agent-skill-tdd MCP — Anwendungsfälle, Installieren & Live-Demo

Warum nutzen

Hauptfunktionen

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

Live-Demo

In der Praxis

agent-skill-tdd-skill.replay ▶ bereit

0/0

Installieren

Wählen Sie Ihren Client

~/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
    }
  }
}

Öffne Claude Desktop → Settings → Developer → Edit Config. Nach dem Speichern neu starten.

~/.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 nutzt das gleiche mcpServers-Schema wie Claude Desktop. Projektkonfiguration schlägt die globale.

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
    }
  }
}

Klicken Sie auf das MCP-Servers-Symbol in der Cline-Seitenleiste, dann "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
    }
  }
}

Gleiche Struktur wie Claude Desktop. Windsurf neu starten zum Übernehmen.

~/.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 nutzt ein Array von Serverobjekten statt einer 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"
        ]
      }
    }
  }
}

In context_servers hinzufügen. Zed lädt beim Speichern neu.

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

Einzeiler. Prüfen mit claude mcp list. Entfernen mit claude mcp remove.

Anwendungsfälle

Praxisnahe Nutzung: agent-skill-tdd

Implement a new feature with full TDD discipline

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

Wann einsetzen: Non-trivial feature where 'just write it' has burned you before.

Voraussetzungen

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

Ablauf

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.✓ Kopiert

→ Claude reads code, summarizes current state
Clarify requirements

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

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

Run design review — architecture fit, hotspots.✓ Kopiert

→ Design critique, not just approval
TDD loop

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

→ Red-green-refactor cycles, each reviewed

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

Fallstricke

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

Kombinieren mit: 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

Wann einsetzen: A subtle bug where the reproduction is half the battle.

Ablauf

Investigate + document

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

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

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

→ Red test
Fix + peer review

Minimum fix to go green. Peer review.✓ Kopiert

→ Green + review notes

Ergebnis: 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

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

Ablauf

Only run steps 1–4

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

→ Requirements doc + design review without touching code

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

Kombinationen

Mit anderen MCPs für 10-fache Wirkung

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.✓ Kopiert

agent-skill-tdd-skill + github

Link requirements doc in the PR description

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

Werkzeuge

Was dieses MCP bereitstellt

Werkzeug	Eingaben	Wann aufrufen	Kosten
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

Kosten & Limits

Was der Betrieb kostet

API-Kontingent: None from the skill; Serena and Lad have their own footprints
Tokens pro Aufruf: Moderate — each step is a round trip
Kosten in €: Free
Tipp: Full 6-step is overkill for trivial tasks — run steps 1–4 only on small work

Sicherheit

Rechte, Secrets, Reichweite

Credential-Speicherung: None

Datenabfluss: Only via Serena/Lad if configured

Fehlerbehebung

Häufige Fehler und Lösungen

Serena not available

Install the Serena MCP server and register it with your agent

Requirements doc not created

Ensure filesystem write access to .requirements/

Prüfen: ls .requirements/

Design review step feels rubber-stamp

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

Alternativen

agent-skill-tdd vs. andere

Alternative	Wann stattdessen	Kompromiss
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

Mehr

Ressourcen

📖 Offizielle README auf GitHub lesen

🐙 Offene Issues ansehen

🔍 Alle 400+ MCP-Server und Skills durchsuchen