AI agent testing toolkit to generate, review, and debug Playwright and Cypress E2E tests. Four agent skills: generate tests from scratch with live exploration only on local/disposable or externally isolated approved non-production targets and explicit user approval; review existing specs or PR/diff-scoped test changes against 24 anti-patterns grouped by P0/P1/P2 severity — P0 must-fix (name-assertion mismatch, missing Then, error swallowing, Cypress uncaught:exception suppression, vacuous/non-retrying assertions, bypass patterns, focused test leak, missing assertions, missing auth setup), P1 should-fix (raw DOM queries, hard-coded sleeps, flaky test patterns, inconsistent POM usage, hardcoded credentials, missing await on expect, missing await on action, direct page action API, expect.soft overuse, module-level mutable state in test utilities, unmocked real-backend writes, optimistic UI without call proof), P2 nice-to-fix (YAGNI + zombie specs, manually-captured session-file dependency, fixture ignores render guards); debug failed Playwright tests from playwright-report/; debug failed Cypress tests from cypress/reports/.

🏪

voidmatcha/e2e-skills🏪Marketplace

AI agent testing toolkit for Playwright and Cypress: generate E2E tests from scratch, review existing specs against 24 anti-patterns (P0/P1/P2 silent-always-pass smells), and debug flaky failures from playwright-report/ or cypress/reports/. Agent Skills for Claude Code and Codex.