What problem does it solve? Driving a Mac's GUI programmatically usually means hijacking the user's cursor, keyboard focus, and active Space, which interrupts their work. This Skill lets an AI operate macOS apps in the background — clicking, typing, scrolling, and dragging — while the user keeps working uninterrupted. ## Core Features & Use Cases - Element-indexed interaction: Capture screenshots with numbered overlays on every interactable element plus an accessibility-tree index, then click by element number instead of fragile pixel coordinates. - Background input routing: Target any app on any Space without raising windows, stealing focus, or moving the user's cursor. - Model-agnostic workflow: Works with any tool-capable model (Claude, GPT, Gemini, or local models) through a single computer_use tool with capture, click, type, key, scroll, drag, and wait actions. - Use Case: Ask the AI to file a message in native Mail, organize Finder windows, or operate a Mac-only app like Figma or Logic while you continue typing in your editor. ## Quick Start Ask the AI to open Safari in the background, capture the page, and click the sign-in button by its element index.
