What problem does it solve? Automating native macOS applications normally requires stealing the user's cursor and keyboard focus, interrupting their work. This Skill drives the Mac desktop in the background — clicking, typing, scrolling, and dragging in any app or Space without disrupting the user, and works with any tool-capable model. ## Core Features & Use Cases - Background GUI Automation: Capture screenshots with numbered element overlays (SOM mode) and click by element index instead of unreliable pixel coordinates. - Full Input Control: Supports click, double-click, right-click, drag-and-drop, scroll, text typing, and keyboard shortcuts like cmd+s, all with optional post-action capture for verification. - Safety Guardrails: Hard-blocks dangerous patterns (log out, lock screen, fork bombs), refuses to type secrets, and treats on-screen content as untrusted to prevent prompt injection. - Use Case: Ask the agent to organize files in Finder or reply in the native Mail app while you keep typing in your editor — the automation runs in another Space without touching your focus. ## Quick Start Use the computer_use tool to capture the Safari window and click the Sign In button by its element index.
