What problem does it solve? Manually interacting with websites for testing, scraping, or repetitive form entry is slow and error-prone. This Skill gives an AI agent full programmatic control of a Chrome/Chromium browser through the agent-browser CLI, so tasks like logging in, filling forms, clicking through flows, and capturing pages run as deterministic commands. ## Core Features & Use Cases - Snapshot-and-Ref Interaction: Get compact accessibility snapshots with element refs (@e1, @e2) and use them to click, fill, select, and scroll without parsing raw HTML. - Authentication & Sessions: Reuse login state via auth vault, persistent profiles, session names, or saved state files, including OAuth and 2FA flows. - Capture & Verification: Take screenshots (including annotated and full-page), save PDFs, record video, and diff page states to verify actions worked. - Use Case: Test a signup flow end-to-end by opening the page, snapshotting the form, filling each field by ref, submitting, and diffing the result against the baseline snapshot. ## Quick Start Ask the agent to open a website with agent-browser, take an interactive snapshot, and fill out and submit the login form using the discovered element refs.
