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?
Master web automation with OpenClaw. Navigate sites, extract data, and interact with forms using natural language CLI commands in local or remote browser environments.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/peytoncasper/browser-automationWhat This Skill Does
The browser automation skill provides a robust interface for controlling web browsers through natural language commands using the OpenClaw agent. By leveraging Stagehand CLI and Claude, this skill abstracts away the complexities of DOM manipulation, enabling users to navigate, extract data, and interact with complex web applications effortlessly. It seamlessly handles both local and remote environments; it detects the presence of Browserbase API keys to switch between local Chrome execution for rapid development and high-availability remote execution for production-grade scraping. The tool serves as an autonomous bridge between human intent and browser behavior, enabling end-to-end task automation such as filling forms, clicking dynamic elements, and harvesting unstructured data.
Installation
To install this skill, use the ClawHub command: clawhub install openclaw/skills/skills/peytoncasper/browser-automation. Once installed, check your local setup.json file. If the setupComplete flag is set to false, navigate to the skill directory and run npm install followed by npm link to initialize the global command-line interface. For remote automation, ensure your environment variables BROWSERBASE_API_KEY and BROWSERBASE_PROJECT_ID are correctly configured within your .env file.
Use Cases
This skill is designed for scenarios requiring repeatable web interactions. Common applications include: automating sign-in workflows for internal tools, monitoring competitor pricing or stock availability, harvesting structured data from e-commerce platforms into JSON formats, and performing multi-step regression testing on web UIs. It is particularly effective for tasks involving CAPTCHA-heavy sites or protected environments where Browserbase's stealth features are required.
Example Prompts
- "Open the browser, navigate to the LinkedIn login page, and fill in my email and password fields using my vault credentials."
- "Go to the latest news page for techcrunch.com and extract the headlines and publication times into a structured data format."
- "Navigate to the OpenClaw documentation page, find the search bar, click it, type 'getting started', and then take a screenshot of the results."
Tips & Limitations
For optimal reliability, always verify the page state using browser screenshot after performing complex actions to ensure the DOM has updated. When elements are not responding as expected, use browser observe to audit available UI selectors. Note that local mode is faster for rapid prototyping but lacks the stealth and proxy capabilities found in Browserbase mode. Always prioritize the use of browser close to prevent memory leaks and dangling browser instances. If an action fails, consider adding brief wait times or verifying your internet connection, as remote environments rely on high-latency cloud connections.
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-browser-automation": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access, external-api
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