Automates post-deployment browser QA: smoke tests, UI interaction checks, visual regression and accessibility audits.
- What it does
- Guides an agent through four browser-automation QA phases on a deployed page: smoke testing (console errors, failed requests, Core Web Vitals, screenshots), interaction testing (navigation links, form success and error states, auth flows, key user paths), visual regression across three breakpoints, and accessibility checks with axe-core or equivalent. It produces a structured QA report with per-area findings and a release conclusion.
- When to use it
- Use after deploying to staging or a preview environment, when verifying cross-page UI behavior, before release to confirm layout, forms and interactions work, when reviewing front-end PRs, or for accessibility and responsive testing.
- Requirements
- A browser automation MCP such as claude-in-chrome, Playwright via browserbase, or Puppeteer, plus network access to the target URL. Accessibility checks need axe-core or an equivalent tool. No scripts ship with the skill; it is instructions only.