$ loading_
Drive local ComfyUI end to end from AI coding agents.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "ComfyUI-Agent-Kit" yet — see the docs or source repo.
Create an end-to-end workflow for local ComfyUI: generate a final image from a character sketch, enable ControlNet, and automatically choose models and templates suitable for the current hardware.
An executable ComfyUI workflow or steps including ControlNet, model/template selection, and run flow.
Build a multi-shot video generation workflow in local ComfyUI: produce multiple shots around one theme and reuse suitable prompt recipes and templates when possible.
A multi-shot video workflow plan describing generation steps for each shot and reusable templates or prompt recipes.
Use local ComfyUI to enhance and restore an old photo, prioritizing an approach that fits the current device and providing the full execution flow.
A ComfyUI workflow for enhancement/restoration, including hardware-aware selection and processing steps.
Developers using Claude Code, Codex, Gemini CLI, or Qwen Code can use this skill to drive local ComfyUI end to end, reducing manual workflow setup. It is useful for delegating prompts, templates, and workflow orchestration to the agent.
When local machines vary in performance, this skill can make hardware-aware choices to match suitable models, prompt recipes, and templates. It fits teams that want a runnable workflow faster.
Designers or researchers can use it to build multi-shot video workflows or image pipelines for HDR, enhancement, and restoration. It is suited to agent-driven production setups that integrate ComfyUI capabilities.
It is built for AI coding agents and lets them drive local ComfyUI end to end. The description says it supports workflow building, model and template selection, ControlNet, multi-shot video, HDR, enhancement, and restoration.
The original description explicitly lists Claude Code, Codex, Gemini CLI, and Qwen Code. For fuller compatibility details, see the source repository.
From the description, it is meant to drive a local ComfyUI instance and includes hardware-aware selection and auto-start. Specific installation steps, prerequisites, and hardware requirements are not provided here; see the source repository.
Build multi-model agent workflows in ComfyUI with voice, OCR, and LAG integration.
Let Claude Code inspect and edit ComfyUI workflows through MCP and terminal.
Let MCP-compatible coding tools control ComfyUI for image generation.
Coordinate AI agents across terminals with messaging, watching, and task spawning.
Generate anime-style images with ComfyUI and preview them directly in chat.
Discover reusable agent skills for AI coding tools and workflows.