peekaboo

Automate macOS UI by capturing screenshots and executing input events.

Updated Mar 26, 2026
One-click install
npx skills add https://github.com/tedtv1007-ctrl/milk-skills-library --skill peekaboo-tedtv1007-ctrl
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: peekaboo
Source: https://github.com/tedtv1007-ctrl/milk-skills-library/tree/main/peekaboo
Command: npx skills add https://github.com/tedtv1007-ctrl/milk-skills-library --skill peekaboo-tedtv1007-ctrl

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill solves the challenge of automating legacy or non-API-driven macOS applications by providing a programmatic interface to interact with UI elements, windows, and system menus.

Core Features & Use Cases

  • UI Automation: Perform clicks, drags, typing, and hotkey sequences on any macOS application.
  • Visual Inspection: Capture screenshots, inspect UI element hierarchies, and analyze screen content for intelligent decision-making.
  • System Management: Control app lifecycle, window positioning, and system-level interactions like the Dock and Menu Bar.
  • Use Case: Automate a repetitive data entry workflow in a desktop application that lacks a public API by using visual snapshots to locate fields and simulate keyboard input.

Quick Start

Use the peekaboo skill to list all open applications and then click on the window titled Login in the Safari browser.

Frequently Asked Questions about peekaboo

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate macOS UI interactions for desktop applications that lack a public API?

macOS UI automation for non-API-driven applications is achieved by programmatically capturing screen snapshots and executing input events on UI elements. This Skill facilitates complex workflows involving application management, window manipulation, and gesture-based interaction on desktop environments.

Do I need special permissions to run macOS UI automation and screen capture tasks?

macOS UI automation and screen capture tasks require the Peekaboo CLI binary and explicit macOS accessibility permissions to function correctly. These prerequisites allow the tool to execute input events and capture visual snapshots of system interfaces.

Can I use visual inspection to locate UI elements and simulate keyboard input?

Visual inspection locates UI elements by capturing screenshots and inspecting UI element hierarchies to analyze screen content. You can then simulate keyboard input, perform clicks, drags, and execute hotkey sequences on any macOS application based on those visual findings.

What is the best way to control application lifecycle and window positioning during desktop automation?

Desktop automation for application lifecycle and window positioning is handled through system-level interactions. You can control app lifecycle, manipulate window positions, and interact with system components like the Dock and Menu Bar programmatically.

Why does my macOS screen capture automation fail to interact with system menus and the Dock?

Screen capture automation fails when macOS accessibility permissions are not granted to the Peekaboo CLI binary. System-level interactions involving the Dock, Menu Bar, and window manipulation require explicit accessibility access to execute input events correctly.