/ 디렉터리 / 플레이그라운드 / swing-skills
● 커뮤니티 TheStack-ai ⚡ 바로 사용

swing-skills

제작: 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.

왜 쓰나요

핵심 기능

라이브 데모

실제 사용 모습

swing-skill.replay ▶ 준비됨
0/0

설치

클라이언트 선택

~/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 열기. 저장 후 앱 재시작.

~/.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
    }
  }
}

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

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

~/.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 Desktop과 같은 형식. Windsurf 재시작 후 적용.

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

Continue는 맵이 아닌 서버 오브젝트 배열 사용.

~/.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_servers에 추가. 저장 시 Zed가 핫 리로드.

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

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

사용 사례

실전 활용법: 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

언제 쓸까: A stakeholder dropped a short, ambiguous request.

사전 조건
  • Skill installed — git clone https://github.com/TheStack-ai/swing-skills ~/.claude/skills/swing-skills
흐름
  1. Run swing-clarify
    Use swing-clarify. Request: 'make the dashboard better'. Decompose 5W1H.✓ 복사됨
    → What/who/when/where/why/how decomposition + clarifying questions

결과: A concrete scope you can actually execute against.

함께 쓰기: agent-skill-tdd-skill

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

👤 Analysts, researchers ⏱ ~45 min intermediate

언제 쓸까: You want a defensible brief, not hallucinated bullet points.

흐름
  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.✓ 복사됨
    → Claim table with tier + source

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

함정
  • B/C-tier claims treated as fact — The grade is there to weight; read them as weaker
함께 쓰기: firecrawl · brave-search

Break anchoring by generating five weighted alternatives

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

언제 쓸까: You've got a favorite solution and want a sanity check.

흐름
  1. Run swing-options
    Use swing-options. Decision: which DB for our new service? Give 5 probability-weighted options including unconventional.✓ 복사됨
    → 5 options with weights + rationale

결과: 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

언제 쓸까: Before committing to a plan or design.

흐름
  1. Run swing-review
    Use swing-review on design.md. Steel-man it first, then attack from correctness, operability, and cost.✓ 복사됨
    → Strong version of the design, then 3 attack surfaces

결과: 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

언제 쓸까: Right before kickoff on risky work.

흐름
  1. Run swing-mortem
    Use swing-mortem. Assume plan.md failed in 6 months. List 5 failure scenarios with leading indicators.✓ 복사됨
    → 5 scenarios + early-warning signals

결과: 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

언제 쓸까: A decision feels off but you can't articulate why.

흐름
  1. Run swing-trace
    Use swing-trace on this decision: 'we'll use Kafka'. Inventory assumptions; call out the weakest.✓ 복사됨
    → Assumption list ranked by risk

결과: The weakest link exposed before it breaks.

조합

다른 MCP와 조합해 10배 효율

swing-skill + skills-skill-6

Layer Swing's firewalls with InfraNodus graph analysis

After swing-review, run InfraNodus critical-perspective for graph-based critique.✓ 복사됨
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.✓ 복사됨

도구

이 MCP가 노출하는 것

도구입력언제 호출비용
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

비용 및 제한

운영 비용

API 쿼터
None
호출당 토큰
Moderate per skill (research is highest)
금액
Free
Use swing-clarify by default; others on-demand

보안

권한, 시크릿, 파급범위

자격 증명 저장: None
데이터 외부 송신: None beyond your LLM calls

문제 해결

자주 발생하는 오류와 해결

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?'

대안

swing-skills 다른 것과 비교

대안언제 쓰나단점/장점
InfraNodus skillsYou want graph-based thinking augmentationNo bias-specific firewalls
Manual reviewOne-off trivial decisionsNo structure

더 보기

리소스

📖 GitHub에서 공식 README 읽기

🐙 열린 이슈 보기

🔍 400+ MCP 서버 및 Skills 전체 보기