browser
Automate web browser interactions using natural language via CLI commands. Use when the user asks to browse websites, navigate web pages, extract data from websites, take screenshots, fill forms, click buttons, or interact with web applications.
Why use this skill?
Learn to automate web navigation, form filling, and data extraction using OpenClaw's browser skill. Integrates Stagehand for local and cloud automation.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/peytoncasper/stagehand-browser-cliWhat This Skill Does
The browser skill is a robust automation tool for OpenClaw that leverages Stagehand CLI to bridge the gap between natural language commands and complex web interactions. It acts as an autonomous agent interface for your Chrome browser, allowing for both local execution and cloud-based automation via Browserbase. By parsing human-readable instructions, it handles navigation, form submission, element interaction, and data extraction, effectively turning the browser into a programmable interface for the AI agent.
Installation
To integrate this skill into your workflow, ensure you have the OpenClaw environment initialized. Run the following command in your terminal:
clawhub install openclaw/skills/skills/peytoncasper/stagehand-browser-cli
Once installed, verify the setup by checking the setup.json file in the skill directory. If setupComplete is marked false, navigate to the directory and run npm install followed by npm link. For cloud-based capabilities, add your BROWSERBASE_API_KEY and BROWSERBASE_PROJECT_ID to your local .env file; otherwise, the skill defaults to local Chrome execution.
Use Cases
This skill is ideal for a variety of tasks ranging from basic web navigation to complex data scraping. Use it for automating recurring tasks like daily login workflows, gathering pricing information from competitive websites, or testing web application components. It is particularly effective for scenarios where you need to extract structured JSON data from unstructured web pages or navigate through multi-step forms that standard request libraries struggle with. It serves as a powerful utility for developers performing end-to-end testing or non-technical users looking to automate data collection without writing custom Puppeteer or Playwright code.
Example Prompts
- "Open the browser, go to Google Finance, and extract the current stock price for NVDA into a JSON object."
- "Navigate to the signup page on example.com, fill in the registration form with my credentials, and take a screenshot of the confirmation message."
- "Search for the latest research papers on artificial intelligence on Google Scholar and click on the first PDF link I find."
Tips & Limitations
Always follow the best practice of navigating to your target site before attempting to perform actions. If an action fails, use the browser observe command to debug and understand what elements are visible to the agent. Note that while local mode is faster for development, it lacks the advanced stealth features and proxy support provided by the Browserbase remote mode. Always ensure you close your browser sessions using browser close to free up system resources. Keep in mind that heavy interaction with dynamic websites can trigger rate-limiting, so use this skill responsibly.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-peytoncasper-stagehand-browser-cli": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access, external-api, code-execution
Related Skills
browser
Automate web browser interactions using natural language via CLI commands. Use when the user asks to browse websites, navigate web pages, extract data from websites, take screenshots, fill forms, click buttons, or interact with web applications.
browser
Automate web browser interactions using natural language via CLI commands. Use when the user asks to browse websites, navigate web pages, extract data from websites, take screenshots, fill forms, click buttons, or interact with web applications.
browser
Automate web browser interactions using natural language via CLI commands. Use when the user asks to browse websites, navigate web pages, extract data from websites, take screenshots, fill forms, click buttons, or interact with web applications.
functions
Guide Claude through deploying serverless browser automation using the official bb CLI