Agent skill

Comfy

by Comfy-Org in Comfy-Org/comfy-skills

Generate images, video, audio, and 3D with Comfy Cloud — search hundreds of models and workflow templates, run custom ComfyUI workflows, and manage generation jobs through the hosted Comfy Cloud MCP…

MITAuto-check passedAgent Workflows

Install Comfy

skills CLI
$ npx skills add Comfy-Org/comfy-skills --skill comfy -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Comfy-Org/comfy-skills comfy --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Comfy-Org/comfy-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/openclaw/comfy .claude/skills/comfy && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
comfy
GitHub stars
219
Token cost
~1.4k tokens
SKILL.md length
662 words
Files
1
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

Generate images, video, audio, and 3D with Comfy Cloud — search hundreds of models and workflow templates, run custom ComfyUI workflows, and manage generation jobs through the hosted Comfy Cloud MCP…

  • Works in 3 steps: Get an API key — sign in at… → Export it (put this in your shell… → Register the MCP server with OpenClaw
  • Any generate/edit an image
  • SKILL.md covers Connect, Which tools to use, Example prompts and Notes
  • Reaches cloud.comfy.org; needs COMFY_API_KEY

What it does

Comfy is an agent skill from Comfy-Org/comfy-skills. Generate images, video, audio, and 3D with Comfy Cloud — search hundreds of models and workflow templates, run custom ComfyUI workflows, and manage generation jobs through the hosted Comfy Cloud MCP server. Cloud-only — connects to the hosted service, not a local ComfyUI install. Use for any "generate/edit an image", "make a video", "text to 3D", or ComfyUI workflow task.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Diffusion and image models, MCP servers and Image generation. It works with ComfyUI and Model Context Protocol. The repository describes itself as: Comfy Cloud product skills: slash commands for generating images, video, audio, and 3D with Comfy Cloud agents. Single source of truth for the installer and MCP server. The licence is MIT.

When your agent uses it

  • Any generate/edit an image
  • ComfyUI workflow task

Example prompts

  • “generate/edit an image”
  • “make a video”
  • “text to 3D”
  • “/comfy”

Requirements

  • A credential in COMFY_API_KEY

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Get an API key — sign in at cloud.comfy.org,
  2. Export it (put this in your shell profile or OpenClaw's env)
  3. Register the MCP server with OpenClaw

What it can do on your machine

Read from SKILL.md and the folder at commit d50722a. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • cloud.comfy.org

    Also links to:

    • docs.comfy.org
    • comfy.org

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • COMFY_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Comfy loads about 1.4k tokens when it runs. Until then it costs about 95 tokens; SKILL.md has 662 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~95
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Comfy-Org/comfy-skills at commit d50722a, republished under its MIT licence (© Comfy-Org). 662 words, ~1,391 tokens.

Download SKILL.mdSave it as .claude/skills/comfy/SKILL.md (or your agent's skills folder).
name
comfy
description
Generate images, video, audio, and 3D with Comfy Cloud — search hundreds of models and workflow templates, run custom ComfyUI workflows, and manage generation jobs through the hosted Comfy Cloud MCP server. Cloud-only — connects to the hosted service, not a local ComfyUI install. Use for any "generate/edit an image", "make a video", "text to 3D", or ComfyUI workflow task.

Comfy Cloud

Comfy Cloud runs ComfyUI in the cloud and exposes it to agents as an MCP server: image/video/audio/3D generation via partner models (Ideogram, Flux, Kling, Veo, Seedance, and more) and open-source pipelines, plus full ComfyUI workflow authoring — search templates, override inputs, submit custom graphs, and fetch outputs as signed URLs.

Scope: this skill connects to the hosted Comfy Cloud MCP server and requires a Comfy account — it does not drive a local ComfyUI install. A local-ComfyUI MCP is on the roadmap and will ship as a separate skill; until then, for local instances see comfy-cli.

Connect

The server supports two auth methods: OAuth (browser sign-in, nothing to manage — recommended) and API keys (for headless or CI setups).

bash
openclaw mcp set comfy '{"url":"https://cloud.comfy.org/mcp","transport":"streamable-http","auth":"oauth"}'
openclaw mcp login comfy
openclaw gateway restart

openclaw mcp login prints an authorization URL — open it, sign in to your Comfy account, and finish the flow as the CLI directs (it may ask you to rerun with --code <code>). Verify with openclaw mcp status --verbose. Note that OpenClaw ignores static headers on a server entry once auth: "oauth" is set, so don't combine the two.

Option B — API key (headless / CI)
  1. Get an API key — sign in at cloud.comfy.org, then create a key under Settings → API Keys. Keys start with comfyui-.

  2. Export it (put this in your shell profile or OpenClaw's env):

    bash
    export COMFY_API_KEY="comfyui-..."
  3. Register the MCP server with OpenClaw:

    bash
    openclaw mcp set comfy '{"url":"https://cloud.comfy.org/mcp","transport":"streamable-http","headers":{"Authorization":"Bearer ${COMFY_API_KEY}"}}'
    openclaw gateway restart

    The server also accepts the key as an X-API-Key: ${COMFY_API_KEY} header, but prefer the Authorization: Bearer form above — standard headers survive every client's proxy layer, and some OpenClaw builds have dropped custom headers on streamable-http transports (see openclaw#65590). If you get a 401 with a key you know is valid, you are probably hitting that: switch to the Bearer form, route through mcporter, or just use OAuth (Option A).

Either way: browsing/search tools work with any account; generation consumes Comfy Cloud credits and needs a subscription or credit balance.

Show full SKILL.md (347 more words)Show less

Which tools to use

Images and video from a named model (Ideogram, Flux, Gemini, Kling, Veo, Seedance, …): before calling partner_generate, check whether the named family also has an OSS route — some families (MiniMax H3 is a current example, as of 2026-08) ship BOTH a paid partner node and open-source weights under the identical display title. Run search_templates for the family name alongside search_nodes; if both exist, tell the user the OSS option exists (it has no partner/API fee, but running it still spends ordinary Comfy Cloud compute credits — it isn't free on Comfy Cloud, only free of the partner surcharge) and ask which they want. If only the partner route exists, or the user picks paid, call partner_generate — it runs the provider through Comfy Cloud and saves the result to your asset library. Do not hand-build a workflow for plain text-to-image/video when a partner model is named.

Anything workflow-shaped (open-source models, LoRA/ControlNet, multi-step pipelines): start from a template — search_templates → get_template_schema → run_template with input_overrides. For fully custom graphs use submit_workflow (the graph must end in an output node like SaveImage, or validation rejects it). Save and reuse with save_workflow / run_saved_workflow.

Editing an existing image: upload_file first, then reference the uploaded file from a LoadImage node (or pass it to partner_generate for image-to-image partners). Never inline base64 image data into a workflow.

Getting results: wait_for_job → get_output. Outputs come back as time-limited signed URLs — download them exactly as returned (don't edit query params, they're part of the signature). get_queue and cancel_job manage in-flight jobs; submit_batch / wait_for_batch fan out variations.

Discovery: search_models (checkpoints/LoRAs on the platform), search_nodes (available ComfyUI nodes with wiring hints), get_prompting_guide (model-specific prompting advice).

Example prompts

  • "Generate an image of a cozy bookstore café on a rainy afternoon with Ideogram and download it to ./bookstore.png"
  • "Take ./product.jpg, remove the background, and upscale the result 2×"
  • "Find a text-to-video template for Kling, run it with the prompt 'a paper boat drifting down a rain gutter, cinematic', and give me the output URL"

Notes

  • Generation spends Comfy Cloud credits; search/discovery tools are free.
  • Full MCP docs and per-client setup: docs.comfy.org/cloud/mcp

© Comfy-Org, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in openclaw/comfy of Comfy-Org/comfy-skills.

Open the folder on GitHubat commit d50722a

Compare with similar skills

Comfy next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Comfy compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Comfy this skillComfy-Org/comfy-skills219—~1.4kAutomated safety check: PassMIT
Setupguaardvark/guaardvark2551 repos~1.2kAutomated safety check: PassMIT
Workflow Assistantfilliptm/ComfyUI_FL-MCP127—~3.6kAutomated safety check: PassMIT
Comfyui Skill OpenclawHuangYuChuh/ComfyUI_Skills_OpenClaw411—~2.7kAutomated safety check: PassApache-2.0
Imageguaardvark/guaardvark255—~1.8kAutomated safety check: PassMIT
ComfyUI Local DriverSlavaSexton/ComfyUI-Agent-Kit105—~12kAutomated safety check: PassApache-2.0

Similar skills

  • Setup

    guaardvark/guaardvark

    Connect this agent to a running Guaardvark (self-hosted AI studio) and check what it can do right now.

    255 GitHub starsUsed in 1 repo~1.2k tokens
    AI & LLM EngineeringAuto-check passed
  • Workflow Assistant

    filliptm/ComfyUI_FL-MCP

    A skill your agent uses when working with ComfyUI workflows through FL-MCP or similar MCP tools: inspect, explain, create, edit, debug, compact, validate, queue, screenshot, or organize node graphs…

    127 GitHub stars~3.6k tokensUpdated 23 days ago
    Agent WorkflowsAuto-check passed
  • Comfyui Skill Openclaw

    HuangYuChuh/ComfyUI_Skills_OpenClaw

    Run registered ComfyUI workflows through the fast comfyui-skill CLI, and use the official local Comfy MCP for live template, node, model, validation, and orchestration capabilities.

    411 GitHub stars~2.7k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check passed
  • Image

    guaardvark/guaardvark

    Generate or edit images on the user's own GPU through Guaardvark: single images, instruction edits, background cut-outs, inpaint and outpaint, consistent characters from the Cast Library, and batch…

    255 GitHub stars~1.8k tokensUpdated today
    Media & CreativeAuto-check passed
  • ComfyUI Local Driver

    SlavaSexton/ComfyUI-Agent-Kit

    Drives a local ComfyUI install over its HTTP API to generate and edit images, video and audio, with per-model prompt recipes and workflow guidance.

    105 GitHub stars~12k tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed
  • Panel Node Pack Sync

    artokun/comfyui-mcp

    Keep the ComfyUI sidebar panel node-pack (comfyui-agent-panel) in step with the orchestrator after comfyui-mcp updates.

    795 GitHub stars~2.9k tokensUpdated 3 days ago
    AI & LLM EngineeringAuto-check: notes

Questions about Comfy

What does Comfy do?

Generate images, video, audio, and 3D with Comfy Cloud — search hundreds of models and workflow templates, run custom ComfyUI workflows, and manage generation jobs through the hosted Comfy Cloud MCP…. Comfy is an agent skill from Comfy-Org/comfy-skills. Generate images, video, audio, and 3D with Comfy Cloud — search hundreds of models and workflow templates, run custom ComfyUI workflows, and manage generation jobs through the hosted Comfy Cloud MCP server.

When should I use Comfy?

Comfy fits situations like: any generate/edit an image; comfyUI workflow task.

How do I install Comfy in Claude Code?

Run `npx skills add Comfy-Org/comfy-skills --skill comfy -a claude-code`. Or copy the skill folder (openclaw/comfy in Comfy-Org/comfy-skills) into .claude/skills/comfy in your project. Claude Code loads it when a task matches its description.

How do I install Comfy in Codex?

Run `npx skills add Comfy-Org/comfy-skills --skill comfy -a codex`. Or copy the skill folder (openclaw/comfy in Comfy-Org/comfy-skills) into .agents/skills/comfy in your project. Codex loads it when a task matches its description.

Can I use Comfy in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Comfy-Org/comfy-skills --skill comfy -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/comfy, .gemini/skills/comfy, .github/skills/comfy and .opencode/skills/comfy in your project.

What does Comfy need to run?

Going by SKILL.md and its folder, Comfy needs credentials named COMFY_API_KEY. Our summary lists: A credential in COMFY_API_KEY.

Does Comfy access the network?

SKILL.md names 3 domains. In commands or code: cloud.comfy.org; the agent is likely to contact it when it follows the instructions. As links in the text: docs.comfy.org and comfy.org. This is read from the text; nothing was executed.

Is Comfy safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Comfy use?

Comfy is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Comfy use?

About 1.4k tokens (SKILL.md is roughly 5.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Comfy?

Skills that share tags, products or a category with Comfy: Setup (guaardvark/guaardvark, 255 stars), Workflow Assistant (filliptm/ComfyUI_FL-MCP, 127 stars), Comfyui Skill Openclaw (HuangYuChuh/ComfyUI_Skills_OpenClaw, 411 stars) and Image (guaardvark/guaardvark, 255 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Comfy?

Comfy-Org (a GitHub organization) maintains it in Comfy-Org/comfy-skills, which has 219 GitHub stars. The repository was last updated on October 8, 2026.

Source: Comfy-Org/comfy-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.