comfyui-agent-skill
Generate images, video, music, and speech via ComfyUI
All Skills in This Repository (1)
Pure Emerald Level IndicatorsFrequently Asked Questions
FAQPage SchemaHow to install comfyui-agent-skill?▼
Run `npx skills add MieMieeeee/comfyui-agent-skill --all -g -y` in your terminal to install the skill globally. You also need a local or self-hosted ComfyUI server running.
What can I generate with this skill?▼
You can create text-to-image art, posters with embedded text, image edits, text-to-video and image-to-video clips, music tracks, and text-to-speech voice audio.
Do I need my own ComfyUI server?▼
Yes. This skill is a client only and does not include or install ComfyUI, so you must point it at a local or trusted self-hosted ComfyUI server.
Can I add my own ComfyUI workflows?▼
Yes. Export a working workflow from ComfyUI in API format, import it with the import-workflow command, review the generated config, and it becomes a registered workflow.
Does it work without coding experience?▼
Yes. You describe what you want in plain language and the agent picks the right workflow, builds the prompt, and returns the finished image, video, or audio file.
Related Repositories in Design & Creative
View All in Design & Creative→ui-ux-pro-max-skill
AI design intelligence for professional UI, brands, and presentations
ui
Build and customize beautiful React component libraries with AI
open-design
Open-source AI design studio for decks, prototypes, images, and video