SkillFoxx

ComfyUI Agent Skill

The agent runs reviewed ComfyUI workflows from the command line: images, video, music, speech and object cutouts.

  • 119 ★ on the repository
  • Last commit
  • Apache-2.0
Skill

Broad access

Why this level

  • The voice cloning and face transfer workflows can produce material for impersonation.
  • The skill sends jobs and prompts to a ComfyUI server and runs heavy models on your hardware.
All reasons and checks

miemieeeee/comfyui-agent-skillAuthor:MieMieeeee

Install

In your terminal, with SkillFoxx CLI

npx skillfoxx add skills/comfyui-agent-skill

Detects the agents on your machine, shows the access level and pins the version.

Other ways to install

Access and checks

How we review

Broad accessThe tool can change data, run commands or handle secrets.

  • The voice cloning and face transfer workflows can produce material for impersonation.
  • The skill sends jobs and prompts to a ComfyUI server and runs heavy models on your hardware.

This is third-party code. Review the repository files before installing.

What it does

The skill gives an agent a stable CLI for registered ComfyUI workflows. It ships 12 ready ones: text to image, image editing, text and image to video, music, speech synthesis and voice cloning, text-driven object cutout and expression transfer. Commands print structured JSON with result paths, error codes and metadata. You import your own workflow into a private registry with `import-workflow` and activate it after reviewing its config. The skill does not run arbitrary unreviewed JSON. The default server address is `http://127.0.0.1:8188`.

Who it is for. Creators and developers with a local ComfyUI who want to generate media straight from a conversation with an agent.

Good fit when

  • A poster with a title is needed, and the agent picks the `qwen_image_2512_4step` workflow and size on its own.
  • An existing photo is edited from a description while keeping its composition.
  • A still frame becomes a short MP4, or a text gets a voice-over.
  • Before a long run the agent checks the server and dependencies with `doctor`.
  • A working ComfyUI workflow is added to the private registry as a new command.

Not a fit when

  • No ComfyUI server is running and you do not plan to start one: the skill neither installs ComfyUI nor hosts generation.
  • Only prompt text is needed, without generation.
  • The server sits on an open network under someone else control: the skill expects a local or trusted one.

Example request

Make a summer sale poster in a modern style, blue and white palette, portrait format.

Limitations

A local or trusted ComfyUI server is required; the skill neither installs it nor hosts generation. Each workflow needs its nodes and models on the server, otherwise the command returns `PREFLIGHT_MISSING_NODES` or `PREFLIGHT_MISSING_MODELS`. Do not point the skill at an untrusted public endpoint. If the agent runs in WSL or a container, `127.0.0.1` may not reach the host, so pass the address with `--server`. Python is installed through pipx or uv.

How to disable. Delete the skill folder from the agent skills directory and run `pipx uninstall comfyui-agent-skill-mie`. Personal workflows and outputs live in the per-user `comfyui-skill` directory and are removed by hand.

FAQ

Does the skill install ComfyUI itself?

No. ComfyUI must run separately, locally or on a trusted server. The skill only calls it over HTTP and checks readiness with `check` and `doctor`.

How do I add my own workflow?

Export it from ComfyUI in API format, run `python -m comfyui import-workflow my_workflow.json --id my_custom_workflow`, review `workflow.config.template.json` and rename it to `workflow.config.json`.

Where do outputs go?

To a per-user directory: `%APPDATA%\comfyui-skill` on Windows, `~/Library/Application Support/comfyui-skill` on macOS and `~/.local/share/comfyui-skill` on Linux. The file path is in the JSON response.

Which workflows ship with it?

Twelve: `z_image_turbo`, `klein_edit`, `qwen3_tts`, `ltx_23_t2v_distill`, `ltx_23_i2v_distilled`, `ace_step_15_music`, `qwen_image_2512_4step`, `anima_turbo`, `krea2_turbo`, `sam3_mat_image` and `liveportrait` and `qwen3_tts_clone`.

What does PREFLIGHT_MISSING_MODELS mean?

The ComfyUI server lacks the model files the workflow needs. Download them from the list in `references/workflow_nodes.md` and rerun `comfyui-skill doctor`.

Discussion

No questions or reviews yet.

Skills

A skill and CLI that turn saved ComfyUI workflows into agent commands, with a parameter schema and several servers

SkillExtended access422
Official

The official Comfy Org MCP server: an agent runs workflows in your local ComfyUI and collects the finished images

MCP serverBroad access341
Official

A Comfy Cloud plugin for Claude Code: commands to generate images, video, audio and 3D, connected through a hosted MCP server

PluginExtended access250

A lightweight Python MCP server: an agent generates and iteratively refines images, audio and video in a local ComfyUI

MCP serverExtended access413

A skill and MCP driver that let Claude Code, Codex and Gemini CLI run a local ComfyUI, with prompt recipes for 68 models

SkillExtended access121

infinite-creation takes a novel or script through ComfyUI and ffmpeg to a finished video with voice and subtitles.

SkillExtended access327

Comparison with similar tools

Cards that share the main search query, and how they differ.

ToolOfficialAuthenticationRepository starsMain difference
ComfyUI Agent Skill (this card)no119
ComfyUI MCP Servernonot required413a lightweight MCP server for generation; this is a CLI with a skill and 12 reviewed workflows
ComfyUI-Agent-Kitno121a skill and MCP driver with prompt recipes; this one has a workflow registry with configs and JSON responses

README in short

The stable interface is registered workflows plus a CLI with structured JSON. The agent chooses the workflow from `SKILL.md`, and the CLI applies a fallback only when none is named.

README badge

Original SKILL.md

---
name: comfyui-agent-skill-mie
description: >
  Agent skill for running registered ComfyUI workflows through a stable CLI,
  and for importing a user's own ComfyUI workflow into their private registry
  after review. Supports image, video, music, and speech generation, plus
  text-driven matting, face/expression transfer, and voice cloning, on a local
  or trusted self-hosted ComfyUI server (default http://127.0.0.1:8188). Can
  check server health, preflight workflow dependencies, and save the server
  URL. Runs only registered workflows and reviewed private-registry imports;
  does not execute arbitrary unreviewed workflow JSON.
---

# comfyui-agent-skill-mie

## Purpose

Run registered ComfyUI workflows through a stable Agent-facing CLI, with prompt enhancement, fail-fast errors, and structured JSON results.


Use this skill when the user asks to:

- Generate an image from text.
- Generate a new image inspired by a reference image.
- Edit an input image while preserving some structure or subject details.
- Generate text-to-video or image-to-video MP4 output.
- Generate music / instrumental / song-style MP3 output.
- Synthesize spoken voice audio with Qwen3-TTS.
- Cut out or mask an object in a picture by describing it in words.
- Transfer a face, expression, or pose from a driving video onto a reference face photo.
- Clone a specific voice from a reference audio sample and speak new text in that voice.
- Check whether a ComfyUI server is available.
- Import a workflow the user already validated in ComfyUI into their private registry, and activate it only after the generated config is reviewed.
- Preflight a registered workflow's nodes and models before a long run.
- Save a persistent ComfyUI server URL when the user asks.

Do not use this skill when the user only wants prompt writing, brainstorming, or discussion without actual generation.

A ComfyUI server being unavailable is not a reason to skip this skill. Return `SERVER_UNAVAILABLE`, ask whether ComfyUI is running on the local machine or on another machine, and point the user at `check` (single health check) and `doctor` (server health plus per-workflow preflight) to diagnose it.

## Hard Rules

- Source mode: run CLI commands from the skill root (the directory containing `SKILL.md` and `scripts/`).
- Tool-install mode: `comfyui-agent-skill-mie` / `comfyui-skill` can be run from any directory.
- Source mode: use `uv run --no-sync python -m comfyui` (or `uv run --no-sync comfyui-skill`) for runtime calls.

Report a problem