What problem does it solve? Automating native macOS applications normally requires stealing the user's cursor and keyboard focus, interrupting their work. This Skill lets an agent capture screens, click elements, type, scroll, and drag in the background across any Space, without raising windows or hijacking input. ## Core Features & Use Cases - Element-indexed interaction: Capture screenshots with numbered overlays and an accessibility (AX) tree, then click or drag by element index instead of fragile pixel coordinates. - Background input routing: Target a specific app (e.g., Safari, Finder, Mail) without raising its window, switching Spaces, or moving the user's cursor. - Full action set: click, double/right/middle click, drag, scroll, type, keyboard shortcuts, wait, app listing, and focus management, with optional inline post-action captures. - Use Case: Ask the agent to fill out a form in a native Mac app while you keep typing in your editor; it captures the app's UI, clicks fields by index, types values, and verifies the result with a follow-up screenshot. ## Quick Start Ask the agent to capture the Safari window with the computer_use tool and click the Sign In button by its element index.
