testland/playwright-testing
Authors and remediates Playwright E2E tests across Chromium, Firefox, WebKit - `npm init playwright@latest` scaffolding, `playwright.config.ts` browser projects, accessibility-first locators (`getByRole`/`getByLabelText`) to replace brittle CSS selectors, web-first assertions to eliminate `waitForTimeout` flakiness, Page Object pattern, trace viewer debugging, sharded parallel execution with merged HTML reporting, mobile-web emulation via the `devices` catalog (viewport / DPR / touch per-device projects), the cross-browser matrix with branded channels (chrome / msedge) in references/browser-matrix.md, and GitHub Actions CI integration. Use for new test authoring, flakiness remediation, mobile-breakpoint regression, cross-browser matrix setup, and CI setup; for reviewing codegen output specifically, use a dedicated codegen-review pass.
91
91%
Does it follow best practices?
Impact
—
Average score across 10 eval scenarios
Passed
No findings from the security scan
Evaluation results
Checkout spec is flaky on CI
Every test signs in through the form before it can start
Export test hand-rolls its own waiting loop
Image comparison fails on things nobody changed
Lookups started failing with "resolved to 2 elements"
Mobile layout regressions reach production
Playwright suite has no CI story
Steps that open a second window or save a file only work on my machine
Suite depends on a partner API that throttles us
Support closes iPhone bugs because our "Safari" job is green
- Agent
- Claude Code
- Model
- Claude Sonnet 4.6