What problem does it solve? Automating native macOS applications normally requires moving the user's cursor, stealing keyboard focus, or switching Spaces, which interrupts the user's own work. This Skill drives the Mac desktop entirely in the background using the computer_use tool, so GUI automation runs without disturbing the active session. ## Core Features & Use Cases - Element-indexed interaction: Capture screenshots with numbered overlays and an accessibility tree, then click, drag, or scroll by element index instead of fragile pixel coordinates. - Background input routing: Click, type, scroll, and send keyboard shortcuts to any app on any Space without raising windows or moving the user's cursor. - Safety guardrails: Hard rules block interaction with permission dialogs, password prompts, payment UI, and prompt-injection content found in screenshots. - Use Case: Ask the agent to fill out a form in a native Mac app like Mail or Finder while you keep typing in your editor; the agent captures the app, clicks elements by index, and verifies each step with follow-up screenshots. ## Quick Start Use the computer_use tool to capture Safari with SOM mode, then click the Sign In element by its index and show me the result.
