Menu
Generate and manage n8n workflows for AI agents. Creates automation workflows that complement Mastra agents.
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Baseado na classificação ocupacional SOC
| name | n8n-workflow |
| description | Generate and manage n8n workflows for AI agents. Creates automation workflows that complement Mastra agents. |
| disable-model-invocation | true |
| allowed-tools | Read, Write, Bash, WebFetch |
| argument-hint | ["create|list|sync"] |
Generiere n8n Workflows passend zu deinen Mastra Agents.
┌─────────────────────────────────────────────────────────────────────┐
│ AGENT + WORKFLOW ARCHITECTURE │
├─────────────────────────────────────────────────────────────────────┤
│ │
│ MASTRA AGENT N8N WORKFLOW │
│ ──────────── ──────────── │
│ • AI Reasoning • Scheduled Triggers │
│ • Tool Execution • Webhook Endpoints │
│ • Context Management • Data Transformations │
│ • Decision Making • External Integrations │
│ │
│ ┌─────────────┐ ┌─────────────┐ │
│ │ │ triggers │ │ │
│ │ Agent │◄──────────────►│ Workflow │ │
│ │ │ calls │ │ │
│ └─────────────┘ └─────────────┘ │
│ │
│ WHEN TO USE WHAT: │
│ • Agent: Complex reasoning, multi-step decisions │
│ • Workflow: Scheduled tasks, webhooks, integrations │
│ • Both: Agent decides → Workflow executes │
│ │
└─────────────────────────────────────────────────────────────────────┘
n8n hat native MCP-Unterstützung via MCP Server Trigger Node:
# In n8n: MCP Server Trigger Node hinzufügen
# Workflow als Tool für Claude/Agents exponieren
Vorteile:
# Community MCP Server für n8n Workflows
claude mcp add n8n-server -- npx @anthropic-ai/mcp-server-n8n
Oder mit dem populären czlonkowski/n8n-mcp:
{
"mcpServers": {
"n8n": {
"command": "npx",
"args": ["-y", "@anthropic-ai/mcp-server-n8n"],
"env": {
"N8N_HOST": "https://n8n.example.com",
"N8N_API_KEY": "your-api-key"
}
}
}
}
/n8n-workflow create [agent-name]Generiere n8n Workflow Template für einen Mastra Agent.
Workflow:
n8n/workflows/Output:
{
"name": "Customer Support Agent Triggers",
"nodes": [
{
"name": "Webhook",
"type": "n8n-nodes-base.webhook",
"position": [240, 300],
"parameters": {
"httpMethod": "POST",
"path": "agent-trigger"
}
},
{
"name": "Process Request",
"type": "n8n-nodes-base.code",
"position": [460, 300],
"parameters": {
"jsCode": "// Process and route to agent"
}
}
]
}
/n8n-workflow listListe alle Workflows in n8n/workflows/.
/n8n-workflow syncSynchronisiere Workflows mit n8n Instance.
Workflow startet Agent-Ausführung.
┌──────────┐ ┌──────────┐ ┌──────────┐ ┌──────────┐
│ Schedule │ ─► │ Prepare │ ─► │ Call │ ─► │ Process │
│ Trigger │ │ Context │ │ Mastra │ │ Result │
└──────────┘ └──────────┘ │ Agent │ └──────────┘
└──────────┘
Use Cases:
Agent delegiert Aufgabe an Workflow.
┌──────────┐ ┌──────────┐ ┌──────────┐
│ Mastra │ ─► │ n8n │ ─► │ External │
│ Agent │ │ Workflow │ │ Systems │
└──────────┘ └──────────┘ └──────────┘
Use Cases:
End-to-end Request Processing.
┌──────────┐ ┌──────────┐ ┌──────────┐ ┌──────────┐
│ Webhook │ ─► │ Mastra │ ─► │ n8n │ ─► │ Response │
│ Request │ │ Agent │ │ Actions │ │ Webhook │
└──────────┘ └──────────┘ └──────────┘ └──────────┘
Use Cases:
{
"name": "Daily Report Agent",
"nodes": [
{
"name": "Schedule Trigger",
"type": "n8n-nodes-base.scheduleTrigger",
"parameters": {
"rule": { "interval": [{ "field": "hours", "hoursInterval": 24 }] }
}
},
{
"name": "Fetch Data",
"type": "n8n-nodes-base.httpRequest",
"parameters": {
"url": "={{$env.API_URL}}/metrics"
}
},
{
"name": "Call Agent",
"type": "n8n-nodes-base.httpRequest",
"parameters": {
"method": "POST",
"url": "={{$env.MASTRA_URL}}/agents/report-generator/run",
"body": "={{ JSON.stringify($json) }}"
}
},
{
"name": "Send Report",
"type": "n8n-nodes-base.slack",
"parameters": {
"channel": "#reports",
"text": "={{ $json.report }}"
}
}
]
}
{
"name": "Agent Router",
"nodes": [
{
"name": "Webhook",
"type": "n8n-nodes-base.webhook",
"parameters": {
"httpMethod": "POST",
"path": "agent-router"
}
},
{
"name": "Route Decision",
"type": "n8n-nodes-base.switch",
"parameters": {
"rules": {
"rules": [
{ "value": "support", "output": 0 },
{ "value": "sales", "output": 1 }
]
}
}
},
{
"name": "Support Agent",
"type": "n8n-nodes-base.httpRequest",
"parameters": {
"method": "POST",
"url": "={{$env.MASTRA_URL}}/agents/support/run"
}
},
{
"name": "Sales Agent",
"type": "n8n-nodes-base.httpRequest",
"parameters": {
"method": "POST",
"url": "={{$env.MASTRA_URL}}/agents/sales/run"
}
}
]
}
n8n/
├── workflows/
│ ├── templates/ # Wiederverwendbare Templates
│ │ ├── daily-report.json
│ │ ├── webhook-router.json
│ │ └── notification.json
│ │
│ └── agents/ # Agent-spezifische Workflows
│ ├── support-agent.json
│ └── sales-agent.json
│
└── README.md
❌ Agent macht HTTP Calls direkt
✅ Agent entscheidet → Workflow führt aus
❌ Workflow verändert State ohne Check
✅ Workflow prüft vor Aktion
{
"name": "Error Handler",
"type": "n8n-nodes-base.errorTrigger"
}
❌ API Keys in Workflow JSON
✅ n8n Credentials verwenden
# n8n Instance
N8N_HOST=https://n8n.example.com
N8N_API_KEY=your-api-key
# Mastra (für Callbacks)
MASTRA_URL=https://app.example.com/api/mastra
Cross-project audit and sync. Backs up, bootstraps, promotes, syncs, and verifies all downstream projects.
Structured pre-planning research. Explores codebase, asks clarifying questions, and produces a brainstorm output file for /plan-feature input.
Capture knowledge from development sessions. Debug patterns, architecture decisions, framework gotchas, and integration learnings compound over time.
Load project context and show current status. Use at the start of a session or when context is needed.
Run parallel code reviews using specialized agents (security, performance, simplicity, nextjs-react). Produces a structured report.
Initialize a new project from Agent Kit boilerplate. Use when creating a new downstream project.