Agent skill
frontend-testing
Test web applications using Chrome DevTools. Use for visual regression testing, performance analysis, accessibility checks, console error detection, and automated UI testing. Works with live URLs or local development servers.
Install this agent skill to your Project
npx add-skill https://github.com/timogilvie/wavemill/tree/main/skills/frontend-testing
SKILL.md
Frontend Testing Skill
Purpose
Automate frontend testing using Chrome DevTools Protocol to verify UI functionality, performance, and correctness.
When to Use This Skill
- Testing UI components in a browser
- Checking for console errors or warnings
- Performance profiling of web pages
- Visual regression testing with screenshots
- Automated user flows (clicking, typing, form filling)
- Network request validation
- Accessibility testing
Instructions
1. Basic Page Testing
- Use
navigate_pageto load the target URL - Use
wait_forto ensure page is ready (e.g., wait for specific elements) - Use
take_screenshotto capture the current state - Use
list_console_messagesto check for errors or warnings
2. Performance Testing
- Use
performance_start_tracebefore loading the page - Navigate to the target URL
- Use
performance_stop_traceto capture metrics - Use
performance_analyze_insightto get actionable insights
3. Interactive Testing
- Use
clickto interact with buttons or links - Use
fillorfill_formto test form inputs - Use
press_keyfor keyboard interactions - Use
hoverto test hover states - Take screenshots after each interaction to verify state changes
4. Network Testing
- Navigate to the page
- Use
list_network_requeststo see all requests - Use
get_network_requestto inspect specific requests - Verify API responses, status codes, and timing
5. Multi-Page Testing
- Use
new_pageto open additional tabs - Use
list_pagesto see all open tabs - Use
select_pageto switch between tabs - Use
close_pagewhen done
Best Practices
- Always wait for page load before interacting (
wait_for) - Take screenshots before and after interactions for debugging
- Check console messages after page load to catch JavaScript errors
- Use meaningful filenames for screenshots (include timestamp or test name)
- Clean up by closing pages when tests are complete
Common Testing Patterns
Pattern: Basic Smoke Test
1. Navigate to URL
2. Wait for page load
3. Check console for errors
4. Take screenshot
5. Report results
Pattern: Form Submission Test
1. Navigate to form page
2. Fill form fields using `fill_form`
3. Take screenshot of filled form
4. Click submit button
5. Wait for response/redirect
6. Verify success message or URL change
7. Check console for errors
Pattern: Performance Audit
1. Start performance trace
2. Navigate to URL
3. Wait for page to fully load
4. Stop performance trace
5. Analyze trace for insights
6. Report metrics (LCP, FID, CLS, etc.)
Example Usage
User: "Test the homepage at localhost:3000" Response: Navigate, wait for load, check console, take screenshot, report findings
User: "Profile the performance of example.com" Response: Start trace, navigate, stop trace, analyze, report metrics
User: "Test the login flow with credentials test@example.com / password123" Response: Navigate to login, fill form, submit, verify redirect, check for errors
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
linear-task-selector
Fetch tasks from Linear backlog and handle user selection. Saves selected task context for use in feature/bug/plan workflows. Reduces context usage by consolidating Linear API interactions.
document-orchestrator
Generate structured markdown documents (PRDs, tasks, investigation plans) from templates based on workflow type. Creates directory structure and manages document lifecycle for feature, bug, and plan workflows.
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
issue-writer
Expand Linear issues into comprehensive task packets that enable autonomous AI agent execution with minimal oversight. Transforms brief issue summaries into detailed specs with context, constraints, success criteria, and validation steps.
git-workflow-manager
Handle git branch creation, commits, and PR creation for feature and bugfix workflows. Follows git best practices with structured commit messages and proper PR formatting.
edit-article
Edit and improve articles by restructuring sections, improving clarity, and tightening prose. Use when user wants to edit, revise, or improve an article draft.
Didn't find tool you were looking for?