agent-skill-tdd MCP — Cas d'usage, Installer & Démo en direct

Pourquoi l'utiliser

Fonctionnalités clés

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

Démo en direct

Aperçu en pratique

agent-skill-tdd-skill.replay ▶ prêt

0/0

Installer

Choisissez votre 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
    }
  }
}

Ouvrez Claude Desktop → Settings → Developer → Edit Config. Redémarrez après avoir enregistré.

~/.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 utilise le même schéma mcpServers que Claude Desktop. La config projet l'emporte sur la 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
    }
  }
}

Cliquez sur l'icône MCP Servers dans la barre latérale Cline, puis "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
    }
  }
}

Même format que Claude Desktop. Redémarrez Windsurf pour appliquer.

~/.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 utilise un tableau d'objets serveur plutôt qu'une 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"
        ]
      }
    }
  }
}

Ajoutez dans context_servers. Zed recharge à chaud à la sauvegarde.

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

Une seule ligne. Vérifiez avec claude mcp list. Supprimez avec claude mcp remove.

Cas d'usage

Usages concrets : agent-skill-tdd

Implement a new feature with full TDD discipline

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

Quand l'utiliser : Non-trivial feature where 'just write it' has burned you before.

Prérequis

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

Déroulement

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.✓ Copié

→ Claude reads code, summarizes current state
Clarify requirements

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

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

Run design review — architecture fit, hotspots.✓ Copié

→ Design critique, not just approval
TDD loop

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

→ Red-green-refactor cycles, each reviewed

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

Pièges

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

Combiner avec : 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

Quand l'utiliser : A subtle bug where the reproduction is half the battle.

Déroulement

Investigate + document

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

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

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

→ Red test
Fix + peer review

Minimum fix to go green. Peer review.✓ Copié

→ Green + review notes

Résultat : 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

Quand l'utiliser : The ticket is ambiguous and you suspect you're about to build the wrong thing.

Déroulement

Only run steps 1–4

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

→ Requirements doc + design review without touching code

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

Combinaisons

Associez-le à d'autres MCPs pour un effet 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.✓ Copié

agent-skill-tdd-skill + github

Link requirements doc in the PR description

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

Outils

Ce que ce MCP expose

Outil	Entrées	Quand appeler	Coût
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

Coût et limites

Coût d'exécution

Quota d'API: None from the skill; Serena and Lad have their own footprints
Tokens par appel: Moderate — each step is a round trip
Monétaire: Free
Astuce: Full 6-step is overkill for trivial tasks — run steps 1–4 only on small work

Sécurité

Permissions, secrets, portée

Stockage des identifiants : None

Sortie de données : Only via Serena/Lad if configured

Dépannage

Erreurs courantes et correctifs

Serena not available

Install the Serena MCP server and register it with your agent

Requirements doc not created

Ensure filesystem write access to .requirements/

Vérifier : ls .requirements/

Design review step feels rubber-stamp

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

Alternatives

agent-skill-tdd vs autres

Alternative	Quand l'utiliser	Compromis
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

Plus

Ressources

📖 Lire le README officiel sur GitHub

🐙 Voir les issues ouvertes

🔍 Parcourir les 400+ serveurs MCP et Skills