Chrome Devtools

[IMPORTANT] Use TaskCreate to break ALL work into small tasks BEFORE starting — including tasks for each file read. This prevents context loss from long files. For simple tasks, AI MUST ask user whether to skip.

Quick Summary

Goal: Automate browser interactions, debugging, and performance analysis using Puppeteer CLI scripts with persistent sessions.

Workflow:

1. Discover Structure — Use aria-snapshot.js to get ARIA tree of unknown pages
2. Interact by Ref — Use select-ref.js to click, fill, hover elements by stable refs
3. Capture Evidence — Take screenshots, collect console logs, monitor network traffic
4. Analyze — Performance profiling, accessibility audits, visual regression checks

Key Rules:

• Use headed mode on Windows/macOS, headless only on Linux/WSL/CI
• All scripts output JSON for structured processing
• Store snapshots in .claude/chrome-devtools/snapshots/ with timestamps

Be skeptical. Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence percentages (Idea should be more than 80%).

Chrome DevTools Agent Skill

Browser automation via Puppeteer scripts with persistent sessions. All scripts output JSON.

Skill Location

Skills can exist in project-scope or user-scope. Priority: project-scope > user-scope.

# Detect skill location
SKILL_DIR=""
if [ -d ".claude/skills/chrome-devtools/scripts" ]; then
  SKILL_DIR=".claude/skills/chrome-devtools/scripts"
elif [ -d "$HOME/.claude/skills/chrome-devtools/scripts" ]; then
  SKILL_DIR="$HOME/.claude/skills/chrome-devtools/scripts"
fi
cd "$SKILL_DIR"

Choosing Your Approach

Automation Browsing Running Mode

• Detect current OS and launch browser as headless only when running on Linux, WSL, or CI environments.
• For macOS/Windows, browser always runs in headed mode for better debugging.
• Run multiple scripts/sessions in parallel to simulate real user interactions.
• Run multiple scripts/sessions in parallel to simulate different device types (mobile, tablet, desktop).
• Skills can exist in project-scope or user-scope. Priority: project-scope > user-scope.

ARIA Snapshot (Element Discovery)

When page structure is unknown, use aria-snapshot.js to get a YAML-formatted accessibility tree with semantic roles, accessible names, states, and stable element references.

Get ARIA Snapshot

# Generate ARIA snapshot and output to stdout
node aria-snapshot.js --url https://example.com

# Save to file in snapshots directory
node aria-snapshot.js --url https://example.com --output ./.claude/chrome-devtools/snapshots/page.yaml

Example YAML Output

- banner:
  - link "Hacker News" [ref=e1]
    /url: https://news.ycombinator.com
  - navigation:
    - link "new" [ref=e2]
    - link "past" [ref=e3]
    - link "comments" [ref=e4]
- main:
  - list:
    - listitem:
      - link "Show HN: My new project" [ref=e8]
      - text: "128 points by user 3 hours ago"
- contentinfo:
  - textbox [ref=e10]
    /placeholder: "Search"

Interpreting ARIA Notation

Interact by Ref

Skills can exist in project-scope or user-scope. Priority: project-scope > user-scope. Use select-ref.js to interact with elements by their ref:

# Click element with ref e5
node select-ref.js --ref e5 --action click

# Fill input with ref e10
node select-ref.js --ref e10 --action fill --value "search query"

# Get text content
node select-ref.js --ref e8 --action text

# Screenshot specific element
node select-ref.js --ref e1 --action screenshot --output ./logo.png

# Focus element
node select-ref.js --ref e10 --action focus

# Hover over element
node select-ref.js --ref e5 --action hover

Store Snapshots

Skills can exist in project-scope or user-scope. Priority: project-scope > user-scope. Store snapshots for analysis in <project>/.claude/chrome-devtools/snapshots/:

# Create snapshots directory
mkdir -p .claude/chrome-devtools/snapshots

# Capture and store with timestamp
SESSION="$(date +%Y%m%d-%H%M%S)"
node aria-snapshot.js --url https://example.com --output .claude/chrome-devtools/snapshots/$SESSION.yaml

Workflow: Unknown Page Structure

1. Get snapshot to discover elements:

   node aria-snapshot.js --url https://example.com
   

2. Identify target from YAML output (e.g., [ref=e5] for a button)

3. Interact by ref:

   node select-ref.js --ref e5 --action click
   

4. Verify result with screenshot or new snapshot:

   node screenshot.js --output ./result.png
   

Local HTML Files

Skills can exist in project-scope or user-scope. Priority: project-scope > user-scope. IMPORTANT: Never browse local HTML files via file:// protocol. Always serve via local server: Why: file:// protocol blocks many browser features (CORS, ES modules, fetch API, service workers). Local server ensures proper HTTP behavior.

# Option 1: npx serve (recommended)
npx serve ./dist -p 3000 &
node navigate.js --url http://localhost:3000

# Option 2: Python http.server
python -m http.server 3000 --directory ./dist &
node navigate.js --url http://localhost:3000

Note: when port 3000 is busy, find an available port with lsof -i :3000 and use a different one.

Quick Start

# Install dependencies
cd .claude/skills/chrome-devtools/scripts
npm install  # Installs puppeteer, sharp, debug, yargs

# Test (browser stays running for session reuse)
node navigate.js --url https://example.com
# Output: {"success": true, "url": "...", "title": "..."}

Linux/WSL only: Run ./install-deps.sh first for Chrome system libraries.

Session Persistence

Browser state persists across script executions via WebSocket endpoint file (.browser-session.json).

Default behavior: Scripts disconnect but keep browser running for session reuse.

# First script: launches browser, navigates, disconnects (browser stays running)
node navigate.js --url https://example.com/login

# Subsequent scripts: connect to existing browser, reuse page state
node fill.js --selector "#email" --value "user@example.com"
node fill.js --selector "#password" --value "secret"
node click.js --selector "button[type=submit]"

# Close browser when done
node navigate.js --url about:blank --close true

Session management:

• --close true: Close browser and clear session
• Default (no flag): Keep browser running for next script

Available Scripts

Skills can exist in project-scope or user-scope. Priority: project-scope > user-scope. All in .claude/skills/chrome-devtools/scripts/:

Workflow Loop

1. Execute focused script for single task
2. Observe JSON output
3. Assess completion status
4. Decide next action
5. Repeat until done

Writing Custom Test Scripts

Skills can exist in project-scope or user-scope. Priority: project-scope > user-scope. For complex automation, write scripts to <project>/.claude/chrome-devtools/tmp/:

# Create tmp directory for test scripts
mkdir -p $SKILL_DIR/.claude/chrome-devtools/tmp

# Write a test script
cat > $SKILL_DIR/.claude/chrome-devtools/tmp/login-test.js << 'EOF'
import { getBrowser, getPage, disconnectBrowser, outputJSON } from '../scripts/lib/browser.js';

async function loginTest() {
  const browser = await getBrowser();
  const page = await getPage(browser);

  await page.goto('https://example.com/login');
  await page.type('#email', 'user@example.com');
  await page.type('#password', 'secret');
  await page.click('button[type=submit]');
  await page.waitForNavigation();

  outputJSON({
    success: true,
    url: page.url(),
    title: await page.title()
  });

  await disconnectBrowser();
}

loginTest();
EOF

# Run the test
node $SKILL_DIR/.claude/chrome-devtools/tmp/login-test.js

Key principles for custom scripts:

• Single-purpose: one script, one task
• Always call disconnectBrowser() at the end (keeps browser running)
• Use closeBrowser() only when ending session completely
• Output JSON for easy parsing
• Plain JavaScript only in page.evaluate() callbacks

Screenshots

Skills can exist in project-scope or user-scope. Priority: project-scope > user-scope. Store screenshots for analysis in <project>/.claude/chrome-devtools/screenshots/:

# Basic screenshot
node screenshot.js --url https://example.com --output ./.claude/chrome-devtools/screenshots/page.png

# Full page
node screenshot.js --url https://example.com --output ./.claude/chrome-devtools/screenshots/page.png --full-page true

# Specific element
node screenshot.js --url https://example.com --selector ".main-content" --output ./.claude/chrome-devtools/screenshots/element.png

Auto-Compression (Sharp)

Screenshots >5MB auto-compress using Sharp (4-5x faster than ImageMagick):

# Default: compress if >5MB
node screenshot.js --url https://example.com --output ./.claude/chrome-devtools/screenshots/page.png

# Custom threshold (3MB)
node screenshot.js --url https://example.com --output ./.claude/chrome-devtools/screenshots/page.png --max-size 3

# Disable compression
node screenshot.js --url https://example.com --output ./.claude/chrome-devtools/screenshots/page.png --no-compress

Store screenshots for analysis in <project>/.claude/chrome-devtools/screenshots/.

Console Log Collection & Analysis

Skills can exist in project-scope or user-scope. Priority: project-scope > user-scope.

Capture Logs

# Capture all logs for 10 seconds
node console.js --url https://example.com --duration 10000

# Filter by type
node console.js --url https://example.com --types error,warn --duration 5000

Session Storage Pattern

Store logs for analysis in <project>/.claude/chrome-devtools/logs/<session>/:

# Create session directory
SESSION="$(date +%Y%m%d-%H%M%S)"
mkdir -p .claude/chrome-devtools/logs/$SESSION

# Capture and store
node console.js --url https://example.com --duration 10000 > .claude/chrome-devtools/logs/$SESSION/console.json
node network.js --url https://example.com > .claude/chrome-devtools/logs/$SESSION/network.json

# View errors
jq '.messages[] | select(.type=="error")' .claude/chrome-devtools/logs/$SESSION/console.json

Root Cause Analysis

# 1. Check for JavaScript errors
node console.js --url https://example.com --types error,pageerror --duration 5000 | jq '.messages'

# 2. Correlate with network failures
node network.js --url https://example.com | jq '.requests[] | select(.response.status >= 400)'

# 3. Check specific error stack traces
node console.js --url https://example.com --types error --duration 5000 | jq '.messages[].stack'

Finding Elements

Skills can exist in project-scope or user-scope. Priority: project-scope > user-scope. Use snapshot.js to discover selectors before interacting:

# Get all interactive elements
node snapshot.js --url https://example.com | jq '.elements[] | {tagName, text, selector}'

# Find buttons
node snapshot.js --url https://example.com | jq '.elements[] | select(.tagName=="button")'

# Find by text content
node snapshot.js --url https://example.com | jq '.elements[] | select(.text | contains("Submit"))'

Error Recovery

Skills can exist in project-scope or user-scope. Priority: project-scope > user-scope. If script fails:

# 1. Capture current state (without navigating to preserve state)
node screenshot.js --output ./.claude/skills/chrome-devtools/screenshots/debug.png

# 2. Get console errors
node console.js --url about:blank --types error --duration 1000

# 3. Discover correct selector
node snapshot.js | jq '.elements[] | select(.text | contains("Submit"))'

# 4. Try XPath if CSS fails
node click.js --selector "//button[contains(text(),'Submit')]"

Common Patterns

Web Scraping

node evaluate.js --url https://example.com --script "
  Array.from(document.querySelectorAll('.item')).map(el => ({
    title: el.querySelector('h2')?.textContent,
    link: el.querySelector('a')?.href
  }))
" | jq '.result'

Form Automation

node navigate.js --url https://example.com/form
node fill.js --selector "#search" --value "query"
node click.js --selector "button[type=submit]"

Performance Testing

node performance.js --url https://example.com | jq '.vitals'

Script Options

All scripts support:

• --headless false - Show browser window
• --close true - Close browser completely (default: stay running)
• --timeout 30000 - Set timeout (ms)
• --wait-until networkidle2 - Wait strategy Skills can exist in project-scope or user-scope. Priority: project-scope > user-scope.

Troubleshooting

Skills can exist in project-scope or user-scope. Priority: project-scope > user-scope.

Screenshot Analysis: Missing Images

If images don't appear in screenshots, they may be waiting for animation triggers:

1. Scroll-triggered animations: Scroll element into view first

   node evaluate.js --script "document.querySelector('.lazy-image').scrollIntoView()"
   # Wait for animation
   node evaluate.js --script "await new Promise(r => setTimeout(r, 1000))"
   node screenshot.js --output ./result.png
   

2. Sequential animation queue: Wait longer and retry

   # First attempt
   node screenshot.js --url http://localhost:3000 --output ./attempt1.png
   
   # Wait for animations to complete
   node evaluate.js --script "await new Promise(r => setTimeout(r, 2000))"
   
   # Retry screenshot
   node screenshot.js --output ./attempt2.png
   

3. Intersection Observer animations: Trigger by scrolling through page

   node evaluate.js --script "window.scrollTo(0, document.body.scrollHeight)"
   node evaluate.js --script "await new Promise(r => setTimeout(r, 1500))"
   node evaluate.js --script "window.scrollTo(0, 0)"
   node screenshot.js --output ./full-loaded.png --full-page true
   

Reference Documentation

• ./references/cdp-domains.md - Chrome DevTools Protocol domains
• ./references/puppeteer-reference.md - Puppeteer API patterns
• ./references/performance-guide.md - Core Web Vitals optimization
• ./scripts/README.md - Detailed script options

IMPORTANT Task Planning Notes (MUST FOLLOW)

• Always plan and break work into many small todo tasks
• Always add a final review todo task to verify work quality and identify fixes/enhancements