What it does
This repo is a collection of 14 skills
- Connects Instruction files the AI reads
- Account or key Not confirmed yet (README not read yet)
- Category Automation and agents
Maker’s original description
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.For makers: add a badge to your README
If you made this, paste this code into your README. The badge links back to this page.
[](https://mcp.popnx.com/en/skills/comfy-org-comfy-skills)Similar Skills
Same kind of work, ordered like the Skills list
14 skills (instruction sets) by Comfy-Org that an AI reads and follows · not an MCP server
Pick the skill to install
Install only the ones you use. Open a skill to see how to install it
Install the whole set (14)
If you want every one, let the AI install them in one go. Know 2 things first
- Every installed skill’s description is loaded into every chat. The more you install, the easier it is for the AI to pick the wrong one
- Some skills duplicate tools the AI already has built in. Installing only the ones you use works better
Uploading to Claude on the web and apps: you need 14 uploads, one ZIP per skill. Open each skill in the list below to download it
Checked against official docs Nov 12, 2026 · Source: support.claude.com, code.claude.com, learn.chatgpt.com, cursor.com
- clone-voice
Clone a voice from a reference recording and speak new lines with it on Comfy Cloud. Use when the user wants to copy a voice, match a recording they supply, or perform text-to-speech in that voice, including a multi-speaker script read in cloned voices.
- comfy
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 "gener…
- comfy-sdk
Build an app that generates images, video or audio through Comfy Router using the Comfy SDK (Python `comfy-sdk` or TypeScript `@comfyorg/sdk`). Use when a task mentions the Comfy SDK, Comfy Router, `models.run`, or adding generation to an app via api.comfy.org. Not for driving the `comfy` CLI, Comf…
- consistent-characters
Keep one or more characters visually consistent across images or video on Comfy Cloud. Use when the user wants the same person, mascot, or character to match across scenes, a turnaround, a storyboard, or a sequence of shots.
- generate-3d
Generate a 3D model on Comfy Cloud. Use when the user asks for a mesh, a GLB or OBJ, text-to-3D, or image-to-3D from a photo or drawing.
- generate-audio
Generate speech, music, or sound effects on Comfy Cloud. Use when the user asks for audio, music, a soundtrack, sound effects, ambience, or text-to-speech that is not a clone of a specific recording.
- generate-image
Generate, edit, or restyle a still image on Comfy Cloud. Use when the user asks to create, draw, design, edit, inpaint, or restyle a picture, photo, illustration, poster, or other still image, including from text or from a source image they provide.
- generate-video
Generate, edit, or extend a video on Comfy Cloud. Use when the user asks for a clip, animation, text-to-video, image-to-video, or to change or continue a video they already have.
- help
Explain what Comfy Cloud can create and how to start. Use when the user asks what this plugin can do, how to sign in, whether they need a local install or an API key, or for examples of images, video, audio, or 3D they can request.
- remove-background
Remove or replace the background of an image on Comfy Cloud. Use when the user asks to cut out a subject, make a background transparent, erase a backdrop, or drop a person or product onto a new background.
- search-models
Search Comfy Cloud's model catalog. Use when the user asks which checkpoints, LoRAs, VAEs, ControlNets, or upscalers exist, or asks for a model by style, base family, or source.
- search-nodes
Search Comfy Cloud's nodes and how to wire them. Use when the user asks which node does a job, what inputs a node takes, or how to connect nodes for a ComfyUI workflow.
- search-templates
Find a pre-built Comfy Cloud workflow template. Use when the user asks for a template, a starting workflow, or which ready-made graph matches a task, a tag, or a model family.
- upscale-image
Upscale an image on Comfy Cloud. Use when the user asks to enlarge a photo or illustration, increase resolution, or run super-resolution on an image they provide.
How a Skill differs from MCP
MCP = the hands
Connects the AI to an outside service or data, such as reading Notion or creating an invoice. A program or server has to be running.
Skill = the manual
A text file that teaches the AI how to do a task. It connects to nothing.
Some overlap: a few Skills run scripts that call tools, and a few MCP servers only send knowledge. Start from the task you want done.
Works with
Claude CodeCodexCursor
From the maker’s README and the folders in the repo
Install
Pick a skill first
This repo has 14 skills. Pick one from the list above; its page shows every way to install it, including letting the AI install it and a ZIP
The maker’s command installs the whole set of 14
Checking the commands · copy buttons appear once they pass
Copied from the maker’s README; it downloads and runs the maker’s code
Discussion
Ask, share a tip or report that it does not work. Sorted by what people marked helpful.
No posts yet. Be the first to ask or share.
Posts here are written by users, not the PopNx team.
From GitHub
- GitHub stars
- 262
Stars are for the whole repo, not each skill - Maker
- Comfy-Org
- License
- MIT
- Last code change
- Nov 11, 2026
- SKILL.md files in the repo (including translated copies and templates)
- 14
- Topics
- ai-agents, claude, comfyui, mcp, skills