agent-skill-tdd MCP — 사용 사례, 설치 & 라이브 데모

왜 쓰나요

핵심 기능

6-step workflow: Serena -> Investigate -> Clarify -> Document -> Design Review -> TDD
Timestamped .requirements/ docs per task
Explicit requirements confirmation before code
Architecture review via Lad MCP before implementation
Per-change peer review on every edit
Agent-agnostic — Claude Code, Codex, Cursor, Windsurf, Antigravity

라이브 데모

실제 사용 모습

agent-skill-tdd-skill.replay ▶ 준비됨

0/0

설치

클라이언트 선택

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "agent-skill-tdd-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/Shelpuk-AI-Technology-Consulting/agent-skill-tdd",
        "~/.claude/skills/agent-skill-tdd"
      ],
      "_inferred": true
    }
  }
}

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

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "agent-skill-tdd-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/Shelpuk-AI-Technology-Consulting/agent-skill-tdd",
        "~/.claude/skills/agent-skill-tdd"
      ],
      "_inferred": true
    }
  }
}

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

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "agent-skill-tdd-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/Shelpuk-AI-Technology-Consulting/agent-skill-tdd",
        "~/.claude/skills/agent-skill-tdd"
      ],
      "_inferred": true
    }
  }
}

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

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "agent-skill-tdd-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/Shelpuk-AI-Technology-Consulting/agent-skill-tdd",
        "~/.claude/skills/agent-skill-tdd"
      ],
      "_inferred": true
    }
  }
}

Claude Desktop과 같은 형식. Windsurf 재시작 후 적용.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "agent-skill-tdd-skill",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/Shelpuk-AI-Technology-Consulting/agent-skill-tdd",
        "~/.claude/skills/agent-skill-tdd"
      ]
    }
  ]
}

Continue는 맵이 아닌 서버 오브젝트 배열 사용.

~/.config/zed/settings.json

{
  "context_servers": {
    "agent-skill-tdd-skill": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/Shelpuk-AI-Technology-Consulting/agent-skill-tdd",
          "~/.claude/skills/agent-skill-tdd"
        ]
      }
    }
  }
}

context_servers에 추가. 저장 시 Zed가 핫 리로드.

claude mcp add agent-skill-tdd-skill -- git clone https://github.com/Shelpuk-AI-Technology-Consulting/agent-skill-tdd ~/.claude/skills/agent-skill-tdd

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

사용 사례

실전 활용법: agent-skill-tdd

Implement a new feature with full TDD discipline

👤 Teams where AI coders jump to implementation and miss requirements ⏱ ~120 min intermediate

언제 쓸까: Non-trivial feature where 'just write it' has burned you before.

사전 조건

Skill cloned — git clone https://github.com/Shelpuk-AI-Technology-Consulting/agent-skill-tdd ~/.claude/skills/agent-skill-tdd
Serena available — Install Serena MCP server
Lad MCP for design review — Install Lad MCP server

흐름

Kick off with the skill

Use agent-skill-tdd. I want to add a 'saved searches' feature. Start from step 1 — activate Serena and investigate.✓ 복사됨

→ Claude reads code, summarizes current state
Clarify requirements

Confirm what I just said maps to these acceptance criteria — don't code yet.✓ 복사됨

→ Back-and-forth until confirmed; .requirements/ file saved
Design review via Lad

Run design review — architecture fit, hotspots.✓ 복사됨

→ Design critique, not just approval
TDD loop

Now begin TDD — write a failing test, minimum code to pass, refactor. Peer review each step.✓ 복사됨

→ Red-green-refactor cycles, each reviewed

결과: Feature shipped with tests, requirements history, and design rationale preserved.

함정

Skipping clarify to 'save time' — That's where most AI coding value is lost — hold the line

함께 쓰기: filesystem · github

Fix a bug after writing down what correct behavior should be

👤 Devs tired of AI 'fixes' that break other paths ⏱ ~60 min intermediate

언제 쓸까: A subtle bug where the reproduction is half the battle.

흐름

Investigate + document

Use agent-skill-tdd bug mode. Symptom: <description>. Write the reproduction + expected behavior to .requirements/ first.✓ 복사됨

→ Timestamped doc with As-Is and To-Be
Write failing test

Test that expresses the expected behavior — currently failing.✓ 복사됨

→ Red test
Fix + peer review

Minimum fix to go green. Peer review.✓ 복사됨

→ Green + review notes

결과: A bug fix with a test preventing regression.

Stop before implementing — validate you understand the spec

👤 Teams where spec-misreading causes rework ⏱ ~30 min beginner

언제 쓸까: The ticket is ambiguous and you suspect you're about to build the wrong thing.

흐름

Only run steps 1–4

Use agent-skill-tdd — investigate + clarify + document + design review. Stop before coding.✓ 복사됨

→ Requirements doc + design review without touching code

결과: You either discover you misread the ticket or greenlight with confidence.

조합

다른 MCP와 조합해 10배 효율

agent-skill-tdd-skill + filesystem

Keep .requirements/ in the repo for future agents to read

Commit .requirements/ to git so the next session has context.✓ 복사됨

agent-skill-tdd-skill + github

Link requirements doc in the PR description

When opening the PR, paste the .requirements/ file path in the description.✓ 복사됨

도구

이 MCP가 노출하는 것

도구	입력	언제 호출	비용
activate_serena	repo path	Step 1	0 — local
investigate	task description	Step 2	0
clarify	task, user answers	Step 3	0
document_requirements	confirmed requirements	Step 4	0
design_review	requirements + repo	Step 5	0
tdd_cycle	requirements	Step 6	0

비용 및 제한

운영 비용

API 쿼터: None from the skill; Serena and Lad have their own footprints
호출당 토큰: Moderate — each step is a round trip
금액: Free
팁: Full 6-step is overkill for trivial tasks — run steps 1–4 only on small work

보안

권한, 시크릿, 파급범위

자격 증명 저장: None

데이터 외부 송신: Only via Serena/Lad if configured

문제 해결

자주 발생하는 오류와 해결

Serena not available

Install the Serena MCP server and register it with your agent

Requirements doc not created

Ensure filesystem write access to .requirements/

확인: ls .requirements/

Design review step feels rubber-stamp

Force an adversarial framing: 'what's the strongest objection to this design?'

대안

agent-skill-tdd 다른 것과 비교

대안	언제 쓰나	단점/장점
claude-gpt-workflow	You want cross-model review instead of self-TDD discipline	Higher API cost
planning-with-files-skill	You want persistence across sessions but less TDD rigor	No test-first enforcement

agent-skill-tdd