Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
Browser automation skill that combines multiple automation approaches into one unified interface. Runs against local Chrome/Chromium or cloud browsers via Browserbase, with automatic environment detection. Supports navigation, clicking, typing, screenshots, and PDF export.
Replaces six or more separate browser automation skills with one that handles both local and cloud execution without changing commands.
When to use it
- Logging into a web app and filling out forms automatically
- Scraping product prices or availability across multiple pages
- Capturing screenshots of pages for visual documentation
- Exporting web pages to PDF for archiving or reporting
- Running goal-based browser tasks against a remote cloud session
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: go to example.com, find the login button, and take a screenshot after logging in
- 1Navigate to the target URL using browser open
- 2Take a snapshot to analyze the page structure and get element refs
- 3Click the login button using its ref from the snapshot
- 4Type credentials into the form fields
- 5Capture a screenshot of the resulting page
A screenshot file showing the post-login state of the page
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.