What problem does it solve? AI agents and scripts often need to interact with websites—logging in, filling forms, clicking buttons, or scraping content—but raw DOM parsing is slow and token-heavy. This Skill provides a CLI that drives Chrome via CDP with compact element refs, making web automation fast and context-efficient. ## Core Features & Use Cases - Snapshot-Based Interaction: Get interactive elements as compact refs (@e1, @e2) and click, fill, or select them directly, reducing token usage dramatically. - Authentication & Sessions: Save and restore login state, use persistent profiles, encrypted auth vaults, and named sessions for parallel isolated browsing. - Capture & Verification: Take annotated screenshots, record video, save PDFs, diff page states, and extract text or structured data from any page. - Use Case: Automate an end-to-end test of a web app's signup flow—open the page, snapshot the form, fill fields by ref, submit, and verify the redirect to the dashboard. ## Quick Start Ask the agent to open a website, snapshot its interactive elements, fill in the login form, and take a screenshot of the result.
