How does Peekaboo identify UI elements to click?

It uses a combination of snapshot IDs generated by the 'see' command, application-specific coordinates, and window titles to target elements accurately.

Does this skill require special macOS permissions?

Yes, Peekaboo requires both Screen Recording and Accessibility permissions to be granted in macOS System Settings to function correctly.

Can I use Peekaboo for web browser automation?

While Peekaboo can control browser windows and menus, it is primarily designed for native macOS UI automation across the entire operating system.

What is the Peekaboo skill for Claude Code?

Peekaboo is a specialized skill that allows Claude to use the Peekaboo CLI to interact with, capture, and automate the macOS user interface.

Is Peekaboo compatible with other operating systems?

No, Peekaboo is designed specifically for macOS (Darwin) and relies on Apple-specific APIs for UI inspection and control.

macOS UI Automation (Peekaboo)

Name: macOS UI Automation (Peekaboo)
Author: HarleyCoops

byHarleyCoops

Productivity & Workflow

Automates and inspects macOS user interfaces using the Peekaboo CLI to drive inputs, capture screens, and manage system windows.

About

Peekaboo is a specialized skill that empowers Claude to control the macOS operating system directly through a robust command-line interface. It enables advanced UI automation tasks such as capturing high-resolution screenshots, identifying UI elements via vision analysis, and simulating human-like keyboard and mouse interactions. By integrating with the macOS Accessibility and Screen Recording APIs, this skill allows for precise management of apps, windows, menus, and the Dock, making it an essential tool for developers building native automation scripts or performing end-to-end UI testing on Apple hardware.

Key Features

0 GitHub stars
Full application lifecycle management (launch, quit, focus, resize)
Comprehensive macOS UI control including clicks, drags, and swipes
Smart screen capture and window-specific visual analysis
Human-like input simulation with adjustable typing speeds and profiles
Snapshot-based element targeting for reliable script execution

Use Cases

Creating complex cross-app workflows and desktop-level RPA
Generating annotated UI maps and screenshots for documentation
Automated end-to-end testing for native macOS desktop applications

About

Key Features

0 GitHub stars
Full application lifecycle management (launch, quit, focus, resize)
Comprehensive macOS UI control including clicks, drags, and swipes
Smart screen capture and window-specific visual analysis
Human-like input simulation with adjustable typing speeds and profiles
Snapshot-based element targeting for reliable script execution

Use Cases

Creating complex cross-app workflows and desktop-level RPA
Generating annotated UI maps and screenshots for documentation
Automated end-to-end testing for native macOS desktop applications