/ ディレクトリ / プレイグラウンド / swing-skills
● コミュニティ TheStack-ai ⚡ 即起動

swing-skills

作者 TheStack-ai · TheStack-ai/swing-skills

6 cognitive firewalls for AI agents — clarify, research, options, review, trace, mortem — each targeting a named bias: premature closure, hallucination, anchoring, confirmation, black-box reasoning, optimism.

A skill pack of 6 self-contained cognitive tools that plug specific biases. swing-clarify forces 5W1H on ambiguous requests. swing-research runs a 4-stage verified pipeline with S/A/B/C source grading. swing-options generates 5 probability-weighted alternatives including unconventional ones. swing-review does structured devil's advocacy (steel-man first, then 3-vector attack). swing-trace inventories assumptions and surfaces weakest links. swing-mortem does prospective failure analysis.

なぜ使うのか

主な機能

ライブデモ

実際の動作

swing-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": {
    "swing-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/TheStack-ai/swing-skills",
        "~/.claude/skills/swing-skills"
      ],
      "_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": {
    "swing-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/TheStack-ai/swing-skills",
        "~/.claude/skills/swing-skills"
      ],
      "_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": {
    "swing-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/TheStack-ai/swing-skills",
        "~/.claude/skills/swing-skills"
      ],
      "_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": {
    "swing-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/TheStack-ai/swing-skills",
        "~/.claude/skills/swing-skills"
      ],
      "_inferred": true
    }
  }
}

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

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

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": {
    "swing-skill": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/TheStack-ai/swing-skills",
          "~/.claude/skills/swing-skills"
        ]
      }
    }
  }
}

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

claude mcp add swing-skill -- git clone https://github.com/TheStack-ai/swing-skills ~/.claude/skills/swing-skills

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: swing-skills

Force clarification before an ambiguous task is executed

👤 Anyone who's seen AI agents gallop off in the wrong direction ⏱ ~10 min beginner

使うタイミング: A stakeholder dropped a short, ambiguous request.

前提条件
  • Skill installed — git clone https://github.com/TheStack-ai/swing-skills ~/.claude/skills/swing-skills
フロー
  1. Run swing-clarify
    Use swing-clarify. Request: 'make the dashboard better'. Decompose 5W1H.✓ コピーしました
    → What/who/when/where/why/how decomposition + clarifying questions

結果: A concrete scope you can actually execute against.

組み合わせ: agent-skill-tdd-skill

Research a topic with graded sources, not a wall of links

👤 Analysts, researchers ⏱ ~45 min intermediate

使うタイミング: You want a defensible brief, not hallucinated bullet points.

フロー
  1. Run swing-research
    Use swing-research. Question: 'what's the state of Rust in web backends (2025)?' Output claims with S/A/B/C grades.✓ コピーしました
    → Claim table with tier + source

結果: A brief you could defend to a skeptical stakeholder.

注意点
  • B/C-tier claims treated as fact — The grade is there to weight; read them as weaker
組み合わせ: firecrawl · brave-search

Break anchoring by generating five weighted alternatives

👤 Decision-makers who notice they're anchoring ⏱ ~20 min beginner

使うタイミング: You've got a favorite solution and want a sanity check.

フロー
  1. Run swing-options
    Use swing-options. Decision: which DB for our new service? Give 5 probability-weighted options including unconventional.✓ コピーしました
    → 5 options with weights + rationale

結果: A decision made from options, not one default.

Structured review: steel-man then attack from 3 vectors

👤 Teams wanting a real review, not rubber-stamps ⏱ ~30 min intermediate

使うタイミング: Before committing to a plan or design.

フロー
  1. Run swing-review
    Use swing-review on design.md. Steel-man it first, then attack from correctness, operability, and cost.✓ コピーしました
    → Strong version of the design, then 3 attack surfaces

結果: A design that either holds or gets better.

Run a pre-mortem on a plan before execution

👤 PMs and leads about to green-light something important ⏱ ~30 min intermediate

使うタイミング: Right before kickoff on risky work.

フロー
  1. Run swing-mortem
    Use swing-mortem. Assume plan.md failed in 6 months. List 5 failure scenarios with leading indicators.✓ コピーしました
    → 5 scenarios + early-warning signals

結果: Early-warning instrumentation built in from day one.

Expose the weakest assumption in a decision tree

👤 Engineers debugging reasoning, not just code ⏱ ~20 min intermediate

使うタイミング: A decision feels off but you can't articulate why.

フロー
  1. Run swing-trace
    Use swing-trace on this decision: 'we'll use Kafka'. Inventory assumptions; call out the weakest.✓ コピーしました
    → Assumption list ranked by risk

結果: The weakest link exposed before it breaks.

組み合わせ

他のMCPと組み合わせて10倍の力を

swing-skill + skills-skill-6

Layer Swing's firewalls with InfraNodus graph analysis

After swing-review, run InfraNodus critical-perspective for graph-based critique.✓ コピーしました
swing-skill + agent-skill-tdd-skill

Clarify + research before the TDD flow

Start with swing-clarify + swing-research, then hand off to agent-skill-tdd.✓ 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
swing-clarify ambiguous request Any vague task 0
swing-research question Research with defensibility 0
swing-options decision Anchoring risk 0
swing-review plan/design Pre-commit review 0
swing-trace decision Reasoning audit 0
swing-mortem plan Before kickoff 0

コストと制限

運用コスト

APIクォータ
None
呼び出しあたりのトークン
Moderate per skill (research is highest)
金額
Free
ヒント
Use swing-clarify by default; others on-demand

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
データ送信先: None beyond your LLM calls

トラブルシューティング

よくあるエラーと対処法

swing-research cites sources that don't check out

Cross-check S-tier sources manually; lower grades are weaker by design

swing-review feels like a formality

Force adversarial framing: 'what would an angry senior engineer say?'

代替案

swing-skills 他との比較

代替案代わりに使う場面トレードオフ
InfraNodus skillsYou want graph-based thinking augmentationNo bias-specific firewalls
Manual reviewOne-off trivial decisionsNo structure

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