← 返回 Skills 市场

Comfyui Automation Skill

Name: Comfyui Automation Skill
Author: wuxiaosa86-cmd

作者 wuxiaosa86-cmd · GitHub ↗ · v1.0.1 · MIT-0

cross-platform ⚠ suspicious

251

总下载

当前安装

版本数

在 OpenClaw 中安装

/install comfyui-automation-skill

功能描述

Automates ComfyUI workflows by collecting required assets, executing tasks via RunningHub API, and returning execution status and results.

使用说明 (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

技能启动阶段：接收用户提供的工作流标识信息
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
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
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
素材完整性检查：验证所有必要的素材是否已收集完整
执行确认阶段：请求用户确认是否执行运行操作
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
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。

安全使用建议

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.

功能分析

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.

能力评估

✓ 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.

如何使用

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-automation-skill
安装完成后，直接呼叫该 Skill 的名称或使用 /comfyui-automation-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

版本历史

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.

元数据

Slug comfyui-automation-skill

版本 1.0.1

许可证 MIT-0

累计安装 1

当前安装数 1

历史版本数 2

常见问题