Browser automation and web testing with Playwright - auto-detects dev servers, creates test scripts, captures screenshots

version
1.0.0
GitHub stars
12

Install

/plugin install ui-tests@claude-craftkit

Run it inside Claude Code after adding the marketplace with /plugin marketplace add marcioaltoe/claude-craftkit.

Contents

Discovered from source

Skills 1

IMPORTANT - Path Resolution: This skill is installed globally but saves outputs to the user's working directory. Always pass CWD environment variable when executing commands to ensure outputs go to the correct location.

Common installation paths:

  • Plugin system: ~/.claude/plugins/marketplaces/claude-craftkit/plugins/ui-tests/skills/web-tests
  • Manual global: ~/.claude/skills/web-tests
  • Project-specific: <project>/.claude/skills/web-tests

Web Testing & Browser Automation

General-purpose browser automation skill. I'll write custom Playwright code for any automation task you request and execute it via the universal executor.

CRITICAL WORKFLOW - Follow these steps in order:

  1. Auto-detect dev servers - For localhost testing, ALWAYS run server detection FIRST:

    cd $SKILL_DIR && node -e "require('./lib/helpers').detectDevServers().then(servers => console.log(JSON.stringify(servers)))"
    
    • If 1 server found: Use it automatically, inform user
    • If multiple servers found: Ask user which one to test
    • If no servers found: Ask for URL or offer to help start dev server
  2. Write scripts to user's working directory - Save to .web-tests/scripts/test-*.js in user's repo

  3. Use visible browser by default - Always use headless: false unless user specifically requests headless mode

  4. Parameterize URLs - Always make URLs configurable via constant at top of script

How It Works

  1. You describe what you want to test/automate
  2. I auto-detect running dev servers (or ask for URL if testing external site)
  3. I write custom Playwright code in .web-tests/scripts/test-*.js (in user's working directory)
  4. I execute it via: CWD=$(pwd) cd $SKILL_DIR && node run.js .web-tests/scripts/test-*.js
  5. Results displayed in real-time, browser window visible for debugging
  6. Screenshots automatically saved to .web-tests/screenshots/

Setup (First Time)

cd $SKILL_DIR
npm run setup

This installs Playwright and Chromium browser. Only needed once.

Execution Pattern

Step 1: Detect dev servers (for localhost testing)

cd $SKILL_DIR && node -e "require('./lib/helpers').detectDevServers().then(s => console.log(JSON.stringify(s)))"

Step 2: Write test script to user's .web-tests/scripts/ with URL parameter

// .web-tests/scripts/test-page.js
const { chromium } = require("playwright");

// Parameterized URL (detected or user-provided)
const TARGET_URL = "http://localhost:3001"; // <-- Auto-detected or from user

(async () => {
  const browser = await chromium.launch({ headless: false });
  const page = await browser.newPage();

  await page.goto(TARGET_URL);
  console.log("Page loaded:", await page.title());

  await page.screenshot({
    path: ".web-tests/screenshots/page.png",
    fullPage: true,
  });
  console.log("📸 Screenshot saved to .web-tests/screenshots/page.png");

  await browser.close();
})();

Step 3: Execute from skill directory with CWD

CWD=$(pwd) cd $SKILL_DIR && node run.js $(pwd)/.web-tests/scripts/test-page.js

Common Patterns

Test a Page (Multiple Viewports)

// .web-tests/scripts/test-responsive.js
const { chromium } = require("playwright");
const helpers = require("$SKILL_DIR/lib/helpers"); // Path will be resolved

const TARGET_URL = "http://localhost:3001"; // Auto-detected

(async () => {
  const browser = await chromium.launch({ headless: false, slowMo: 100 });
  const page = await browser.newPage();

  // Desktop test
  await page.setViewportSize({ width: 1920, height: 1080 });
  await page.goto(TARGET_URL);
  console.log("Desktop - Title:", await page.title());
  await helpers.takeScreenshot(page, "desktop"); // Saves to .web-tests/screenshots/

  // Mobile test
  await page.setViewportSize({ width: 375, height: 667 });
  await helpers.takeScreenshot(page, "mobile");

  await browser.close();
})();

Test Login Flow

// .web-tests/scripts/test-login.js
const { chromium } = require("playwright");

const TARGET_URL = "http://localhost:3001"; // Auto-detected

(async () => {
  const browser = await chromium.launch({ headless: false });
  const page = await browser.newPage();

  await page.goto(`${TARGET_URL}/login`);

  await page.fill('input[name="email"]', "test@example.com");
  await page.fill('input[name="password"]', "password123");
  await page.click('button[type="submit"]');

  // Wait for redirect
  await page.waitForURL("**/dashboard");
  console.log("✅ Login successful, redirected to dashboard");

  await browser.close();
})();

Fill and Submit Form

// .web-tests/scripts/test-form.js
const { chromium } = require("playwright");
const helpers = require("$SKILL_DIR/lib/helpers");

const TARGET_URL = "http://localhost:3001"; // Auto-detected

(async () => {
  const browser = await chromium.launch({ headless: false, slowMo: 50 });
  const page = await browser.newPage();

  await page.goto(`${TARGET_URL}/contact`);

  await page.fill('input[name="name"]', "John Doe");
  await page.fill('input[name="email"]', "john@example.com");
  await page.fill('textarea[name="message"]', "Test message");

  await helpers.takeScreenshot(page, "form-filled");
  await page.click('button[type="submit"]');

  // Verify submission
  await page.waitForSelector(".success-message");
  console.log("✅ Form submitted successfully");
  await helpers.takeScreenshot(page, "form-success");

  await browser.close();
})();

Check for Broken Links

// .web-tests/scripts/test-broken-links.js
const { chromium } = require("playwright");

const TARGET_URL = "http://localhost:3001";

(async () => {
  const browser = await chromium.launch({ headless: false });
  const page = await browser.newPage();

  await page.goto(TARGET_URL);

  const links = await page.locator('a[href^="http"]').all();
  const results = { working: 0, broken: [] };

  for (const link of links) {
    const href = await link.getAttribute("href");
    try {
      const response = await page.request.head(href);
      if (response.ok()) {
        results.working++;
      } else {
        results.broken.push({ url: href, status: response.status() });
      }
    } catch (e) {
      results.broken.push({ url: href, error: e.message });
    }
  }

  console.log(`✅ Working links: ${results.working}`);
  console.log(`❌ Broken links:`, results.broken);

  await browser.close();
})();

Take Screenshot with Error Handling

// .web-tests/scripts/screenshot-with-error-handling.js
const { chromium } = require("playwright");
const helpers = require("$SKILL_DIR/lib/helpers");

const TARGET_URL = "http://localhost:3001";

(async () => {
  const browser = await chromium.launch({ headless: false });
  const page = await browser.newPage();

  try {
    await page.goto(TARGET_URL, {
      waitUntil: "networkidle",
      timeout: 10000,
    });

    await helpers.takeScreenshot(page, "page-success");
    console.log("📸 Screenshot saved successfully");
  } catch (error) {
    console.error("❌ Error:", error.message);
    await helpers.takeScreenshot(page, "page-error");
  } finally {
    await browser.close();
  }
})();

Test Responsive Design (Full)

// .web-tests/scripts/test-responsive-full.js
const { chromium } = require("playwright");
const helpers = require("$SKILL_DIR/lib/helpers");

const TARGET_URL = "http://localhost:3001"; // Auto-detected

(async () => {
  const browser = await chromium.launch({ headless: false });
  const page = await browser.newPage();

  const viewports = [
    { name: "Desktop", width: 1920, height: 1080 },
    { name: "Tablet", width: 768, height: 1024 },
    { name: "Mobile", width: 375, height: 667 },
  ];

  for (const viewport of viewports) {
    console.log(
      `Testing ${viewport.name} (${viewport.width}x${viewport.height})`
    );

    await page.setViewportSize({
      width: viewport.width,
      height: viewport.height,
    });

    await page.goto(TARGET_URL);
    await page.waitForTimeout(1000);

    await helpers.takeScreenshot(page, viewport.name.toLowerCase());
  }

  console.log("✅ All viewports tested");
  await browser.close();
})();

Inline Execution (Simple Tasks)

For quick one-off tasks, you can execute code inline without creating files:

# Take a quick screenshot
cd $SKILL_DIR && CWD=$(pwd) node run.js "
const browser = await chromium.launch({ headless: false });
const page = await browser.newPage();
await page.goto('http://localhost:3001');
await helpers.takeScreenshot(page, 'quick-test');
console.log('Screenshot saved');
await browser.close();
"

When to use inline vs files:

  • Inline: Quick one-off tasks (screenshot, check if element exists, get page title)
  • Files: Complex tests, responsive design checks, anything user might want to re-run

Available Helpers

Optional utility functions in lib/helpers.js:

const helpers = require("./lib/helpers");

// Detect running dev servers (CRITICAL - use this first!)
const servers = await helpers.detectDevServers();
console.log("Found servers:", servers);

// Safe click with retry
await helpers.safeClick(page, "button.submit", { retries: 3 });

// Safe type with clear
await helpers.safeType(page, "#username", "testuser");

// Take timestamped screenshot (auto-saves to .web-tests/screenshots/)
await helpers.takeScreenshot(page, "test-result");

// Handle cookie banners
await helpers.handleCookieBanner(page);

// Extract table data
const data = await helpers.extractTableData(page, "table.results");

See lib/helpers.js for full list.

Directory Structure

When testing, the skill creates this structure in the user's working directory:

user-repo/
└── .web-tests/
    ├── scripts/          # Test scripts (reusable)
    │   ├── test-login.js
    │   ├── test-form.js
    │   ├── test-responsive.js
    │   └── test-broken-links.js
    └── screenshots/      # Screenshots with timestamps
        ├── desktop-2025-10-23T12-30-45.png
        ├── mobile-2025-10-23T12-30-51.png
        └── form-success-2025-10-23T12-31-05.png

Tips

  • CRITICAL: Detect servers FIRST - Always run detectDevServers() before writing test code for localhost testing
  • Save to .web-tests/ - Write scripts to .web-tests/scripts/, screenshots auto-save to .web-tests/screenshots/
  • Parameterize URLs - Put detected/provided URL in a TARGET_URL constant at the top of every script
  • DEFAULT: Visible browser - Always use headless: false unless user explicitly asks for headless mode
  • Headless mode - Only use headless: true when user specifically requests "headless" or "background" execution
  • Slow down: Use slowMo: 100 to make actions visible and easier to follow
  • Wait strategies: Use waitForURL, waitForSelector, waitForLoadState instead of fixed timeouts
  • Error handling: Always use try-catch for robust automation
  • Console output: Use console.log() to track progress and show what's happening
  • Use helpers: The helpers.takeScreenshot() automatically saves to .web-tests/screenshots/

Troubleshooting

Playwright not installed:

cd $SKILL_DIR && npm run setup

Module not found: Ensure running from skill directory via run.js wrapper with CWD set

Browser doesn't open: Check headless: false and ensure display available

Element not found: Add wait: await page.waitForSelector('.element', { timeout: 10000 })

Screenshots not in .web-tests/: Make sure CWD environment variable is set when executing

Example Usage

User: "Test if the marketing page looks good"

Claude: I'll test the marketing page across multiple viewports. Let me first detect running servers...
[Runs: detectDevServers()]
[Output: Found server on port 3001]
I found your dev server running on http://localhost:3001

[Writes custom automation script to .web-tests/scripts/test-marketing.js with URL parameterized]
[Runs: CWD=$(pwd) cd $SKILL_DIR && node run.js .web-tests/scripts/test-marketing.js]
[Shows results with screenshots from .web-tests/screenshots/]
User: "Check if login redirects correctly"

Claude: I'll test the login flow. First, let me check for running servers...
[Runs: detectDevServers()]
[Output: Found servers on ports 3000 and 3001]
I found 2 dev servers. Which one should I test?
- http://localhost:3000
- http://localhost:3001

User: "Use 3001"

[Writes login automation to .web-tests/scripts/test-login.js]
[Runs: CWD=$(pwd) cd $SKILL_DIR && node run.js .web-tests/scripts/test-login.js]
[Reports: ✅ Login successful, redirected to /dashboard]

Notes

  • Each automation is custom-written for your specific request
  • Not limited to pre-built scripts - any browser task possible
  • Auto-detects running dev servers to eliminate hardcoded URLs
  • Test scripts saved to .web-tests/scripts/ for reusability
  • Screenshots automatically saved to .web-tests/screenshots/ with timestamps
  • Code executes reliably with proper module resolution via run.js
  • Works as global tool - no per-repo installation needed

Commands 3

--url --check-type

Check Webpage for Issues

Automatically check webpages for common issues like broken links, console errors, missing images, or accessibility problems.

Works from any directory - Saves report to your working directory's .web-tests/ folder.

How It Works

When you run /check, Claude will:

  1. Auto-detect dev server (or use provided URL)
  2. Create check script in .web-tests/scripts/
  3. Run automated checks based on check-type
  4. Generate report in .web-tests/reports/
  5. Show summary of findings

Usage

# Check for broken links
/check --check-type links

# Check for console errors
/check --url http://localhost:3001 --check-type console

# Check for missing images
/check --check-type images

# Check accessibility
/check --check-type a11y

# Check all issues
/check --check-type all

Check Types

  • links - Find broken links (404s, timeouts)
  • console - Capture JavaScript errors and warnings
  • images - Check for missing or broken images
  • a11y - Basic accessibility checks (ARIA, alt text, etc.)
  • performance - Basic performance metrics
  • all - Run all checks

What Claude Will Do

  1. Auto-detect dev server (if no URL provided)
  2. Create check script in .web-tests/scripts/check-{type}-{timestamp}.js
  3. Execute checks with: CWD=$(pwd) cd <skill-dir> && node run.js .web-tests/scripts/check-*.js
  4. Generate report in .web-tests/reports/
  5. Display summary of issues found

Output Structure

your-repo/
└── .web-tests/
    ├── scripts/
    │   └── check-links-2025-10-23.js
    └── reports/
        └── check-links-2025-10-23.md

Report Contents

The report will include:

  • Summary - Total issues found
  • Details - Each issue with location and description
  • Severity - Critical, Warning, Info
  • Suggestions - How to fix each issue

Examples

# Check for broken links
/check --check-type links

# Check for console errors on specific page
/check --url http://localhost:3001/dashboard --check-type console

# Full health check
/check --check-type all

# Check accessibility
/check --url http://localhost:3001 --check-type a11y

What Gets Checked

Links:

  • External links (status codes)
  • Internal links (navigation)
  • Anchor links
  • Download links

Console:

  • JavaScript errors
  • Network failures
  • Console warnings

Images:

  • Missing images (404s)
  • Broken src attributes
  • Missing alt text

Accessibility:

  • Missing ARIA labels
  • Color contrast (basic)
  • Semantic HTML
  • Keyboard navigation

Performance:

  • Page load time
  • Resource sizes
  • Number of requests

Tips

  • Run before deployment - Catch issues early
  • Check after changes - Verify nothing broke
  • Commit reports - Track issues over time
  • Automated quality checks - Quick health check

See Also

  • /test - Run automated tests
  • /screenshot - Take screenshots

--url --viewports

Take Screenshots

Capture screenshots of web pages across different viewports. Screenshots are saved to .web-tests/screenshots/ in your working directory.

Works from any directory - Saves screenshots to your working directory's .web-tests/screenshots/ folder.

How It Works

When you run /screenshot, Claude will:

  1. Auto-detect dev server (or use provided URL)
  2. Create screenshot script in .web-tests/scripts/
  3. Capture screenshots across specified viewports
  4. Save to .web-tests/screenshots/ with timestamps
  5. Report file locations

Usage

# Screenshot current dev server
/screenshot

# Screenshot specific URL
/screenshot --url http://localhost:3001

# Screenshot across all viewports
/screenshot --viewports all

# Screenshot specific viewports
/screenshot --viewports desktop,mobile

# Screenshot external site
/screenshot --url https://example.com --viewports desktop

Viewport Options

  • all - Desktop (1920x1080), Tablet (768x1024), Mobile (375x667)
  • desktop - 1920x1080
  • tablet - 768x1024
  • mobile - 375x667
  • custom - Claude will ask for dimensions

What Claude Will Do

  1. Auto-detect dev server (if no URL provided)
  2. Create screenshot script in .web-tests/scripts/screenshot-{timestamp}.js
  3. Execute script with: CWD=$(pwd) cd <skill-dir> && node run.js .web-tests/scripts/screenshot-*.js
  4. Take screenshots across specified viewports
  5. Report file locations

Output Structure

your-repo/
└── .web-tests/
    ├── scripts/
    │   └── screenshot-2025-10-23.js
    └── screenshots/
        ├── desktop-2025-10-23T12-30-45.png
        ├── tablet-2025-10-23T12-30-48.png
        └── mobile-2025-10-23T12-30-51.png

Screenshot Options

Claude can configure:

  • Full page - Captures entire scrollable page (default: true)
  • Specific element - Screenshot just one element
  • Visible viewport - Only visible portion
  • Wait for load - Waits for page to fully load

Examples

# Quick screenshot of current dev server
/screenshot

# Screenshot homepage across all devices
/screenshot --url http://localhost:3001 --viewports all

# Mobile-only screenshot
/screenshot --viewports mobile

# Screenshot specific page
/screenshot --url http://localhost:3001/dashboard --viewports desktop

Tips

  • Screenshots include full page by default (scrolls entire page)
  • Timestamps in filenames prevent overwriting
  • Saved in working directory - easy to commit or share
  • Browser visible - see what's being captured

See Also

  • /test - Run automated tests
  • /check - Check for broken links or issues

--url --test-type

Test Webapp Feature

Run automated browser tests for your webapp using Playwright. Tests are saved to .web-tests/ in your current working directory.

Works from any directory - Saves test scripts and screenshots to your working directory's .web-tests/ folder.

How It Works

When you run /test, Claude will:

  1. Auto-detect running dev servers (or use the provided URL)
  2. Create a custom test script in .web-tests/scripts/
  3. Execute the test with visible browser
  4. Save screenshots to .web-tests/screenshots/
  5. Show results with console output

Usage

# Test specific feature
/test --test-type login

# Test with specific URL
/test --url http://localhost:3001 --test-type form

# Test responsive design
/test --test-type responsive

# Test page load
/test --url https://example.com --test-type page-load

Common Test Types

  • login - Test login flow and authentication
  • form - Test form filling and submission
  • responsive - Test across multiple viewports (desktop, tablet, mobile)
  • page-load - Test if page loads correctly
  • navigation - Test navigation and routing
  • custom - Claude will ask what to test

What Claude Will Do

  1. Auto-detect dev server (if testing localhost)
  2. Write test script to .web-tests/scripts/test-{type}-{timestamp}.js
  3. Execute test using: CWD=$(pwd) cd <skill-dir> && node run.js .web-tests/scripts/test-*.js
  4. Report results with any errors or successes
  5. Save screenshots automatically to .web-tests/screenshots/

Output Structure

your-repo/
└── .web-tests/
    ├── scripts/
    │   └── test-login-2025-10-23.js
    └── screenshots/
        ├── login-page-2025-10-23T12-30-45.png
        └── dashboard-2025-10-23T12-30-50.png

Environment Variables

Claude can use these environment variables:

  • CWD - Your current working directory (auto-set)
  • HEADLESS - Set to true for background execution (default: false)
  • SLOW_MO - Slow down actions for debugging (default: 0)

Examples

# Test login with credentials
/test --test-type login

# Test contact form
/test --test-type form --url http://localhost:3001/contact

# Test homepage across viewports
/test --test-type responsive --url http://localhost:3001

Tips

  • Tests run with visible browser by default (easier to debug)
  • Screenshots are automatic - saved to .web-tests/screenshots/
  • Test scripts are reusable - found in .web-tests/scripts/
  • Auto-detects servers - no need to specify URL for localhost

See Also

  • /screenshot - Take screenshots of pages
  • /check - Check for broken links or issues

MCP servers 1

Sponsors

Details

Marketplace
marcioaltoe/claude-craftkit
Source
plugins/ui-tests
Author
Marcio Altoé
Category
Testing
License
MIT
Keywords
playwright, browser-automation, testing, e2e, screenshots, web-testing

More from marcioaltoe/claude-craftkit

All 8