level ranking, not single-skill depthBreadth over depth

더 보기

리소스

📖 GitHub에서 공식 README 읽기

🐙 열린 이슈 보기

🔍 400+ MCP 서버 및 Skills 전체 보기