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.
npx claudepluginhub c0x12c/ai-toolkit --plugin ai-toolkitThis skill uses the workspace's default tool permissions.
Test web apps with a real browser. Find bugs users would find.
Delivers DB-free sandbox API regression tests for Next.js/Vitest to catch AI blind spots in self-reviewed code changes like API routes and backend logic.
Implements Clean Architecture in Android and Kotlin Multiplatform projects: module layouts, dependency rules, UseCases, Repositories, domain models, and data layers with Room, SQLDelight, Ktor.
Provides process, architecture, review, hiring, and testing guidelines for engineering teams relying on AI code generation.
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.