skills.rest
JOHNNYWHITEMIKE
JOHNNYWHITEMIKECOMMUNITY
Explore all skills by this author →
GitHub

peekaboo

Automate macOS UI capture, inspection, and interaction via JSON snapshots.

Updated Apr 8, 2026
Search Tags:#macos#ui automation#screen capture#element targeting#click typing#scripting json#accessibility permissions
One-click install
npx skills add https://github.com/JOHNNYWHITEMIKE/openclaw --skill peekaboo-johnnywhitemike
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: peekaboo
Source: https://github.com/JOHNNYWHITEMIKE/openclaw/tree/main/openclaw/.openclaw/openclaw/skills/peekaboo
Command: npx skills add https://github.com/JOHNNYWHITEMIKE/openclaw --skill peekaboo-johnnywhitemike

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automating macOS UI tasks without reliably clicking the right window, button, or screen region wastes time and breaks whenever layouts change.

Core Features & Use Cases

  • UI capture and inspection: capture screens and create inspectable snapshots you can target by ID.
  • Targeted interaction: click, type, drag, scroll, swipe, and send hotkeys with UI-aware targeting and waits.
  • Automation with scripting support: run scripted capture/interaction flows and leverage JSON output for repeatable workflows (including permissions checks for Screen Recording and Accessibility).

Quick Start

Run peekaboo permissions, then run peekaboo see with annotation for the app and window you care about, and finally click the annotated target ID to drive the UI.

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 interaction without brittle manual coordinate clicks?▼

macOS UI automation uses UI-aware snapshots to target on-screen elements by ID instead of brittle manual coordinate clicks. You capture an annotated snapshot of the app window, then issue click, type, or drag commands referencing the target ID for reliable execution.

How do I capture screenshots and inspect UI elements on macOS for scripting?▼

To capture screenshots and inspect macOS UI elements for scripting, run a snapshot command with annotation enabled for your target app and window. This produces a JSON output mapping on-screen elements to targetable IDs for repeatable workflows.

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

Yes, macOS UI automation and screen capture scripts require Screen Recording and Accessibility permissions. You verify and grant these by running the permissions check command before executing any snapshot, click, or type automation flows.

Can I script repeatable click, type, and drag sequences using JSON output on macOS?▼

Yes, you can script repeatable click, type, and drag sequences using JSON output on macOS. After generating a JSON snapshot, you reference the extracted element IDs to build automated interaction flows with configurable input timing and waits.

Why do my macOS screen automation scripts break when the application window layout changes?▼

macOS screen automation scripts break when layouts change because they rely on fixed screen coordinates rather than UI-aware targeting. By capturing JSON snapshots and targeting elements by their annotated ID, your scripts remain stable across layout shifts.

Related Skills

Explore More Software Engineering Skills→
steipetesteipete
385.7k

peekaboo

Capture and control macOS UI elements via CLI commands.

Community
Advanced
diegoliriodiegolirio

setup-atlassian-mcp

Configure Atlassian MCP integration with a personal API token.

Community
Intermediate
yigitkonuryigitkonur
11

run-agent-browser

Drives browser automation via agent-browser CLI for navigation, DOM interaction, sessions, tabs, screenshots, and data extraction.

Community
Intermediate
freire19freire19

peekaboo

Capture and inspect macOS UI elements to drive deterministic input automation.

Community
Intermediate