Context Engineering Kit (Claude Skill) — インストール & ライブデモ

なぜ使うのか

主な機能

Subagent-driven development pattern
Test-driven development with rigid red/green loops
Branch-finishing skill (review → cleanup → merge)
Context-window budget management
Multi-agent compatibility

ライブデモ

実際の動作

context-engineering-kit-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": {
    "context-engineering-kit-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/NeoLabHQ/context-engineering-kit",
        "~/.claude/skills/context-engineering-kit"
      ],
      "_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": {
    "context-engineering-kit-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/NeoLabHQ/context-engineering-kit",
        "~/.claude/skills/context-engineering-kit"
      ],
      "_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": {
    "context-engineering-kit-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/NeoLabHQ/context-engineering-kit",
        "~/.claude/skills/context-engineering-kit"
      ],
      "_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": {
    "context-engineering-kit-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/NeoLabHQ/context-engineering-kit",
        "~/.claude/skills/context-engineering-kit"
      ],
      "_inferred": true
    }
  }
}

Claude Desktop と同じ形式。Windsurf を再起動して反映。

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "context-engineering-kit-skill",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/NeoLabHQ/context-engineering-kit",
        "~/.claude/skills/context-engineering-kit"
      ]
    }
  ]
}

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": {
    "context-engineering-kit-skill": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/NeoLabHQ/context-engineering-kit",
          "~/.claude/skills/context-engineering-kit"
        ]
      }
    }
  }
}

context_servers に追加。保存時に Zed がホットリロード。

claude mcp add context-engineering-kit-skill -- git clone https://github.com/NeoLabHQ/context-engineering-kit ~/.claude/skills/context-engineering-kit

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： Context Engineering Kit

Keep a multi-hour coding session from blowing the context window

👤 Engineers on long agent sessions ⏱ ~15 min intermediate

使うタイミング： You're 3 hours into a coding loop and the model is starting to drop context.

前提条件

Server/skill installed and authenticated — See repo README

フロー

Checkpoint

Use the context-engineering skill's 'checkpoint' to summarize what we've done into a tight handoff doc.✓ コピーしました

→ A handoff doc Claude can re-read instead of full history
Resume

Compact the conversation and resume from the handoff doc.✓ コピーしました

→ Session continues with fresh context

結果： Sessions that don't degrade as they grow.

注意点

Checkpointing too often loses fine-grained context. The kit suggests every ~30 turns or before any /compact. — Checkpointing too often loses fine-grained context. The kit suggests every ~30 turns or before any /compact.

コストと制限

運用コスト

APIクォータ: See provider docs for rate limits
呼び出しあたりのトークン: Varies by tool
金額: See repo README for pricing details
ヒント: Cache tool results and avoid repeated identical calls.

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： Use environment variables; never commit secrets

データ送信先： Tool calls go to the provider's API as documented

トラブルシューティング

よくあるエラーと対処法

checkpoint doc too long

Tune the skill's max-length; default is ~1500 tokens. Anything bigger and the doc itself eats context.

確認： wc -w on the checkpoint

subagent doesn't have enough context

The skill's spawn template requires a 'mission' block — fill it explicitly, don't let it default.

確認： Read the spawn doc the skill produces

代替案

Context Engineering Kit 他との比較

代替案	代わりに使う場面	トレードオフ
obra/superpowers	You want a broader skill library	Different opinions on workflow

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