Setup & Installation
openclaw skills install @jeremysommerfeld8910-cpu/xdotool-control
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
npx clawhub install xdotool-control
What This Skill Does
Mouse, keyboard, and window automation for Linux desktops using xdotool. Covers clicking at screen coordinates, typing into GUI apps, switching browser tabs, and running screenshot-verify-click loops. Works when browser CDP is unavailable.
Handles desktop UI automation directly on Linux without requiring a browser debugging protocol or remote relay.
When to use it
- Clicking Chrome extension icons by name
- Typing commands into a terminal window
- Switching browser tabs without a relay
- Automating desktop GUI interactions via coordinate clicks
- Running screenshot loops to verify and click UI elements
Example Workflow
Here's how your AI assistant might use this skill in practice.
INPUT
User asks: click the OpenClaw extension icon in Chrome
AGENT
- 1Run xdotool getdisplaygeometry to get screen dimensions
- 2Take a toolbar screenshot with scrot to verify icon positions
- 3Find and focus the Chrome window with xdotool search and windowactivate --sync
- 4Wait 0.3s for focus to settle
- 5Click the extension icon coordinates with xdotool mousemove and click 1
OUTPUT
Chrome extension icon clicked at the correct toolbar position