What problem does it solve? Automating macOS desktop interactions normally requires fragile AppleScript or manual clicking. This Skill provides a structured CLI to capture screens, identify UI elements, and drive mouse, keyboard, apps, windows, and menus programmatically. ## Core Features & Use Cases - Screen Capture & Vision: Take screenshots of screens, windows, or menu bar regions, generate annotated UI maps with element IDs via peekaboo see, and optionally analyze captures with AI prompts. - UI Interaction: Click, type, drag, scroll, swipe, and press hotkeys targeting elements by ID, query, or coordinates, with smart waits and focus control. - System Management: Launch, quit, hide, and switch apps; move, resize, and focus windows; click menus, menu bar items, and Dock icons; handle system dialogs and clipboard content. - Use Case: Automate a login flow by running peekaboo see --annotate to map the window, then peekaboo click --on B3 and peekaboo type to fill credentials without manual input. ## Quick Start Ask the agent to run peekaboo see with annotation on the frontmost app, then click a specific element and type text into it.