research

Record macOS screen with verification, retry logic, and format conversion for Discord, GitHub, JetBrains. Integrates with window-controller for window discovery.

Find text in images using EasyOCR, returning click coordinates. Works on any image (screenshots, UI captures, etc.) without requiring accessibility permissions. Useful for UI automation, finding buttons/labels in screenshots, and extracting text positions.

Find and switch to macOS Spaces/Desktops by application name. Use when asked to find which Space an app is on, switch to a Space containing a specific app (like GoLand, IntelliJ, VS Code), navigate between Mission Control Spaces, or detect full-screen application windows across desktops.

Capture macOS screenshots with verification and retry logic. Integrates with window-controller for window discovery.

Find, activate, and screenshot macOS windows across Spaces. Filter by app name, window title, process path, or command line. Useful for automating window workflows, capturing screenshots for documentation, and distinguishing between production and sandbox/dev instances (e.g., JetBrains IDEs).

Complete guide for investigating and implementing web browser automation. Use when you need to automate browser interactions but don't know the DOM structure, element IDs, or what tools to use. Covers investigation methodology, selector discovery, tool selection, debugging techniques, and common pitfalls for any web automation scenario.

Programmatic control of Chrome and Firefox browsers via CDP (Chrome DevTools Protocol) and Marionette. Connect to running browser instances for tab management, navigation, DOM interaction, form filling, JavaScript execution, and screenshots. Useful for browser automation, web scraping, and testing.