Skip to content
Get packs

ComfyUI Command-Line Control

Lets an agent queue ComfyUI image jobs, manage models, and download generated images from the terminal.

Source Download skill
Repository
HKUDS/CLI-Anything
Stars
58,084
Licence
Apache-2.0
Files
1 file

What it does

Once installed, the agent can operate a locally running ComfyUI image generator through a command-line tool instead of its graphical interface. It can check the server, list available models and node types, submit saved workflow files to the generation queue, monitor progress and history, and download finished images to a folder. Output can be requested in JSON so an agent can read results reliably.

Great for

  • Users who already run ComfyUI locally and want an agent to queue and collect image generations
  • Developers building automated image pipelines who want scriptable access to ComfyUI
  • Power users who prefer terminal workflows over the browser interface

Skip it if

  • People without a local ComfyUI installation, since the tool only talks to a server at localhost:8188 and will not generate images on its own
  • Users who want to generate images without installing ComfyUI and a capable GPU setup
  • Anyone expecting the skill to manage cloud image services; it only targets a local ComfyUI REST API

Try asking

  • “Check whether my ComfyUI server is running and how much GPU memory is free before starting a batch.”
  • “List the checkpoint and LoRA models I have installed so I can pick one for a portrait workflow.”
  • “Queue my saved workflow file portrait.json and then tell me when it finishes.”
  • “Download all images generated by prompt ID abc123 into ./outputs.”
Step-by-step guide: how to use ComfyUI Command-Line ControlInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 1 original files, the Apache-2.0 licence and an attribution note.

    skills.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip skills.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip skills.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Run the system stats command first to confirm ComfyUI is reachable before queuing work.
  • Use absolute file paths for workflows and output folders, as the skill recommends.
  • Ask the agent to use JSON output so it can parse results and check return codes.

What's inside

  • SKILL.md

Redistributed unmodified from HKUDS/CLI-Anything under the Apache-2.0 licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.