performance-testing
Performance testing with Lighthouse and Web Vitals integration in Playwright. Use when measuring page load times, Core Web Vitals, Lighthouse audits, or performance budgets.
Performance testing with Lighthouse and Web Vitals integration in Playwright. Use when measuring page load times, Core Web Vitals, Lighthouse audits, or performance budgets.
Write, review, or debug end-to-end tests using Playwright. Use when creating test suites, fixing flaky tests, implementing UI interaction sequences, or ensuring test reliability. Invoke with /playwright-e2e or when user mentions e2e tests, Playwright, or test automation.
Toolkit for testing local web applications using Playwright. Use when verifying frontend functionality, debugging UI behavior, capturing browser screenshots, or viewing browser logs.
Test local web applications using Playwright for UI verification, debugging, screenshot capture, and end-to-end testing. Use when testing web apps, verifying UI behavior, or capturing screenshots of running applications.
Perform exploratory QA testing on web applications using Playwright. Navigate flows, analyze pages, find issues, and generate actionable reports with evidence.
Comprehensive performance testing framework for load testing, stress testing, and benchmarking. Measures throughput, latency percentiles (p50, p95, p99), and resource utilization. Identifies bottlenecks and detects performance regressions across releases.
Performance Test Agent. 성능 테스트 계획 및 실행을 담당합니다. Load Test, Lighthouse, Core Web Vitals 측정을 수행합니다.
Tests web applications with Playwright including E2E tests, locators, assertions, and visual testing. Use when writing end-to-end tests, testing across browsers, automating user flows, or debugging test failures. Triggers: "playwright", "e2e tests", "end-to-end testing", "cross-browser testing", "automated tests", "ui tests", "visual testing".
Browser-based E2E testing for feature verification. Use when running end-to-end tests, validating features in browser, verifying user flows, or testing feature completion.
Set up synthetic monitoring with Lighthouse CI and Playwright. Use when implementing automated performance testing, CI/CD performance gates, or proactive monitoring.
Open and analyze Playwright HTML test reports. Use when user asks to see test results, check test report, view test output, or analyze test failures.
Test cross-browser compatibility on Chrome, Firefox, Safari, and Edge using Playwright. Use when ensuring browser compatibility or fixing browser-specific issues.
Increase test coverage from 0% to 80%+ in ANY project, ANY testing framework
Autonomously build and test web applications using Playwright MCP server. Enables iterative development with automatic verification - make changes, run the app, visually verify, check for errors, and iterate. Use when building websites, debugging UI issues, or implementing features that need visual verification.
Analyze test coverage, identify gaps, suggest strategic test cases. Use when writing features, after bug fixes, or during test reviews. Ensures comprehensive coverage without over-testing.
Deep contextual grep for codebases. Expert at finding patterns, architectures, implementations, and answering "Where is X?", "Which file has Y?", and "Find code that does Z" questions. Use when exploring unfamiliar codebases, finding specific implementations, understanding code organization, discovering patterns across multiple files, or locating functionality in a project. Supports three thoroughness levels: quick, medium, very thorough.
Deep contextual grep for codebases. Expert at finding patterns, architectures, implementations, and answering "Where is X?", "Which file has Y?", and "Find code that does Z" questions. Use when exploring unfamiliar codebases, finding specific implementations, understanding code organization, discovering patterns across multiple files, or locating functionality in a project. Supports three thoroughness levels quick, medium, very thorough.
Use for token-expensive operations requiring multi-file analysis - codebase exploration, broad searches, architecture understanding, tracing flows, finding implementations across files. Uses MCP cursor-agent server (company pays) with clean async interface. Do NOT use for single-file analysis, explaining code already in immediate context, or pure reasoning tasks.
Analyze files in a codebase to understand structure, find patterns, extract metadata, and generate summaries. Use when exploring unfamiliar codebases, documenting project structure, or when users ask about file contents, organization, or relationships.
Auto-detects technology stack from existing project files (package.json, tsconfig, etc.). Use ONLY for existing projects with established code to discover what's already installed. For NEW projects where tech stack hasn't been decided, use stack-advisor skill instead.