/install comfyui-complete-toolkit-skill
ComfyUI Portable Skill
Use this skill when the task is to work with ComfyUI in a reusable, installation-agnostic way.
Minimum trigger scope
Trigger on requests like:
- "Build a ComfyUI workflow"
- "Fix this ComfyUI workflow"
- "Use the ComfyUI API"
- "Why is this ComfyUI graph failing?"
- "Add a LoRA / model / node to this ComfyUI setup"
Do not assume any particular machine, model inventory, file layout, GPU, or custom node pack.
First move: assume zero install knowledge
Before writing or editing any workflow:
- Read references/setup.md.
- If the install is unknown, collect the missing setup fields from the user or discover them from the running ComfyUI instance.
- Prefer discovery over assumptions:
- use
/object_infoto detect node classes and model dropdown values - confirm checkpoints, VAEs, encoders, and LoRAs from the target install
- stop and report missing requirements clearly
- use
Read path by task
- Setup / first run / portability questions -> references/setup.md
- API submission / queue / history / WebSocket -> references/api.md
- Programmatic graph building -> references/workflow-patterns.md
- Model-family requirements -> references/models.md
- Cross-family validation / node availability -> references/compatibility.md
- LoRA loading and compatibility -> references/lora.md
- Prompt construction -> references/prompting.md
- Graph hygiene / debugging -> references/graph-conventions.md
- Release history -> references/changelog.md
- User-fill config template -> references/config-template.md
Global operating rules
- Treat node classes as discoverable, not guaranteed constants.
- Treat model filenames as examples until confirmed on the target install.
- Use filename-only model references in workflow JSON unless the install explicitly requires a subdirectory path.
- Use defensive parsing for
/historyand/object_info; schema details can vary by ComfyUI version and custom nodes. - Fail fast when a required node class, model, or custom node is missing.
- Keep setup-specific notes out of this file; put them in a per-user config or setup reference.
Cold-read test
Before publishing or packaging changes, check that a fresh reader could answer:
- What does this skill do?
- When should it trigger?
- What must be discovered first?
- Where do install-specific values go?
- Which reference file should be opened for the current task?
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install comfyui-complete-toolkit-skill - 安装完成后,直接呼叫该 Skill 的名称或使用
/comfyui-complete-toolkit-skill触发 - 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
Comfy UI Complete Toolkit 是什么?
Portable ComfyUI workflow and API guidance for any install. Use when building, validating, or troubleshooting ComfyUI image/video workflows, discovering avai... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 333 次。
如何安装 Comfy UI Complete Toolkit?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install comfyui-complete-toolkit-skill」即可一键安装,无需额外配置。
Comfy UI Complete Toolkit 是免费的吗?
是的,Comfy UI Complete Toolkit 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
Comfy UI Complete Toolkit 支持哪些平台?
Comfy UI Complete Toolkit 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。
谁开发了 Comfy UI Complete Toolkit?
由 Zambav(@zambav)开发并维护,当前版本 v1.0.0。