ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified media Safety 4/5

comfyui-runner

Start/stop/status for a ComfyUI instance.

Why use this skill?

Learn how to easily start, stop, and check the status of your ComfyUI server using the OpenClaw comfyui-runner skill for streamlined generative AI automation.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/xtopher86/comfyui-runner
Or

What This Skill Does

The comfyui-runner skill acts as an interface between the OpenClaw agent and a local ComfyUI instance. ComfyUI is a powerful node-based GUI for Stable Diffusion, and managing it manually can be cumbersome. This skill provides a streamlined mechanism to control the server lifecycle directly from your terminal or chat interface. It enables you to start the server when you need to generate images, stop it to free up system resources, or verify its operational status with a simple command. By leveraging the health check endpoint, the skill ensures that your automation workflow is aware of whether the inference engine is ready to accept tasks, effectively bridging the gap between automation agents and generative media tools.

Installation

To integrate this skill into your environment, use the OpenClaw hub. Ensure you have the necessary system permissions to execute processes on your machine. Run the following command in your terminal:

clawhub install openclaw/skills/skills/xtopher86/comfyui-runner

After installation, configure your connection settings by creating a .env file in the skill directory or by setting the environment variables COMFYUI_HOST and COMFYUI_PORT. If your instance is protected by basic authentication, ensure COMFYUI_USER and COMFYUI_PASS are provided to avoid connection errors.

Use Cases

This skill is perfect for users who want to optimize system performance by running ComfyUI on-demand rather than as a persistent background process. Developers can use it to build automated pipelines where images are generated only when certain triggers are met, ensuring that GPU memory is reclaimed immediately after a task finishes. It is also highly effective for remote management, allowing users to wake up their AI workstation and check its status before sending heavy generation requests.

Example Prompts

  1. "Check if my ComfyUI server is currently running."
  2. "Please start the ComfyUI server so I can generate some concept art."
  3. "I'm done with my project, stop the ComfyUI service now."

Tips & Limitations

Note that this skill relies on the system PATH to find the ComfyUI executable; if it is not found, you may need to specify the full path in your skill configuration. Additionally, the tool uses standard curl requests, so firewall settings or VPNs might block the health check if not configured correctly. Always ensure that the port defined in your config matches the port ComfyUI is listening on.

Metadata

Author@xtopher86
Stars879
Views2
Updated2026-02-11
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-xtopher86-comfyui-runner": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Tags(AI)

#generative-ai#stable-diffusion#comfyui#automation#server-management
Safety Score: 4/5

Flags: network-access, code-execution