Control the Linux desktop GUI using xdotool, wmctrl, and dogtail. Use when you need to interact with non-browser applications, simulate mouse/keyboard input, manage windows, or inspect the UI hierarchy of applications on X11/GNOME. Supports: (1) Clicking/typing in apps, (2) Resizing/moving windows, (3) Extracting text-based UI trees from apps (A11y), (4) Taking screenshots for visual analysis.
数据来源:ClawHub。 在 ClawSkills 查看
选择你使用的 Agent
方法一:命令行安装(推荐)
推荐(无需提前安装 clawhub)
npx clawhub@latest --dir ~/.claude/skills install guicountrol或使用 clawhub CLI(需提前安装)
clawhub --dir ~/.claude/skills install guicountrol⚠️ 需要 Node.js 18+,没有 Node?请使用下方方法二直接下载 ZIP。 安装 Node.js →
方法二:手动下载安装(无需 Node)
下载 ZIP,解压后将文件夹放到以下路径,重启 Agent 即可:
安装路径
~/.claude/skills/guicountrol/💡解压后将文件夹放到上方路径,重启 Agent 即可生效
--- name: linux-gui-control description: "Control the Linux desktop GUI using xdotool, wmctrl, and dogtail. Use when you need to interact with non-browser applications, simulate mouse/keyboard input, manage windows, or inspect the UI hierarchy of applications on X11/GNOME. Supports: (1) Clicking/typing in apps, (2) Resizing/moving windows, (3) Extracting text-based UI trees from apps (A11y), (4) Taking screenshots for visual analysis." ---
This skill provides tools and procedures for automating interactions with the Linux desktop environment.
Use wmctrl to find the exact name of the window you want to control.
wmctrl -l
For apps supporting accessibility (GNOME apps, Electron apps with --force-renderer-accessibility), use the inspection script to find button names without taking screenshots.
python3 scripts/inspect_ui.py "<app_name>"
Use xdotool via the helper script for common actions.
# Activate window
./scripts/gui_action.sh activate "<window_name>"
# Click coordinates
./scripts/gui_action.sh click 500 500
# Type text
./scripts/gui_action.sh type "Hello World"
# Press a key
./scripts/gui_action.sh key "Return"
wmctrl -l.scripts/inspect_ui.py to get the list of buttons and inputs.xdotool key Tab and Return to navigate, or click if coordinates are known.Many modern apps (VS Code, Discord, Cider, Chrome) need a flag to expose their UI tree:
pkill <app>
nohup <app> --force-renderer-accessibility > /dev/null 2>&1 &
安装 Linux GUI Control 后,可以对 AI 说这些话来触发它
Help me get started with Linux GUI Control
Explains what Linux GUI Control does, walks through the setup, and runs a quick demo based on your current project
Use Linux GUI Control to control the Linux desktop GUI using xdotool, wmctrl, and dogtail
Invokes Linux GUI Control with the right parameters and returns the result directly in the conversation
What can I do with Linux GUI Control in my design & creative workflow?
Lists the top use cases for Linux GUI Control, with example commands for each scenario
将技能文件夹放到 ~/.claude/skills/guicountrol/ 目录(个人级,所有项目可用),或 .claude/skills/guicountrol/(项目级)。重启 AI 客户端后,用 /guicountrol 主动调用,或让 AI 根据上下文自动发现并使用。
Linux GUI Control 支持 Claude、Cursor、OpenClaw,可与这些 AI 平台无缝集成,扩展其能力。
Linux GUI Control 可免费安装使用。请查阅仓库了解许可证信息。
Control the Linux desktop GUI using xdotool, wmctrl, and dogtail. Use when you need to interact with non-browser applications, simulate mouse/keyboard input, manage windows, or inspect the UI hierarchy of applications on X11/GNOME. Supports: (1) Clicking/typing in apps, (2) Resizing/moving windows, (3) Extracting text-based UI trees from apps (A11y), (4) Taking screenshots for visual analysis.
Automate my design & creative tasks using Linux GUI Control
Identifies repetitive steps in your workflow and sets up Linux GUI Control to handle them automatically
Linux GUI Control 属于「Design & Creative」分类,该分类的技能帮助 AI 智能体在此领域执行专业任务。