A cloud-based browser automation skill that enables scalable scraping, PDF generation, and automated testing without managing infrastructure.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install browserless
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 browserless 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 Browserless?
Browserless is a powerful cloud service that provides scalable headless browsers for high-performance automation. As part of the Openclaw Skills ecosystem, this integration allows developers to programmatically control browser instances to extract web content, generate high-quality PDFs, and perform automated testing across various web environments. It effectively removes the operational burden of managing local browser binaries and infrastructure.
By leveraging the Membrane framework, this skill ensures that all browser interactions are secure and efficiently handled. It bridges the gap between AI agents and the web, allowing for complex data extraction and UI interaction through a simplified interface that manages the underlying browser lifecycle automatically.
Browserless Use Cases
- Web Scraping: Extracting structured data from complex, JavaScript-heavy websites.
- Automated PDF Generation: Converting web pages or HTML templates into print-ready PDF documents.
- UI Testing: Running automated browser tests to verify frontend functionality without local setup.
- Content Snapshots: Programmatically capturing screenshots of live web pages for monitoring or archiving.
- Workflow Automation: Interacting with web-based dashboards to perform repetitive tasks.
How Browserless Works
- Authentication: The skill connects to the Membrane platform to handle secure credential management and session persistence.
- Connection Establishment: A dedicated connection to Browserless is initialized, ensuring a ready state for browser commands.
- Action Discovery: The system searches for specific browser actions (like screenshot or content retrieval) based on natural language intent.
- Execution: Commands are sent to the Browserless cloud API, which spins up a browser instance to perform the requested task.
- Data Retrieval: The resulting output, such as HTML content, binary PDF data, or cookies, is returned to the agent for further processing.
Browserless Setup
To get started with this skill, install the Membrane CLI and authenticate your environment:
npm install -g @membranehq/cli@latest
membrane login --tenant --clientName=openclaw
Create a connection to the Browserless service:
membrane connection ensure "https://browserless.io/" --json
If the connection state is BUILDING, poll for readiness:
npx @membranehq/cli connection get <id> --wait --json
Browserless Data Schema & Taxonomy
The Browserless skill organizes data through a hierarchical structure of browser entities and metadata:
| Entity | Attributes | Description |
|---|---|---|
| Browser | Sessions, Limits | The top-level instance managing browser resources. |
| Page | URL, Headers | Individual tabs or windows within the browser. |
| Artifacts | Screenshot, PDF | The generated files resulting from a browser action. |
| Metadata | Metrics, Cookies | Operational data regarding performance and session state. |
Browserless Advanced Features
- Intent-Based Action Discovery: Use natural language to find the specific browser action needed for your task.
- Membrane Proxy Requests: Send direct requests to the Browserless API with automatic header injection and credential refresh.
- Multi-Agent Support: Optimized for various agent types including openclaw, claude, and codex.
- Transparent Auth Lifecycle: No local secrets required; Membrane manages API keys and OAuth server-side.
- Automated Pagination: Pre-built actions handle complex data retrieval across multiple pages automatically.
SKILL.md
Loading
Related Openclaw Skills
Cacoo
A powerful integration for managing Cacoo diagrams, folders, and team workflows directly within your AI agent environment.
Calendarific
A professional-grade API integration providing global public holiday data for over 230 countries directly through Openclaw Skills.
ZenQuote
ZenQuote is a productivity-focused skill that integrates the ZenQuotes.io API to deliver automated daily wisdom and inspirational quote images to AI agents.
Burp Suite Skill
An advanced integration for Burp Suite that enables AI agents to automate web application security testing and HTTP traffic manipulation using Openclaw Skills.
Bump
A professional integration for managing Bump data, contacts, and file sharing workflows via the Membrane ecosystem.
Amazon Elasticsearch
A robust integration for managing AWS Elasticsearch clusters, indexing documents, and automating real-time search workflows.
Featured*
