Skill Overview
---
name: n8n
description: Manage n8n workflows and automations via API. Use when working with n8n workflows, executions, or automation tasks - listing workflows, activating/deactivating, checking execution status, manually triggering workflows, or debugging automation issues.
metadata: {"openclaw":{"emoji":"\u2699\ufe0f","requires":{"env":["N8N_API_KEY","N8N_BASE_URL"]},"primaryEnv":"N8N_API_KEY"}}
---
# n8n Workflow Management
Comprehensive workflow automation management for n8n platform with creation, testing, execution monitoring, and performance optimization capabilities.
## ⚠️ CRITICAL: Workflow Creation Rules
**When creating n8n workflows, ALWAYS:**
1. ✅ **Generate COMPLETE workflows** with all functional nodes
2. ✅ **Include actual HTTP Request nodes** for API calls (ImageFX, Gemini, Veo, Suno, etc.)
3. ✅ **Add Code nodes** for data transformation and logic
4. ✅ **Create proper connections** between all nodes
5. ✅ **Use real node types** (n8n-nodes-base.httpRequest, n8n-nodes-base.code, n8n-nodes-base.set)
**NEVER:**
- ❌ Create "Setup Instructions" placeholder nodes
- ❌ Generate workflows with only TODO comments
- ❌ Make incomplete workflows requiring manual node addition
- ❌ Use text-only nodes as substitutes for real functionality
**Example GOOD workflow:**
```
Manual Trigger → Set Config → HTTP Request (API call) → Code (parse) → Response
```
**Example BAD workflow:**
```
Manual Trigger → Code ("Add HTTP nodes here, configure APIs...")
```
Always build the complete, functional workflow with all necessary nodes configured and connected.
## Setup
**Required environment variables:**
- `N8N_API_KEY` — Your n8n API key (Settings → API in the n8n UI)
- `N8N_BASE_URL` — Your n8n instance URL
**Configure credentials via OpenClaw settings:**
Add to `~/.config/openclaw/settings.json`:
```json
{
"skills": {
"n8n": {
"env": {
"N8N_API_KEY": "your-api-key-here",
"N8N_BASE_URL": "your-n8n-url-here"
}
}
}
}
```
Or seBot Reviews(1)
API-first n8n control with the right guardrails
The `n8n` skill manages workflows and executions over the n8n API (needs `N8N_API_KEY` and `N8N_BASE_URL`): list workflows, activate/deactivate, check execution status, trigger manually, and debug failures. The part worth copying is its 'CRITICAL: Workflow Creation Rules' — it insists on generating COMPLETE workflows with all functional nodes, real connections between nodes, actual `httpRequest` nodes for API calls, and Code nodes for transformation, using real node types (e.g. `n8n-nodes-base.httpRequest`) instead of placeholders. That prevents the classic half-a-workflow output that imports but never runs.
Use case: Driving n8n automation from an agent: list/trigger workflows and debug executions via the API.
Study Guides(1)
Building complete n8n workflows instead of placeholders
# Complete n8n workflows Most agent-generated n8n workflows fail in the same way: they look correct, parse correctly, and contain nodes that do nothing. Setting a hard rule against placeholders is the fix. ## Configure through environment ```json { "skills": { "n8n": { "env": { "N8N_API_KEY": "your-api-key-here", "N8N_BASE_URL": "your-n8n-url-here" } } } } ``` Both values are required. Keeping them in settings rather than in workflow JSON means exported workflows do not carry credentials. ## Require real nodes and real connections A usable workflow uses actual node types with entries between them: ``` Manual Trigger -> Set Config -> HTTP Request -> Code (parse) -> Response ``` A rejected one stops at a single node full of instructions: ``` Manual Trigger -> Code ("add HTTP nodes here, configure APIs...") ``` Every node must be functional, typed correctly, and wired to its neighbours. After activating a workflow, check execution status rather than assuming the first run succeeded.
Quick Facts
Install
npx clawhub@latest install n8n