chrome-automation

Launch and control Chrome with AT-SPI2 accessibility for browser automation. Use when asked to start chrome, open browser, launch chrome, begin browser automation, or control web pages.

⭐2stars🔀0forks📁View on GitHub🕐Updated Dec 31, 2025⬇️3downloads

When & Why to Use This Skill

The Chrome Automation skill enables Claude to programmatically launch, control, and interact with the Google Chrome browser using AT-SPI2 accessibility features. It bridges the gap between AI reasoning and web execution, allowing for seamless navigation, element interaction (clicking, typing), and automated browser tasks. This skill is optimized for environments requiring reliable, accessible-driven web control for complex automation workflows.

Use Cases

  • Automated Web Testing: Perform end-to-end QA by simulating real user behavior such as clicking buttons, navigating through multi-step forms, and verifying UI elements.
  • Dynamic Data Extraction: Access and scrape data from modern, JavaScript-heavy websites that require active browser rendering and user-like interaction.
  • Repetitive Task Automation: Streamline administrative workflows by automating routine browser tasks like generating reports from web dashboards or managing cloud-based software interfaces.
  • Accessibility Auditing: Leverage the AT-SPI2 integration to programmatically inspect web elements and ensure web applications meet accessibility standards.
namechrome-automation
descriptionLaunch and control Chrome with AT-SPI2 accessibility for browser automation. Use when asked to start chrome, open browser, launch chrome, begin browser automation, or control web pages.

Chrome Automation

Launch Chrome with accessibility features enabled for programmatic control via AT-SPI2.

Quick Start

Check if Chrome is Running

~/.claude/skills/chrome-automation/scripts/launch.sh status

Or manually:

pgrep -f "chrome.*no-sandbox" && echo "Running" || echo "Not running"

Launch Chrome

~/.claude/skills/chrome-automation/scripts/launch.sh [URL]

The script automatically checks if Chrome is already running.

Or launch manually:

export DISPLAY=:1
export GTK_MODULES=gail:atk-bridge
export NO_AT_BRIDGE=0
export GNOME_ACCESSIBILITY=1

google-chrome \
    --no-sandbox \
    --disable-gpu \
    --start-maximized \
    --force-renderer-accessibility \
    --no-first-run \
    "https://google.com" &

Restart Chrome

~/.claude/skills/chrome-automation/scripts/launch.sh restart [URL]

Control Chrome (after launching)

List clickable elements:

chrome-a11y list

Click an element:

chrome-a11y click "Button Name"

Navigate to URL:

chrome-a11y navigate "https://example.com"

Type text:

chrome-a11y type "search query"

Send keyboard shortcut:

chrome-a11y key "ctrl+t"   # New tab
chrome-a11y key "ctrl+l"   # Focus address bar

Stop Chrome

pkill -9 chrome

Important Notes

  1. Must run in background with & to avoid blocking
  2. --force-renderer-accessibility is required for AT-SPI2 control
  3. --no-sandbox is required when running as root
  4. Wait 3-5 seconds after launch before using chrome-a11y

Prerequisites

Ensure these are installed:

  • TigerVNC running on :1
  • AT-SPI2 packages: gir1.2-atspi-2.0, at-spi2-core, python3-gi
  • The chrome-a11y tool in PATH

For detailed documentation, see REFERENCE.md.