What problem does it solve? Automating native desktop applications normally requires moving the user's cursor and stealing keyboard focus, interrupting their work. This Skill drives macOS, Windows, and Linux desktops in the background using accessibility trees and numbered element overlays, so GUI automation runs without disturbing the user. ## Core Features & Use Cases - Background GUI Automation: Click, type, scroll, and drag in any app without moving the real cursor, raising windows, or switching virtual desktops. - Element-Indexed Targeting: Capture screenshots with numbered overlays and an accessibility-tree index, then click elements by index instead of fragile pixel coordinates. - Cross-Platform Support: Works on macOS (AX), Windows (UIA), and Linux (AT-SPI) with any tool-capable model, powered by cua-driver. - Use Case: Ask the agent to fill out a form in a native desktop app like Mail or Figma while you keep typing in your editor; it captures the app, clicks the right fields by index, and verifies each step. ## Quick Start Ask the agent to open a specific desktop application and perform a task in it, such as clicking a button or filling a field, using the computer_use tool.
