Shahfarzane

Capture the frontmost macOS application window as an appshot (screenshot + accessibility tree)

Check Appshots permissions and storage health

Fetch the most recent appshot without taking a new capture

List recent appshots with metadata

Search past appshots by app name, window title, URL, or captured text

Automate web browser interactions using natural language via CLI commands. Use when the user asks to browse websites, navigate web pages, extract data from websites, take screenshots, fill forms, click buttons, interact with web applications, monitor network requests, debug web pages, or extract design tokens. Triggers include "browse", "navigate to", "go to website", "open webpage", "extract data from webpage", "screenshot", "web scraping", "fill out form", "click on", "search for on the web", "check network requests", "debug page", "get design tokens", "extract colors", "analyze website design". When taking actions be as specific as possible.