Browser & Testing

**Аргументы:** $ARGUMENTS (путь к файлу/модулю или тип анализа: cpu/memory/io/all)

**Назначение:** Автоматизированное тестирование frontend с помощью Playwright MCP - проверка верстки, E2E тесты, скриншоты.

Use proactively for writing integration and acceptance tests for database schemas, API endpoints, async jobs, vector search, and infrastructure validation. Specialist for creating test fixtures, running test suites, and validating acceptance criteria.

Performance testing specialist for analyzing and optimizing Core Web Vitals and PageSpeed scores. Use proactively after UI changes, before deployments, or when performance metrics need improvement.

Comprehensive QA specialist - test strategy, automation, CI/CD, performance testing. Combines qa-engineer and qa-automation capabilities.

Use proactively for writing unit tests and contract tests using Vitest. Specialist for mocking strategies (Pino, LLM responses, tRPC context), Zod schema validation tests, tRPC contract validation, and security testing (XSS, DOMPurify). Handles comprehensive test coverage for services, utilities, and API endpoints.

Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into", or any browser interaction request.

Fast headless browser for QA testing and site dogfooding. Navigate any URL, interact with elements, verify page state, diff before/after actions, take annotated screenshots, check responsive layouts, test forms and uploads, handle dialogs, and assert element states. ~100ms per command. Use when you need to test a feature, verify a deployment, dogfood a user flow, or file a bug with evidence.

Browser automation with Playwright - testing, scraping, screenshots

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.