A sophisticated browser automation tool designed to query Grok AI and extract responses via Openclaw Skills and Chrome relay.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install grok-browser
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install grok-browser using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Grok Browser?
The Grok Browser skill provides a robust interface for interacting with the Grok AI platform programmatically. By utilizing Chrome browser automation and a specialized relay extension, this skill bypasses traditional scraping limitations to interact directly with Grok's dynamic UI. It is specifically engineered to handle complex web elements like contenteditable text fields and streaming responses, making it a premier choice for developers using Openclaw Skills to integrate real-time AI insights into their local environments.
This skill excels at capturing clean text responses rather than simple screenshots, ensuring that the data you retrieve is immediately actionable. Whether you are looking to leverage Grok's DeepSearch capabilities or simply automate repetitive queries, the Grok Browser skill provides the necessary hooks to perform these tasks with high reliability and precision within the Openclaw Skills ecosystem.
Grok Browser Use Cases
- Automating research tasks by querying Grok DeepSearch for detailed technical analysis.
- Integrating Grok AI responses into local development pipelines and documentation workflows.
- Programmatically extracting AI-generated code snippets or explanations to the system clipboard.
- Managing multiple AI chat contexts through automated session refreshing and tab handling.
How Grok Browser Works
- Launch Google Chrome at the Grok URL and execute the browser relay attachment script.
- Query the browser status to identify the active targetId for the Grok tab.
- Use JavaScript evaluation to focus the contenteditable input field and inject the desired query text.
- Simulate an Enter key press to submit the prompt to the Grok engine.
- Monitor the browser state and wait for the AI response to finalize and the Copy button to appear.
- Execute a click action on the Copy button and retrieve the response text from the system clipboard.
Grok Browser Setup
To get started with this skill, ensure you have Google Chrome installed with the Browser Relay extension and configured to use the profile=chrome setting. Use the following commands to initialize the environment:
# Open Grok and allow time for the page to load
open -a "Google Chrome" "https://grok.com"
sleep 3
# Attach the required browser relay script
~/clawd/scripts/attach-browser-relay.sh
# Verify the connection status
browser action=status profile=chrome
Grok Browser Data Schema & Taxonomy
The Grok Browser skill manages data through DOM interactions and system-level clipboard operations. Below is the primary data handling structure used by these Openclaw Skills:
| Element | Interaction Type | Purpose |
|---|---|---|
| Editor | JS Evaluate | Injecting queries into [contenteditable="true"] |
| Copy Button | Click Event | Transferring AI response to system clipboard |
| Target ID | Metadata | Unique identifier for the Chrome tab session |
| Clipboard | pbpaste | Retrieving final text output for the agent |
| Snapshots | UI Metadata | Identifying button references and response completion |
Grok Browser Advanced Features
- Direct integration with Grok DeepSearch by toggling specific UI elements before submission.
- Automated context management using native Grok keyboard shortcuts like Meta+J for fresh sessions.
- Intelligent response detection that waits for specific UI indicators like response time markers or follow-up suggestions.
- Advanced troubleshooting hooks to monitor CDP (Chrome DevTools Protocol) readiness and relay status.
SKILL.md
Loading
Related Openclaw Skills
CapMonster Cloud CAPTCHA Solver
An API-driven tool for programmatically bypassing reCAPTCHA, hCaptcha, Turnstile, and image CAPTCHAs during browser automation.
Anemone Browser
A managed headful Chrome browser designed for agents, featuring anti-detection, human-in-the-loop VNC takeover, and multi-session isolation.
Abstract Searcher
A tool for automatically populating BibTeX files with academic abstracts via public APIs and intelligent browser automation.
MinerU
A sophisticated document parsing tool that converts complex PDFs, Word docs, and PPTs into AI-ready Markdown with full support for formulas and tables.
m3u8-downloader
A high-performance utility for Openclaw Skills that automates the extraction, parallel downloading, and decryption of HLS video streams.
Mac Control
A powerful automation suite for controlling macOS UI elements using mouse, keyboard, and system-level scripts.
Featured*
