/ ディレクトリ / プレイグラウンド / skill-optimizer
● コミュニティ hqhq1025 ⚡ 即起動

skill-optimizer

作者 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).

なぜ使うのか

主な機能

ライブデモ

実際の動作

skill-optimizer-skill.replay ▶ 準備完了
0/0

インストール

クライアントを選択

~/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 を開く。保存後、アプリを再起動。

~/.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
    }
  }
}

Cursor は Claude Desktop と同じ mcpServers スキーマを使用。プロジェクト設定はグローバルより優先。

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 サイドバーの MCP Servers アイコンをクリックし、"Edit Configuration" を選択。

~/.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 Desktop と同じ形式。Windsurf を再起動して反映。

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

Continue はマップではなくサーバーオブジェクトの配列を使用。

~/.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_servers に追加。保存時に Zed がホットリロード。

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

ワンライナー。claude mcp list で確認、claude mcp remove で削除。

ユースケース

実用的な使い方: skill-optimizer

How to diagnose and fix one underperforming skill

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

使うタイミング: You notice one skill never activates, or activates wrongly.

前提条件
  • 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
フロー
  1. Point it at the skill
    Analyze ~/.claude/skills/my-skill/SKILL.md using my last 2 weeks of session logs.✓ コピーしました
    → Static + runtime findings
  2. Review the patch
    Show me the proposed SKILL.md diff.✓ コピーしました
    → Minimal, reviewable diff
  3. Apply and validate
    Apply the patch and tell me what to watch for this week.✓ コピーしました
    → Validation checklist

結果: A targeted improvement with an accountability plan.

注意点
  • Optimizing for activation rate but breaking scope — Include a 'false positive rate' acceptance metric
組み合わせ: skillcompass-skill

Polish your first SKILL.md before publishing

👤 First-time skill authors ⏱ ~20 min beginner

使うタイミング: You wrote a SKILL.md and want expert review before shipping.

フロー
  1. Ask for a review
    Review my SKILL.md against skill-optimizer's static checks.✓ コピーしました
    → Checklist with pass/fail + rationale
  2. Fix issues
    Apply the fixes and show me the final version.✓ コピーしました
    → Clean SKILL.md

結果: A ship-ready SKILL.md.

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

組み合わせ

他のMCPと組み合わせて10倍の力を

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.✓ コピーしました
skill-optimizer-skill + filesystem

Apply SKILL.md patches directly

Apply the proposed diff to ~/.claude/skills/my-skill/SKILL.md.✓ コピーしました

ツール

このMCPが提供する機能

ツール入力呼び出すタイミングコスト
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

コストと制限

運用コスト

APIクォータ
none beyond LLM
呼び出しあたりのトークン
2–10k per skill analysis
金額
free
ヒント
Static analysis is nearly free; log analysis costs more — run it only when iterating

セキュリティ

権限、シークレット、影響範囲

認証情報の保管: none; logs may contain sensitive prompts — treat their path carefully
データ送信先: none

トラブルシューティング

よくあるエラーと対処法

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

代替案

skill-optimizer 他との比較

代替案代わりに使う場面トレードオフ
skillcompass-skillYou need bundle-level ranking, not single-skill depthBreadth over depth

その他

リソース

📖 GitHub の公式 README を読む

🐙 オープンな issue を見る

🔍 400以上のMCPサーバーとSkillsを見る