/ Verzeichnis / Playground / metaskill
← Alle Server ↗ GitHub
● Community xvirobotics ⚡ Sofort

metaskill

von xvirobotics · xvirobotics/metaskill

/metaskill command that researches your domain, then builds a 4-6 agent team with routing docs, skills, coding standards, and MCP config.

xvirobotics/metaskill is a Claude Code skill that generates AI agent teams from one prompt. Four phases: Research (web searches on industry team structures, existing agents, MCPs, best practices) → Build (routing docs, 4-6 specialized agents, 2-4 skills, coding standards, MCP config) → Credentials (optional API key collection) → Verify. Detects intent to route between team generation, single-agent creation, and single-skill creation. Default output: tech-lead (Opus) + specialists (Sonnet) across frontend/backend/testing/design with mandatory code review gates.

▶ Demo ansehen 📦 Installieren 💡 Anwendungsfälle

Warum nutzen

Hauptfunktionen

Live-Demo

In der Praxis

metaskill-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": {
    "metaskill-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/xvirobotics/metaskill",
        "~/.claude/skills/metaskill"
      ],
      "_inferred": true
    }
  }
}

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

~/.cursor/mcp.json · .cursor/mcp.json
{
  "mcpServers": {
    "metaskill-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/xvirobotics/metaskill",
        "~/.claude/skills/metaskill"
      ],
      "_inferred": true
    }
  }
}

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

VS Code → Cline → MCP Servers → Edit
{
  "mcpServers": {
    "metaskill-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/xvirobotics/metaskill",
        "~/.claude/skills/metaskill"
      ],
      "_inferred": true
    }
  }
}

Klicken Sie auf das MCP-Servers-Symbol in der Cline-Seitenleiste, dann "Edit Configuration".

~/.codeium/windsurf/mcp_config.json
{
  "mcpServers": {
    "metaskill-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/xvirobotics/metaskill",
        "~/.claude/skills/metaskill"
      ],
      "_inferred": true
    }
  }
}

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

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

Continue nutzt ein Array von Serverobjekten statt einer Map.

~/.config/zed/settings.json
{
  "context_servers": {
    "metaskill-skill": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/xvirobotics/metaskill",
          "~/.claude/skills/metaskill"
        ]
      }
    }
  }
}

In context_servers hinzufügen. Zed lädt beim Speichern neu.

claude mcp add metaskill-skill -- git clone https://github.com/xvirobotics/metaskill ~/.claude/skills/metaskill

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

Anwendungsfälle

Praxisnahe Nutzung: metaskill

Bootstrap an AI agent team for a fullstack project

👤 Founders and solo devs who want structured multi-agent setups ⏱ ~20 min beginner

Wann einsetzen: Starting a new project and you'd like proper agent separation instead of one overloaded Claude.

Voraussetzungen
  • Skill cloned — git clone https://github.com/xvirobotics/metaskill ~/.claude/skills/metaskill
Ablauf
  1. Describe the project
    /metaskill fullstack web app with React, TanStack, Postgres, Stripe subscriptions.✓ Kopiert
    → Research phase runs web searches; then build phase produces routing + agents + skills
  2. Review the generated team
    Walk me through each agent's scope and the routing rules between them.✓ Kopiert
    → Clear per-agent responsibility with no overlap
  3. Provide credentials (optional)
    Skip credentials for now — I'll add them later.✓ Kopiert
    → Skill proceeds to verification without blocking

Ergebnis: A working multi-agent setup you can start using immediately.

Fallstricke
  • Generated team has too many roles for a 1-person project — Use the single-agent mode instead ('create a single agent for X')
Kombinieren mit: github · filesystem

Create one specialized agent for an existing workflow

👤 Devs who already have a project and want to add one role ⏱ ~10 min beginner

Wann einsetzen: You need a 'security reviewer' agent but already have everything else.

Ablauf
  1. Invoke single-agent mode
    /metaskill — a single security reviewer agent for a Node.js API.✓ Kopiert
    → Targeted agent file with scope, not a full team

Ergebnis: One focused agent integrated into your existing setup.

Generate a single deploy skill without building a whole team

👤 Devs formalizing a workflow ⏱ ~15 min beginner

Wann einsetzen: You keep running the same deploy steps manually and want a skill for it.

Ablauf
  1. Invoke single-skill mode
    /metaskill — a deploy-to-staging skill for Cloudflare Workers with rollback on health-check failure.✓ Kopiert
    → SKILL.md with triggers and steps

Ergebnis: A reusable skill you can install right away.

Kombinieren mit: skillcheck-free-skill

Kombinationen

Mit anderen MCPs für 10-fache Wirkung

metaskill-skill + skillcheck-free-skill

Validate Metaskill's generated SKILL.md files against the agentskills spec before using them

After /metaskill, run SkillCheck on every generated SKILL.md.✓ Kopiert
metaskill-skill + github

Commit the generated team structure as a first PR to seed your repo

After generation, commit .claude/ and agent docs in a single 'seed' PR.✓ Kopiert

Werkzeuge

Was dieses MCP bereitstellt

WerkzeugEingabenWann aufrufenKosten
generate_team project description Fresh project 0 + web search tokens
generate_single_agent role description Existing team, need one more role 0
generate_single_skill workflow description Formalizing a repeated workflow 0
verify generated files Auto-run after generation 0

Kosten & Limits

Was der Betrieb kostet

API-Kontingent
Uses web search during research phase
Tokens pro Aufruf
High for team generation (research + build); lower for single-agent/skill modes
Kosten in €
Free — skills are local files. Web search may count against your own MCP's quotas.
Tipp
Use single-agent mode when you don't need a full team; it's much cheaper.

Sicherheit

Rechte, Secrets, Reichweite

Credential-Speicherung: No credentials in the skill itself. Credentials phase asks for your API keys if you opt-in.
Datenabfluss: Research phase performs web searches

Fehlerbehebung

Häufige Fehler und Lösungen

Skill not invoked — Claude sets up agents manually

Use '/metaskill' as a literal trigger.

Prüfen: ls ~/.claude/skills/metaskill/SKILL.md
SKILL.md frontmatter wrong

Re-clone; description drives activation.

Prüfen: head ~/.claude/skills/metaskill/SKILL.md
Wrong trigger keywords — generates a skill when you wanted a team

Phrase the project description clearly; 'fullstack web app' triggers team mode, 'a skill for X' triggers skill mode.

Alternativen

metaskill vs. andere

AlternativeWann stattdessenKompromiss
Manual agent designYou have strong opinions about role structureMore control, much slower
rootnode-skillYou want Project-level engineering rather than agent-team generationDifferent axis — Claude Projects vs Claude Code multi-agent

Mehr

Ressourcen

📖 Offizielle README auf GitHub lesen

🐙 Offene Issues ansehen

🔍 Alle 400+ MCP-Server und Skills durchsuchen