metaskill MCP — Casos de uso, Instalar & Demo ao vivo

Por que usar

Principais recursos

/metaskill single command — no manual role design
Research phase runs live web searches so output reflects current ecosystem
Generates routing doc, agents, skills, standards, and MCP config in one pass
Three intent modes: full team / single agent / single skill
Default architecture uses Opus tech-lead + Sonnet specialists with review gates

Demo ao vivo

Como fica na prática

metaskill-skill.replay ▶ pronto

0/0

Instalar

Escolha seu cliente

~/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
    }
  }
}

Abra Claude Desktop → Settings → Developer → Edit Config. Reinicie após salvar.

~/.cursor/mcp.json · .cursor/mcp.json

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

Cursor usa o mesmo esquema mcpServers que o Claude Desktop. Config de projeto vence a global.

VS Code → Cline → MCP Servers → Edit

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

Clique no ícone MCP Servers na barra lateral do Cline, depois "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

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

Mesmo formato do Claude Desktop. Reinicie o Windsurf para aplicar.

~/.continue/config.json

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

O Continue usa um array de objetos de servidor em vez de um map.

~/.config/zed/settings.json

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

Adicione em context_servers. Zed recarrega automaticamente ao salvar.

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

Uma linha só. Verifique com claude mcp list. Remova com claude mcp remove.

Casos de uso

Usos do mundo real: metaskill

Bootstrap an AI agent team for a fullstack project

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

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

Pré-requisitos

Skill cloned — git clone https://github.com/xvirobotics/metaskill ~/.claude/skills/metaskill

Fluxo

Describe the project

/metaskill fullstack web app with React, TanStack, Postgres, Stripe subscriptions.✓ Copiado

→ Research phase runs web searches; then build phase produces routing + agents + skills
Review the generated team

Walk me through each agent's scope and the routing rules between them.✓ Copiado

→ Clear per-agent responsibility with no overlap
Provide credentials (optional)

Skip credentials for now — I'll add them later.✓ Copiado

→ Skill proceeds to verification without blocking

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

Armadilhas

Generated team has too many roles for a 1-person project — Use the single-agent mode instead ('create a single agent for X')

Combine com: 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

Quando usar: You need a 'security reviewer' agent but already have everything else.

Fluxo

Invoke single-agent mode

/metaskill — a single security reviewer agent for a Node.js API.✓ Copiado

→ Targeted agent file with scope, not a full team

Resultado: 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

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

Fluxo

Invoke single-skill mode

/metaskill — a deploy-to-staging skill for Cloudflare Workers with rollback on health-check failure.✓ Copiado

→ SKILL.md with triggers and steps

Resultado: A reusable skill you can install right away.

Combine com: skillcheck-free-skill

Combinações

Combine com outros MCPs para 10× de alavancagem

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.✓ Copiado

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.✓ Copiado

Ferramentas

O que este MCP expõe

Ferramenta	Entradas	Quando chamar	Custo
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

Custo e limites

O que custa rodar

Cota de API: Uses web search during research phase
Tokens por chamada: High for team generation (research + build); lower for single-agent/skill modes
Monetário: Free — skills are local files. Web search may count against your own MCP's quotas.
Dica: Use single-agent mode when you don't need a full team; it's much cheaper.

Segurança

Permissões, segredos, alcance

Armazenamento de credenciais: No credentials in the skill itself. Credentials phase asks for your API keys if you opt-in.

Saída de dados: Research phase performs web searches

Generated agents are suggestions — review them before granting them MCP tool access.

Solução de problemas

Erros comuns e correções

Skill not invoked — Claude sets up agents manually

Use '/metaskill' as a literal trigger.

Verificar: ls ~/.claude/skills/metaskill/SKILL.md

SKILL.md frontmatter wrong

Re-clone; description drives activation.

Verificar: 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.

Alternativas

metaskill vs. outros

Alternativa	Quando usar	Troca
Manual agent design	You have strong opinions about role structure	More control, much slower
rootnode-skill	You want Project-level engineering rather than agent-team generation	Different axis — Claude Projects vs Claude Code multi-agent

Mais

Recursos

📖 Leia o README oficial no GitHub

🐙 Ver issues abertas

🔍 Ver todos os 400+ servidores MCP e Skills