Pyautogui Automation

A comprehensive desktop automation wrapper around PyAutoGUI that gives Claude control over mouse, keyboard, screenshots, and image recognition through a unified CLI interface. You get pixel-perfect color detection, region-based screenshot capture, and the ability to wait for specific images to appear or disappear on screen. The structure is clean with separate modules for mouse, keyboard, screen, and dialog operations, all returning JSON for easy parsing. Built-in failsafe triggers if you slam the mouse to the top-left corner, which is handy when things go sideways. Best for automating repetitive UI tasks, testing desktop apps, or building workflows that need to interact with applications without APIs. Supports Windows-specific features like active window detection if you have pywin32 installed.

skills.sh installs: 671
GitHub stars: 10
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add steelan9199/wechat-publisher --skill pyautogui-automation --agent claude-code

Installs into .claude/skills of the current project.

Files

PyAutoGUI 自动化操作

功能概览

功能类别	支持的操作
截图	全屏截图、区域截图、截图到剪贴板
鼠标控制	点击、双击、移动、相对移动、拖拽、滚动、按下/释放
颜色操作	获取像素颜色、查找颜色位置
键盘操作	输入文本、按键、组合键、快捷操作（复制/粘贴/全选等）
图像识别	在屏幕上查找图片位置、等待图片出现/消失
对话框	警告、确认、输入对话框
系统信息	屏幕分辨率、鼠标位置、窗口信息
工具	等待、暂停

快速开始

基本使用模式

python scripts/automation.py <action> [参数...]

所有操作返回 JSON 格式结果。

脚本位置: scripts/automation.py

操作详解

截图

# 全屏截图（自动生成文件名）
python scripts/automation.py screenshot

# 指定输出路径
python scripts/automation.py screenshot --output my_screenshot.png

# 区域截图
python scripts/automation.py screenshot --output region.png --region 100,100,400,300

# 截图到剪贴板（需要安装 pywin32）
python scripts/automation.py screenshot_to_clipboard
python scripts/automation.py screenshot_to_clipboard --region 100,100,400,300