← Back to Skills Marketplace
wuxiaosa86-cmd

Comfyui Automation Skill

by wuxiaosa86-cmd · GitHub ↗ · v1.0.1 · MIT-0
cross-platform ⚠ suspicious
251
Downloads
0
Stars
1
Active Installs
2
Versions
Install in OpenClaw
/install comfyui-automation-skill
Description
Automates ComfyUI workflows by collecting required assets, executing tasks via RunningHub API, and returning execution status and results.
README (SKILL.md)

name: "comfyui_automation_skill" version: "1.0.0" author: "OpenClaw" tags: ["comfyui", "automation", "workflow"] dependencies: ["python", "requests"] permissions: ["network"]

comfyui_automation_skill

适用场景

  • 需要自动执行ComfyUI工作流的场景
  • 批量处理图像、视频等素材的自动化任务
  • 需要根据工作流需求收集素材并执行的场景
  • 希望通过API接口控制ComfyUI工作流的场景
  • 需要监控工作流执行状态并获取结果的场景

前置条件

  • 输入要求：工作流标识信息（workflowId或工作流昵称）
  • 环境依赖：Python 3.6+，requests库
  • 权限要求：需要网络访问权限以调用RunningHub API
  • API Key：需要RunningHub API密钥

参数定义

  • workflow_identifier (string): 工作流标识信息，可以是workflowId或工作流昵称
  • api_key (string): RunningHub API密钥
  • webhook_url (string) [optional]: 用于接收任务完成通知的webhook URL

执行步骤

  1. 技能启动阶段：接收用户提供的工作流标识信息
  2. 工作流分析阶段：自动获取工作流JSON结构，分析需要用户输入的节点
  3. 节点选择阶段：显示所有识别到的节点，用户选择需要配置的节点
  4. 智能参数收集阶段：对选中的节点进行配置，支持图片上传、文本输入等
  5. 素材完整性检查：验证所有必要的素材是否已收集完整
  6. 执行确认阶段：请求用户确认是否执行运行操作
  7. 工作流执行阶段：使用ComfyUI任务1-简易或任务2-高级接口执行工作流
  8. 结果反馈阶段：监控执行状态，获取返回结果并反馈给用户

支持的节点类型

  • LoadImage: 加载图片节点（支持本地文件或URL）
  • CLIPTextEncode / CLIPTextEncode (NSP): CLIP文本编码器
  • Seed (rgthree): 随机种子节点
  • RH_Translator: RunningHub翻译器
  • KSampler: K采样器（支持seed、steps、cfg、denoise）
  • easy sam3ImageSegmentation: 图像分割
  • ControlNetInpaintingAliMamaApply: ControlNet应用
  • ModelSamplingAuraFlow: 模型采样

异常处理

  • API调用失败：重试3次，每次间隔2秒
  • 工作流执行超时：设置300秒超时
  • 素材格式错误：提示用户重新上传正确格式的素材

最佳实践

  • 确保提供的工作流标识信息正确无误
  • 准备好所有必要的素材文件
  • 在执行前仔细确认工作流参数
  • 建议在 RunningHub 平台先测试工作流

完整文档

详细使用说明请参考 README.md 文件。

Usage Guidance
This skill appears to do what it says (automate ComfyUI workflows via RunningHub) and requires a RunningHub API key. Before installing: (1) Confirm you trust https://www.runninghub.cn because any local file paths you provide will be uploaded to that service; do not provide system or sensitive files. (2) Be aware the skill is interactive (uses input()) which may not work in non-interactive/autonomous runs — test it manually first. (3) The package metadata in the registry omitted required credentials while skill.yaml does require an API key — ask the publisher to clarify metadata. (4) Consider using a scoped/rotatable API key and test with non-sensitive data. (5) Note there are minor code quality issues (e.g., truncated/buggy prompt handling visible in the shipped script) — you may want an updated/reviewed version before trusting it in production.
Capability Analysis
Type: OpenClaw Skill Name: comfyui-automation-skill Version: 1.0.1 The skill bundle automates ComfyUI workflows via the RunningHub API (runninghub.cn). While the logic in `comfyui_automation.py` is aligned with the stated purpose, it implements high-risk capabilities including network communication and local file access (reading and uploading files). Per the provided criteria, the presence of these risky capabilities—even when plausibly needed for the skill's function—requires a suspicious classification. No evidence of intentional malice, such as data exfiltration or backdoors, was identified in the code or the `SKILL.md` instructions.
Capability Assessment
✓ Purpose & Capability
Name/description claim automation of ComfyUI workflows via RunningHub; the code and SKILL.md call RunningHub endpoints, upload local files, fetch workflow JSON, analyze nodes, and execute tasks — all consistent with the stated purpose. skill.yaml also declares a required RunningHub API key (sensitive), which is expected for this integration.
ℹ Instruction Scope
Instructions and code will accept local file paths and upload those files to https://www.runninghub.cn (upload endpoint). They also use interactive input() prompts for creating workflows and confirmations, which may be incompatible with non-interactive agent execution. The behavior of uploading arbitrary files to an external service is expected for this skill but is a privacy/security consideration: only files the user intentionally provides should be uploaded.
✓ Install Mechanism
No install spec (instruction/code bundle only). The skill runs as included Python code and depends on the requests library; there are no downloads from unknown URLs or archive extraction steps in the bundle.
ℹ Credentials
The skill legitimately requires a RunningHub API key (declared as a sensitive setting in skill.yaml). Registry-level metadata earlier listed no required env vars — that mismatch is an inconsistency you may want clarified. No unrelated credentials or broad filesystem access are requested by the skill itself, but the skill will access user-provided local file paths and upload them to RunningHub.
✓ Persistence & Privilege
Skill does not request always:true, does not modify other skills or agent-wide settings, and runs only when invoked. No persistent/privileged behavior was observed in the provided files.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install comfyui-automation-skill
  3. After installation, invoke the skill by name or use /comfyui-automation-skill
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
No functional changes detected in this version. - Version number and documentation remain unchanged. - No file changes were found between 1.0.0 and 1.0.1.
v1.0.0
comfyui-automation-skill v1.0.0 - Initial release with automated execution of ComfyUI workflows via API. - Supports batch processing of images, videos, and other materials. - Allows workflow execution using either workflow ID or nickname. - Collects and verifies required materials based on workflow configuration. - Monitors workflow progress, provides notifications, and handles results. - Includes robust error handling for API failures, timeouts, and material issues.
Metadata
Slug comfyui-automation-skill
Version 1.0.1
License MIT-0
All-time Installs 1
Active Installs 1
Total Versions 2
Frequently Asked Questions

What is Comfyui Automation Skill?

Automates ComfyUI workflows by collecting required assets, executing tasks via RunningHub API, and returning execution status and results. It is an AI Agent Skill for Claude Code / OpenClaw, with 251 downloads so far.

How do I install Comfyui Automation Skill?

Run "/install comfyui-automation-skill" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Comfyui Automation Skill free?

Yes, Comfyui Automation Skill is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Comfyui Automation Skill support?

Comfyui Automation Skill is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Comfyui Automation Skill?

It is built and maintained by wuxiaosa86-cmd (@wuxiaosa86-cmd); the current version is v1.0.1.

More Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463556 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259610 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200551 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191226 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190235 · by oswalpalash

💬 Comments