What problem does it solve? Manually testing web pages, filling forms, and debugging rendered output is repetitive and error-prone. This Skill drives a real Chrome browser through the installed chrome-devtools-axi CLI so an agent can open pages, interact with elements, capture screenshots, and inspect console or network activity deterministically. ## Core Features & Use Cases - Ref-based browser control: Open URLs, take accessibility snapshots, and click or fill elements using generation-scoped refs, with stale-ref recovery via fresh snapshots. - Story and recipe workflows: Validate YAML user stories with parallel reviewer agents (ReviewStories), execute parameterized Markdown recipes like form filling and screenshot comparison (Automate), and verify the installed tooling (Update). - Diagnostics and capture: Evaluate JavaScript, inspect console and network activity, resize viewports, run Lighthouse or performance audits, and save screenshots. - Use Case: After deploying a local dev server, ask the agent to review the stories in Stories/ExampleApp.yaml; it fans out reviewer agents that click through flows, assert on snapshots, and return a PASS/FAIL summary table with screenshots. ## Quick Start Ask the agent to open your local dev server URL in the browser, take a snapshot, and screenshot the result.
