所有操作返回 JSON 格式结果。
Works with
AI-first code editor with Composer
Before installing skills in Cursor, ensure your development environment meets these requirements:
node --versionpyautogui-automationExecute the skills CLI command in your project's root directory to begin installation:
Fetches pyautogui-automation from steelan9199/wechat-publisher and configures it for Cursor.
The CLI shows a list of agents. Use arrow keys and space to select Cursor:
Confirm successful installation by checking the skill directory location:
Restart Cursor to activate pyautogui-automation. Access via /pyautogui-automation in your agent's command palette.
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your environment. Always review source, verify the publisher, and test in isolation before production.
Submit your Claude Code skill and start earning
Automate repetitive workflows and reduce manual effort
Example
Generate reports, summarize documents, draft communications
Save 3-5 hours per week on routine tasks
Learn new skills, understand complex topics, get expert guidance
Example
Explain concepts, provide examples, suggest learning resources
Accelerate learning and skill development by 2x
Enhance output quality through reviews, suggestions, and refinements
Example
Review drafts, suggest improvements, catch errors
Improve work quality by 30-40% with less effort
0
total installs
0
this week
4
GitHub stars
0
upvotes
Run in your terminal
0
installs
0
this week
4
stars
| 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 |
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
# 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
# 左键单击坐标 (100, 200)
python scripts/automation.py click --x 100 --y 200
# 右键双击
python scripts/automation.py click --x 100 --y 200 --button right --clicks 2
# 快捷双击
python scripts/automation.py double_click --x 100 --y 200
# 获取指定坐标的颜色
python scripts/automation.py get_pixel_color --x 100 --y 200
# 返回: {"rgb": [255, 255, 255], "hex": "#ffffff"}
# 查找颜色位置（精确匹配）
python scripts/automation.py find_color --rgb 255,255,255
# 查找颜色（带容差）
python scripts/automation.py find_color --rgb 255,255,255 --tolerance 10
# 在指定区域查找
python scripts/automation.py find_color --rgb 255,0,0 --region 0,0,800,600
# 获取当前鼠标位置
python scripts/automation.py get_mouse_position
# 移动鼠标（瞬间）
python scripts/automation.py move_mouse --x 500 --y 300
# 移动鼠标（动画效果，0.5秒）
python scripts/automation.py move_mouse --x 500 --y 300 --duration 0.5
# 相对当前位置移动鼠标
python scripts/automation.py move_mouse_rel --x 100 --y -50
python scripts/automation.py move_mouse_rel --x 100 --y -50 --duration 0.5
# 拖拽鼠标
python scripts/automation.py drag_mouse --x 800 --y 600 --duration 1.0
# 鼠标按下（不释放）
python scripts/automation.py mouse_down --button left
# 鼠标释放
python scripts/automation.py mouse_up --button left
# 滚动（正数向上，负数向下）
python scripts/automation.py scroll --amount 500
python scripts/automation.py scroll --amount -500 --x 500 --y 300
# 获取屏幕分辨率
python scripts/automation.py get_screen_size
# 返回: {"width": 1920, "height": 1080}
# 获取当前活动窗口信息（需要安装 pywin32）
python scripts/automation.py get_active_window
# 返回: {"title": "窗口标题", "left": 100, "top": 100, "width": 800, "height": 600}
# 获取所有可见窗口列表（需要安装 pywin32）
python scripts/automation.py get_all_windows
# 返回: {"count": 5, "windows": [...]}
# 等待 2 秒
python scripts/automation.py sleep --seconds 2
# 输入文本
python scripts/automation.py type_text --text "Hello World"
# 输入文本（带间隔）
python scripts/automation.py type_text --text "Hello" --interval 0.1
# 按下按键
python scripts/automation.py press_key --key enter
python scripts/automation.py press_key --key esc
# 组合键
python scripts/automation.py hotkey --keys ctrl,c
python scripts/automation.py hotkey --keys ctrl,shift,esc
# 快捷操作
python scripts/automation.py copy # Ctrl+C
python scripts/automation.py paste # Ctrl+V
python scripts/automation.py cut # Ctrl+X
python scripts/automation.py select_all # Ctrl+A
python scripts/automation.py undo # Ctrl+Z
python scripts/automation.py redo # Ctrl+Y
python scripts/automation.py save # Ctrl+S
常用按键名称: enter, esc, tab, space, backspace, delete, up, down, left, right, f1-f12, ctrl, alt, shift, win
需要安装 opencv-python 以使用 confidence 参数：
# 查找图片位置
python scripts/automation.py locate_on_screen --image button.png
# 使用置信度（需要 opencv-python）
python scripts/automation.py locate_on_screen --image button.png --confidence 0.9
# 在指定区域查找
python scripts/automation.py locate_on_screen --image button.png --region 0,0,800,600
# 查找所有匹配位置
python scripts/automation.py locate_all_on_screen --image icon.png
# 等待图片出现（最多等待10秒）
python scripts/automation.py wait_for_image --image button.png --timeout 10
# 等待图片出现（自定义检查间隔）
python scripts/automation.py wait_for_image --image loading.png --timeout 30 --wait_interval 1
# 等待图片消失
python scripts/automation.py wait_for_image_to_vanish --image loading.png --timeout 30
# 警告对话框
python scripts/automation.py alert --title "提示" --text "操作完成"
# 确认对话框
python scripts/automation.py confirm --title "确认" --text "是否继续？"
# 自定义按钮
python scripts/automation.py confirm --title "选择" --text "请选择操作" --buttons "保存,不保存,取消"
# 输入对话框
python scripts/automation.py prompt --title "输入" --text "请输入名称:" --default "默认值"
脚本已启用以下安全保护：
# 1. 截图记录初始状态
python scripts/automation.py screenshot --output login_start.png
# 2. 点击用户名输入框
python scripts/automation.py click --x 500 --y 300
# 3. 输入用户名
python scripts/automation.py type_text --text "myusername"
# 4. 按 Tab 切换到密码框
python scripts/automation.py press_key --key tab
# 5. 输入密码
python scripts/automation.py type_text --text "mypassword"
# 6. 点击登录按钮
python scripts/automation.py click --x 500 --y 400
# 7. 等待页面加载
python scripts/automation.py sleep --seconds 3
# 8. 截图记录结果
python scripts/automation.py screenshot --output login_end.png
# 检测特定位置颜色并执行操作
color=$(python scripts/automation.py get_pixel_color --x 100 --y 100)
# 解析 JSON 判断颜色后执行相应操作
# 查找按钮并点击
result=$(python scripts/automation.py locate_on_screen --image submit_button.png --confidence 0.9)
# 从结果中提取 center_x, center_y 并点击
脚本会自动安装必需的依赖：
pyautogui: 核心自动化库pillow: 图像处理可选依赖（用于图像识别置信度）：
pip install opencv-python
| 用户输入 | AI 行动 |
|---|---|
| "xxx" | 直接执行 xxx |
Prerequisites
Time Estimate
15-45 minutes depending on use case complexity
Steps
Common Pitfalls
✓ Do
✗ Don't
💡 Pro Tips
✓ Use when
Use when skill capabilities match your task, clear ROI on time saved, and you can validate outputs. Best for repetitive tasks, learning, and quality improvement.
✗ Avoid when
Avoid when task requires deep expertise you can't validate, involves sensitive decisions, or when learning process is more valuable than speed of completion.
anthropics/claude-code
mblode/agent-skills
github/awesome-copilot
sickn33/antigravity-awesome-skills
leonxlnx/taste-skill
erichowens/some_claude_skills
pyautogui-automation fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
pyautogui-automation reduced setup friction for our internal harness; good balance of opinion and flexibility.
I recommend pyautogui-automation for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
pyautogui-automation reduced setup friction for our internal harness; good balance of opinion and flexibility.
We added pyautogui-automation from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
We added pyautogui-automation from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
I recommend pyautogui-automation for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
Registry listing for pyautogui-automation matched our evaluation — installs cleanly and behaves as described in the markdown.
pyautogui-automation fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
Registry listing for pyautogui-automation matched our evaluation — installs cleanly and behaves as described in the markdown.
showing 1-10 of 67