Leaderboard/Media/ComfyUI_Skills_OpenClaw
Last commit on August 26, 2026·Created on March 6, 2026

HuangYuChuh/ComfyUI_Skills_OpenClaw

Connects AI agents to ComfyUI for programmatic image generation and workflow execution
Combined rank
#562
across all skills
In Media
#31
category rank
Stars
409
+1.5% in last 7d
Forks
38
0.0% in last 7d
Watchers
0
0 watchers in last 7d
Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of recent attention, adoption, and active maintenance.
TL;DR

This skill enables AI agents to execute registered ComfyUI workflows via a dedicated CLI. It is designed for automation builders who need to integrate precise image generation, stylistic requirements, and batch processing into agentic workflows.

By combining CLI execution for latency-sensitive tasks with the official local Comfy MCP for orchestration, it allows agents to import and sync saved workflows for repeatable visual output.

WHO IT'S FOR
AI agent / automation builders
integrate ComfyUI image generation into agents
AI artists
automate repetitive image generation workflows
Generative AI engineers
orchestrate Stable Diffusion and Flux pipelines
Technical leads / architects
design hybrid MCP and CLI AI toolchains
Repository contents

1 skill file

Compatible AgentsThe repository documents support for these agents. The skills may also work with other agents that can load SKILL.md files, but they may need some setup or small changes.

Use this skill

Follow the documented setup, then try a first task.

I’m using

OpenClaw installation with pip

Installs: ComfyUI Skills for OpenClaw repository bundle · OpenClaw

Before you start
  • Python 3.10+
  • A running ComfyUI server

Platform: macOS, Linux, or Windows; the documented clone commands use bash syntax

Run from: ~/.openclaw/workspace/skills/comfyui-skill-openclaw

  1. In a terminal, clone the repository into OpenClaw's documented skills directory and enter the cloned project root.

    cd ~/.openclaw/workspace/skills
    git clone https://github.com/HuangYuChuh/ComfyUI_Skills_OpenClaw.git comfyui-skill-openclaw
    cd comfyui-skill-openclaw
  2. From the project root in the terminal, install the required CLI with pip.

    pip install comfyui-skill-cli
  3. Manually edit config.json in the project root to define the ComfyUI server. The documented local example uses server id local, URL http://127.0.0.1:8188, enabled true, output directory ./outputs, and local as the default server.

  4. With the ComfyUI server running, execute this complete verification block in a terminal from the project root.

    comfyui-skill server status
    comfyui-skill list
SKILL.md · Checked Sep 18, 2026README.md · Checked Sep 18, 2026

Give it something to do.

Suggested first task

Import a saved ComfyUI workflow

Uses comfyui-skill-openclaw

  • Absolute path replacing [absolute/path/to/workflow.json] with a ComfyUI API-format workflow export
  • Configured config.json
  • Running ComfyUI server
Use the comfyui-skill-openclaw skill to import the ComfyUI API-format workflow at [absolute/path/to/workflow.json] for later reuse. Run all shell commands from the project root, then list the registered workflows and report whether the imported workflow appears. Do not execute the workflow yet.
SKILL.md · Checked Sep 18, 2026README.md · Checked Sep 18, 2026