Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
Automates Linux desktop interactions through command-line tools. Covers screenshot capture, mouse and keyboard control, and window management. Works with X11-based desktop environments.
Provides programmatic desktop control without requiring a dedicated GUI automation framework like PyAutoGUI or Selenium.
When to use it
- Capturing before/after screenshots to verify UI changes
- Automating repetitive form-filling across desktop apps
- Scripting multi-step browser navigation without a browser API
- Recording window state during debugging sessions
- Building unattended GUI test workflows
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: open a terminal, run a command, and screenshot the output
- 1List windows to find the terminal window ID
- 2Move mouse to terminal window and click to focus it
- 3Type the desired command using the type command
- 4Press Return to execute
- 5Capture a screenshot of the terminal window to record output
Screenshot saved to ~/screenshot_YYYYMMDD_HHMMSS.png showing command output