comfyui

Automate ComfyUI media generation workflows via comfy-cli and REST/WebSocket APIs.

Updated Jul 3, 2026
One-click install
npx skills add https://github.com/Toqsick/MaxClaw --skill comfyui-toqsick
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: comfyui
Source: https://github.com/Toqsick/MaxClaw/tree/main/.claude/skills/comfyui
Command: npx skills add https://github.com/Toqsick/MaxClaw --skill comfyui-toqsick

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires comfy-cli, comfyui, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill simplifies the creation and execution of complex media generation workflows using ComfyUI, providing a streamlined approach to image, video, and audio production.

Core Features & Use Cases

  • Media Workflow Automation: Automate the creation and execution of complex media workflows.
  • Custom Node and Model Management: Manage custom nodes and models for tailored workflows.
  • Use Case: Imagine you need to generate a video with custom effects and audio. Use this Skill to combine text-to-image, image-to-video, and audio generation workflows into a single seamless process.

Quick Start

Use the comfyui skill to generate a 3D-animated video with the following parameters: prompt='cyberpunk cityscape', seed=-1, steps=50, output_dir='./outputs/video'

Frequently Asked Questions about comfyui

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate media generation workflows with ComfyUI?

To automate media generation workflows with ComfyUI, you can use this Skill to handle the comfy-cli lifecycle and REST/WebSocket API, injecting parameters and monitoring real-time execution for image, video, and audio creation.

Do I need to install comfy-cli to execute custom media workflows?

Yes, you need to install both ComfyUI and the comfy-cli package, as this Skill relies on the comfy-cli lifecycle and REST/WebSocket API to manage custom nodes, models, and complex workflow execution.

Can I combine text-to-image, image-to-video, and audio generation into a single process?

Yes, you can combine text-to-image, image-to-video, and audio generation into a single process by using this Skill to automate the setup and execution of complex, multi-step media workflows.

What is the best way to monitor real-time execution of custom media workflows?

The best way to monitor real-time execution of custom media workflows is by leveraging the REST and WebSocket API integration provided through the comfy-cli, which allows direct parameter injection and live tracking.

How do I inject workflow parameters like seed and steps for video creation?

You inject workflow parameters for video creation by passing them directly in your prompt, such as setting prompt='cyberpunk cityscape', seed=-1, steps=50, and specifying an output directory.

Are there limitations when managing custom nodes and models for media generation?

A key limitation is the strict dependency on having ComfyUI and comfy-cli pre-installed in your environment, as the Skill cannot execute workflow parameter injection or media generation without these underlying tools.