gstack

What problem does it solve? Manually verifying web pages, user flows, and deployments is slow and error-prone. This Skill gives an AI agent a persistent headless Chromium browser so it can navigate pages, click elements, fill forms, assert state, and capture annotated screenshots as bug evidence. ## Core Features & Use Cases - Interactive page control: Navigate URLs, snapshot accessibility trees with @e refs, click, fill, hover, upload files, and handle dialogs through a single CLI binary. - State verification and diffing: Assert element visibility, enabled/checked state, console errors, and network failures, and diff snapshots before and after actions to confirm changes. - Visual evidence capture: Take full-page, element, region, and responsive (mobile/tablet/desktop) screenshots, plus annotated screenshots labeling every interactive element. - Use Case: After deploying a new login flow, ask the agent to open the staging URL, fill credentials, submit the form, verify the dashboard appears, check the console for errors, and save an annotated screenshot as proof. ## Quick Start Ask the agent to open your site with gstack browse, walk through the login flow, and screenshot the result.