agent-skill-tdd MCP — Сценарии использования, Установка & Живое демо

Зачем использовать

Ключевые функции

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

Живое демо

Как выглядит на практике

agent-skill-tdd-skill.replay ▶ готово

0/0

Установка

Выберите клиент

~/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
    }
  }
}

Откройте Claude Desktop → Settings → Developer → Edit Config. Перезапустите после сохранения.

~/.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
    }
  }
}

Cursor использует ту же схему mcpServers, что и Claude Desktop. Конфиг проекта приоритетнее глобального.

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
    }
  }
}

Щёлкните значок MCP Servers на боковой панели Cline, затем "Edit Configuration".

~/.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
    }
  }
}

Тот же формат, что и Claude Desktop. Перезапустите Windsurf для применения.

~/.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"
      ]
    }
  ]
}

Continue использует массив объектов серверов, а не map.

~/.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"
        ]
      }
    }
  }
}

Добавьте в context_servers. Zed перезагружается автоматически.

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

Однострочная команда. Проверить: claude mcp list. Удалить: claude mcp remove.

Сценарии использования

Реальные сценарии: agent-skill-tdd

Implement a new feature with full TDD discipline

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

Когда использовать: Non-trivial feature where 'just write it' has burned you before.

Предварительные требования

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

Поток

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.✓ Скопировано

→ Claude reads code, summarizes current state
Clarify requirements

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

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

Run design review — architecture fit, hotspots.✓ Скопировано

→ Design critique, not just approval
TDD loop

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

→ Red-green-refactor cycles, each reviewed

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

Подводные камни

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

Сочетать с: 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

Когда использовать: A subtle bug where the reproduction is half the battle.

Поток

Investigate + document

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

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

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

→ Red test
Fix + peer review

Minimum fix to go green. Peer review.✓ Скопировано

→ Green + review notes

Итог: 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

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

Поток

Only run steps 1–4

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

→ Requirements doc + design review without touching code

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

Комбинации

Сочетайте с другими MCP — эффект x10

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.✓ Скопировано

agent-skill-tdd-skill + github

Link requirements doc in the PR description

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

Инструменты

Что предоставляет этот MCP

Инструмент	Входные данные	Когда вызывать	Стоимость
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

Стоимость и лимиты

Во что обходится

Квота API: None from the skill; Serena and Lad have their own footprints
Токенов на вызов: Moderate — each step is a round trip
Деньги: Free
Совет: Full 6-step is overkill for trivial tasks — run steps 1–4 only on small work

Безопасность

Права, секреты, радиус поражения

Хранение учётных данных: None

Исходящий трафик: Only via Serena/Lad if configured

Устранение неполадок

Частые ошибки и исправления

Serena not available

Install the Serena MCP server and register it with your agent

Requirements doc not created

Ensure filesystem write access to .requirements/

Проверить: ls .requirements/

Design review step feels rubber-stamp

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

Альтернативы

agent-skill-tdd в сравнении

Альтернатива	Когда использовать	Компромисс
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

Ещё

Ресурсы

📖 Читать официальный README на GitHub

🐙 Открытые задачи

🔍 Все 400+ MCP-серверов и Skills