LaunchKit · 2026
Back to Skills

guicountrol

Control the Linux desktop GUI using xdotool, wmctrl, and dogtail.

6
9.4k downloads
by @dreamtraveler13

Setup & Installation

openclaw skills install @dreamtraveler13/guicountrol

Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:

npx clawhub install guicountrol

What This Skill Does

Automates Linux desktop GUI interactions using xdotool, wmctrl, and dogtail on X11/GNOME. Supports simulating mouse and keyboard input, managing windows, inspecting UI accessibility trees, and taking screenshots for visual analysis.

Combines window management, input simulation, and accessibility tree inspection in one workflow, covering apps that have no API or web interface.

When to use it

  • Automating repetitive clicks in a desktop app that has no CLI or API
  • Resizing and repositioning windows in a scripted workflow
  • Extracting button and input labels from an Electron app without screenshots
  • Navigating a legacy GUI tool using keyboard simulation
  • Taking screenshots of specific windows for automated visual checks

Example Workflow

Here's how your AI assistant might use this skill in practice.

INPUT

User asks: click the 'Export' button in the desktop app 'MyApp'

AGENT
  1. 1Run wmctrl -l to list open windows and confirm MyApp is running
  2. 2Activate the MyApp window using gui_action.sh activate
  3. 3Run scripts/inspect_ui.py to extract the UI tree and locate the Export button
  4. 4Use xdotool to click the button coordinates or simulate keyboard navigation to it
  5. 5Verify the action completed by re-inspecting the UI tree or taking a screenshot
OUTPUT

The Export button is clicked and the export dialog opens

Requirements

Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.

wmctrl installed on the Linux systemxdotool installed on the Linux systemdogtail installed on the Linux systemscrot installed on the Linux systemX11/GNOME desktop environment