What problem does it solve? Manually verifying that a web feature works, that a deployment looks right, or that a bug is reproducible requires opening a browser, clicking through flows, and capturing evidence. This Skill gives an AI agent a persistent headless Chromium browser so it can navigate pages, interact with elements, and collect proof automatically at roughly 100ms per command. ## Core Features & Use Cases - Page Interaction & Assertions: Navigate URLs, click, fill forms, upload files, handle dialogs, and assert element states (visible, enabled, checked, focused) using accessibility-tree @refs from snapshots. - Visual Evidence & Diffing: Take plain or annotated screenshots, capture responsive layouts at mobile/tablet/desktop viewports, diff snapshots before and after actions, and compare two URLs side by side. - State Persistence & Handoff: Cookies, tabs, and login sessions persist between commands; when blocked by CAPTCHAs or MFA, hand off to a visible Chrome window and resume control afterward. - Use Case: After deploying a login flow, ask the agent to open the staging URL, fill credentials, submit the form, diff the snapshot to confirm the dashboard appeared, check the console for JS errors, and attach an annotated screenshot to the bug report. ## Quick Start Ask the agent to open your app's URL in the browser, test the login flow, and take a screenshot of the result.
