test
Runs end-to-end tests against the deployed application using Playwright browser automation. Use when verifying a deployment works correctly.
What this skill does
# Test — Verify Your Deployment You are running end-to-end tests against the deployed application using the Playwright MCP server to automate a real browser. ## When This Skill Activates - User wants to test the deployed application - User asks "does it work?" or "let's verify the deployment" - User says "test my site" or "check my deployment" - Deployment just completed and user wants verification ## Prerequisites - Application is deployed (`.migration/outputs.json` exists with URLs) - If not deployed, suggest deploying first ## What To Do ### Phase 1: Plan Read `.migration/outputs.json` to get deployed URLs, then show the test plan: 1. **Explain what we'll test:** "I'll open a real browser and test your deployed app. Playwright automates the browser — clicking buttons, filling forms, and checking results — just like a real user would." 2. **Test plan based on what's deployed:** **Core Tests (always run):** - Site loads successfully (CloudFront URL returns 200) - Main page renders correctly - No console errors **API Tests (if API deployed):** - Each API endpoint returns expected data - POST endpoints create data correctly - Error handling works (invalid inputs return proper errors) **Auth Tests (if Cognito deployed):** - Sign-up form works - Sign-in form works - Protected routes reject unauthenticated requests - Protected routes work after sign-in **Database Tests (if DynamoDB deployed):** - Create, read, update, delete operations work - Data persists across requests ### Phase 2: Execute Use the Playwright MCP server to run each test: 1. **Navigate to the site:** - Use `browser_navigate` to open the CloudFront URL - Take a snapshot to verify it loaded - Check for console errors with `browser_console_messages` 2. **Test the frontend:** - Use `browser_snapshot` to check the page content - Verify key elements are present - Take a screenshot for the user 3. **Test API endpoints:** - Use `browser_navigate` to call API endpoints directly - Or use `browser_evaluate` to make fetch calls from the browser - Verify response status codes and data 4. **Test auth flow (if applicable):** - Navigate to sign-up page - Fill in registration form with test credentials using `browser_fill_form` - Submit and verify success - Navigate to sign-in page - Fill in login form - Verify authenticated state - Test a protected API route 5. **Test CRUD operations (if applicable):** - Create a new item through the UI or API - Read it back - Update it - Delete it - Verify it's gone ### Phase 3: Report Create a test results summary: ```markdown # Test Results — [Date] ## Summary - Passed: [N] tests - Failed: [N] tests - Warnings: [N] ## Details ### Frontend - Site loads at [URL] - No console errors - Main page renders correctly ### API - GET /api/items returns data - POST /api/items creates item - DELETE /api/items/:id returns 500 — [details] ### Auth (if tested) - Sign-up works - Sign-in works - Protected routes require auth ### Screenshots [Include screenshots of key pages] ``` For any failures: - Explain what went wrong in simple terms - Suggest specific fixes - Offer to help fix the issues Save results to `.migration/test-results.md` ### Phase 4: Next Steps - If all tests pass: "Everything works! Your app is live and functional." - If some tests fail: "Let's fix these issues. The most important one is [X] because [reason]." - Remind about cleanup: "When you're done, ask me to tear down the resources to stop any costs." ## Important Notes ### Playwright MCP Usage - Use `browser_snapshot` (accessibility tree) for checking content — more reliable than screenshots - Use `browser_take_screenshot` for visual evidence to show the user - Use `browser_console_messages` to catch JavaScript errors - Use `browser_network_requests` to debug API issues - Always close the browser when done with `browser_close` ### Test Data - Use clearly fake data for testing (e.g., [email protected]) - Clean up test data after testing if possible - Don't use real email addresses for Cognito sign-up tests ### Timeouts - CloudFront may take a few minutes to propagate after deployment - Lambda cold starts may cause first request to be slow - If a test fails due to timeout, try once more before reporting failure
Related in Code Review
gstack
IncludedFast headless browser for QA testing and site dogfooding. Navigate pages, interact with elements, verify state, diff before/after, take annotated screenshots, test responsive layouts, forms, uploads, dialogs, and capture bug evidence. Use when asked to open or test a site, verify a deployment, dogfood a user flow, or file a bug with screenshots. (gstack)
startup-due-diligence
IncludedLegal due diligence review for seed-stage and Series A startups (US, Delaware C-Corp focus). Supports both investor and founder perspectives. Capabilities include: (1) Interactive document review and issue spotting; (2) Document request list generation; (3) Cap table and SAFE/convertible note analysis; (4) Red flag identification with severity ratings; (5) Diligence report generation. TRIGGERS: due diligence, DD, startup investment, cap table review, Series A, seed round, investor diligence, legal review startup, SAFE analysis, convertible note, 409A, founder vesting.
interview-master
IncludedThis skill should be used when the user asks to "generate interview questions", "prepare for interview", "optimize resume", "conduct mock interview", "analyze git commits for resume", "generate resume from code", "review my resume", or mentions interview preparation, career assistance, or extracting project experience from git history. Provides comprehensive interview and career development guidance for both job seekers and interviewers.
fix-issue
IncludedFixes GitHub issues using parallel analysis agents for root cause investigation, code exploration, and regression detection. Reads issue context from gh CLI, searches codebase and memory for related patterns, generates a fix with tests, and links the resolution back to the issue via PR. Includes prevention analysis to avoid recurrence. Use when debugging errors, resolving regressions, fixing bugs, or triaging issues.
sf-apex
IncludedGenerates and reviews Salesforce Apex code with 150-point scoring. TRIGGER when: user writes, reviews, or fixes Apex classes, triggers, test classes, batch/queueable/schedulable jobs, or touches .cls/.trigger files. DO NOT TRIGGER when: LWC JavaScript (use sf-lwc), Flow XML (use sf-flow), SOQL-only queries (use sf-soql), or non-Salesforce code.
swift-development
IncludedComprehensive Swift development for building, testing, and deploying iOS/macOS applications. Use when Claude needs to: (1) Build Swift packages or Xcode projects from command line, (2) Run tests with XCTest or Swift Testing framework, (3) Manage iOS simulators with simctl, (4) Handle code signing, provisioning profiles, and app distribution, (5) Format or lint Swift code with SwiftFormat/SwiftLint, (6) Work with Swift Package Manager (SPM), (7) Implement Swift 6 concurrency patterns (async/await, actors, Sendable), (8) Create SwiftUI views with MVVM architecture, (9) Set up Core Data or SwiftData persistence, or any other Swift/iOS/macOS development tasks.