Screenshot

Media

Control your Mac screen, windows, and UI elements

• Capture screenshots and annotated maps
• Click buttons and type keyboard input
• Manage windows, apps, and Spaces

What You Can Do

• Screen capture - Motion-aware screenshots, region selection, video ingest and frame extraction
• App management - Launch, quit, relaunch, hide, show, or switch to any application
• Window control - Focus, move, resize, close, minimize, maximize, tile windows
• UI element targeting - Identify and interact with buttons, text fields, menus, and controls
• Keyboard input - Type text, send hotkeys (cmd+c), special keys (enter, tab, escape, arrows)
• Mouse and gestures - Click, double-click, right-click, drag, swipe, scroll (precise or natural)
• Clipboard operations - Read and write text, images, and file paths
• Menu interaction - Navigate and click menu bar items and context menus
• Annotated UI maps - Generate visual maps with clickable element IDs
• Space management - Create, switch, and organize macOS Spaces
• Scriptable - Define multi-step workflows in .peekaboo.json

Try Asking

• "Show me an annotated UI map of the current app with all clickable elements"
• "Click the Save button in this window"
• "Type 'Hello World' and press enter"
• "Capture a screenshot of the top-left quadrant"
• "Launch Slack and switch to the #general channel"
• "Resize the Chrome window to 1200x800"
• "Copy the selected text and show me what's in clipboard"
• "Drag this file to the Desktop"
• "Create a new Space and move this window there"

Pro Tips

• macOS only - requires Screen Recording + Accessibility permissions
• Use peekaboo see --annotate to identify UI targets before interacting
• Element IDs from annotated maps can be reused in automation scripts
• Natural scrolling mimics human behavior for more reliable interactions
• .peekaboo.json scripts enable complex multi-step automations
• Works with multi-display setups using screen targeting
• Keyboard hotkeys use + syntax: cmd+shift+n, ctrl+c

Plans

More Media Skills

• Text-to-Speech - Generate speech completely offline with zero API costs
• Video Frames - Extract frames from any video at precise timestamps
• Banana AI - Generate and edit images with Gemini 3 Pro
• AI Image Gen - Generate and batch-create images with multiple AI models
• Camera - Capture snapshots and video from network cameras
• GIF Search - Search, preview, and download GIFs from Tenor and Giphy

Explore: Integrations · Glossary · Solutions · Use cases · Examples · Comparisons · Templates · Blog · Docs