- name
SKILL.md
Tệp skill vẫn nằm trong kho mã của nhà phát hành.
Dán lệnh đã sao chép vào terminal. Lệnh sẽ cài đặt tệp SKILL.md này vào agent đó.
npx skills add AgentWorkforce/relay --skill browser-testing-with-screenshots -a cursor -yDán lệnh đã sao chép vào terminal. Lệnh sẽ cài đặt tệp SKILL.md này vào agent đó.
npx skills add AgentWorkforce/relay --skill browser-testing-with-screenshots -a claude-code -yDán lệnh đã sao chép vào terminal. Lệnh sẽ cài đặt tệp SKILL.md này vào agent đó.
npx skills add AgentWorkforce/relay --skill browser-testing-with-screenshots -a codex -yDán lệnh đã sao chép vào terminal. Lệnh sẽ cài đặt tệp SKILL.md này vào agent đó.
npx skills add AgentWorkforce/relay --skill browser-testing-with-screenshots -a grok -yGửi tin nhắn đã sao chép trong cuộc trò chuyện Grok Bot. Bot sẽ lấy tệp SKILL.md này từ GitHub và thêm vào bộ skill mà mọi Bot của bạn dùng chung.
Install this skill: https://github.com/AgentWorkforce/relay/tree/HEAD/.claude/skills/browser-testing-with-screenshotsTừ nhà phát hành
Automate Chrome browser testing with visual verification using browser-tools. Connect to Chrome DevTools Protocol for navigation, interaction, and screenshot capture to confirm application functionality.
REQUIRED: Install agent-tools from https://github.com/badlogic/agent-tools
# Clone and install agent-tools
git clone https://github.com/badlogic/agent-tools.git
cd agent-tools
# Follow installation instructions in the repository
# Ensure all executables (browser-start.js, browser-nav.js, etc.) are in your PATH
Verify installation:
# Check that browser tools are available
which browser-start.js
which browser-nav.js
which browser-screenshot.js
All browser-* commands referenced in this skill come from the agent-tools repository and must be properly installed and accessible in your system PATH.
Use this skill when:
Don't use for:
# Launch Chrome with debugging enabled (preserves user profile)
browser-start.js
# Or start fresh (no cookies, clean state)
browser-start.js --fresh
Expected Result: Chrome opens on port 9222 with DevTools Protocol enabled
# Go to your application starting point
browser-nav.js http://localhost:5172/dashboard
Verify: Browser navigates to dashboard page
# Take initial screenshot to confirm page loaded
browser-screenshot.js
Output: Returns path to screenshot file (e.g., screenshot_20231203_141532.png)
#!/bin/bash
# Test login and dashboard functionality
echo "🚀 Starting browser test..."
# 1. Launch browser
browser-start.js --fresh
# 2. Navigate to login page
browser-nav.js http://localhost:5172/login
sleep 2
# 3. Take screenshot of login page
LOGIN_SHOT=$(browser-screenshot.js)
echo "📸 Login page: $LOGIN_SHOT"
# 4. Fill login form (interactive element picking)
browser-pick.js "Click the username field"
browser-eval.js 'document.activeElement.value = "testuser"'
browser-pick.js "Click the password field"
browser-eval.js 'document.activeElement.value = "password123"'
# 5. Screenshot filled form
FORM_SHOT=$(browser-screenshot.js)
echo "📸 Filled form: $FORM_SHOT"
# 6. Submit form
browser-pick.js "Click the login button"
sleep 3
# 7. Verify dashboard loaded
browser-nav.js http://localhost:5172/dashboard
DASHBOARD_SHOT=$(browser-screenshot.js)
echo "📸 Dashboard: $DASHBOARD_SHOT"
# 8. Verify specific dashboard elements
browser-pick.js "Select the navigation menu"
browser-eval.js 'console.log("Navigation found:", !!document.querySelector(".nav"))'
echo "✅ Test complete. Screenshots saved."
# Interactive element selection (best for dynamic content)
browser-pick.js "Select the submit button"
# User clicks element in browser → returns CSS selector
# Use returned selector for automation
SELECTOR=$(browser-pick.js "Select the submit button" | grep "selector:")
browser-eval.js "document.querySelector('$SELECTOR').click()"
# Take screenshot to verify action
browser-screenshot.js
# Check if element exists before interaction
browser-eval.js 'document.querySelector("#login-form") !== null'
# Wait for dynamic content
browser-eval.js '
new Promise(resolve => {
const check = () => {
if (document.querySelector(".loaded")) resolve(true);
else setTimeout(check, 100);
};
check();
})
'
# Extract form data
browser-eval.js 'JSON.stringify(Object.fromEntries(new FormData(document.querySelector("form"))))'
# Navigate and wait before screenshot
browser-nav.js http://localhost:5172/slow-page
sleep 5 # Wait for animations/loading
browser-screenshot.js
# Get page title
PAGE_TITLE=$(browser-eval.js 'document.title')
echo "Current page: $PAGE_TITLE"
# Extract readable content
browser-content.js > page_content.md
# Check for specific text
browser-eval.js 'document.body.textContent.includes("Welcome to Dashboard")'
# Check if Chrome is running
if ! browser-eval.js 'true' 2>/dev/null; then
echo "❌ Chrome not connected. Running browser-start.js..."
browser-start.js
fi
# Verify navigation succeeded
if browser-eval.js 'location.href.includes("dashboard")'; then
echo "✅ Navigation successful"
else
echo "❌ Navigation failed"
exit 1
fi
screenshot_YYYYMMDD_HHMMSS.png in current directorybrowser-content.jsbrowser-pick.js interactionbrowser-eval.js# Create test evidence directory
mkdir -p test-results/$(date +%Y%m%d_%H%M%S)
cd test-results/$(date +%Y%m%d_%H%M%S)
# Run tests with organized screenshots
browser-start.js
for page in login dashboard profile; do
browser-nav.js "http://localhost:5172/$page"
sleep 2
screenshot=$(browser-screenshot.js)
mv "$screenshot" "${page}_page.png"
echo "✅ $page page tested"
done
Benefits:
Results:
Key principle: Combine automated navigation with human element selection for robust, maintainable browser testing.
Use when testing web applications with visual verification - automates Chrome browser interactions, element selection, and screenshot capture for confirming UI functionality
---name: browser-testing-with-screenshotsdescription: Use when testing web applications with visual verification - automates Chrome browser interactions, element…---# .claude/skills/browser-testing-with-screenshots/SKILL.mdCâu hỏi thường gặp
Tải .claude/skills/browser-testing-with-screenshots/SKILL.md từ nhà phát hành, hoặc sao chép đường dẫn và mở kho mã. PlugMCP chỉ liệt kê skill và không lưu trữ tệp này.
Nhà phát hành duy trì nó tại https://github.com/AgentWorkforce/relay.
Claude, Cursor, Codex và Grok Build có thể đọc tệp SKILL.md mà bạn thêm từ kho mã của nhà phát hành. Grok Bot cài đặt skill khi bạn gửi liên kết thư mục GitHub của skill trong cuộc trò chuyện.