From ai-toolkit
Run real browser QA with Playwright on web apps: checks page health, console/network errors, layout/responsiveness, interactions, navigation, data display; generates reports. Use for frontend feature tests, pre-PR UI verification, post-deploy smoke tests, visual bug investigations.
How this skill is triggered — by the user, by Claude, or both
Slash command
/ai-toolkit:browser-qaThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Test web apps with a real browser. Find bugs users would find.
Test web apps with a real browser. Find bugs users would find.
Every page gets these checks:
See playwright-snippets.md for ready-to-use Playwright code (page tests, mobile viewport, form testing, screenshot on failure) and the QA report template.
networkidle waits forever on apps with websockets or polling. Use domcontentloaded or a specific element selector instead if the app has live connections.page.click() on invisible elements passes silently. Always verify the element is visible before interacting. Use await expect(locator).toBeVisible() first.hasTouch: true in the browser context, not just the viewport size.console.error and failed network requests are bugs.npx claudepluginhub c0x12c/ai-toolkit --plugin ai-toolkitAutomates QA on staging/preview web apps: smoke tests, interactions, visual regression, accessibility audits via Playwright/Puppeteer/Chrome. Use post-deploy or PR reviews.
Automates visual testing and UI interaction verification using browser automation (Playwright/Puppeteer) after deploying features to staging/preview.
Automates systematic web app QA testing with issue taxonomy, health scoring, and regression tracking. Supports browser automation via Playwright, Puppeteer, or Cypress.