A Puppeteer-powered headless browser skill for rendering web pages and extracting readable content for AI agents.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install 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 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 Browser?
The Browser skill is a high-performance automation tool designed to give AI agents the ability to interact with the live web. By leveraging Puppeteer, it can render modern, JavaScript-heavy websites that traditional text-based scrapers often fail to process. This ensures that the agent receives clean, readable content and accurate context from any URL, bridging the gap between an LLM's static training data and real-time web information.
Built specifically for the Openclaw Skills ecosystem, this tool simplifies complex web interactions. It handles the nuances of DOM rendering and content extraction, allowing developers to focus on building intelligent workflows rather than managing browser drivers or dealing with obfuscated HTML.
Browser Use Cases
- Extracting technical documentation or blog posts to provide context for coding tasks.
- Researching real-time data from dynamic websites that require JavaScript execution.
- Automating the retrieval of search engine results for multi-step agentic workflows.
- Scraping specific data points from interactive web applications or single-page apps (SPAs).
How Browser Works
- The agent or user invokes the skill using the standardized read command with a target URL.
- The skill initializes a headless Puppeteer instance to navigate to the specified web address.
- It waits for the page to fully load, ensuring that all asynchronous scripts and DOM elements are rendered.
- The skill extracts the relevant text content while stripping away unnecessary boilerplate like scripts and styling.
- The cleaned data is returned to the agent's context, making it ready for immediate analysis or processing within Openclaw Skills.
Browser Setup
To enable this skill in your environment, use the standard installation command for Openclaw Skills:
openclaw install browser
Ensure that your environment has the necessary permissions to run headless Chromium, which is required by the underlying Puppeteer library.
Browser Data Schema & Taxonomy
The Browser skill processes requests and returns data in a structured format to ensure compatibility across the agent's context:
| Property | Type | Description |
|---|---|---|
url |
String | The source web address requested for rendering. |
content |
String | The extracted and cleaned text content from the rendered page. |
status |
Integer | The HTTP status code returned by the browser session. |
timestamp |
String | The ISO 8601 formatted time of the extraction. |
Browser Advanced Features
- Full JavaScript execution support for rendering modern web frameworks (React, Vue, etc.).
- Intelligent DOM interaction capabilities including the ability to click buttons and navigate elements.
- Automated content cleaning to reduce token consumption by removing non-essential HTML metadata.
- Seamless integration with other Openclaw Skills for complex, multi-agent research and development tasks.
SKILL.md
Loading
Related Openclaw Skills
Intervals.icu API Management
A comprehensive integration for managing athlete profiles, training activities, calendar events, and wellness data via the Intervals.icu API.
signal-cli (Signal Messaging)
A robust integration for automating Signal messenger interactions through a local CLI installation on macOS.
Nano PDF Edit
An AI-powered CLI tool that allows developers to visually edit and update PDF documents using natural language prompts.
QXMP Oracle
A high-performance oracle integration for fetching cryptographically verified real-world asset (RWA) data and proof-of-reserve status from the QELT blockchain.
Social Media Agent
An autonomous social media manager for X/Twitter that uses native browser automation and research tools to grow your audience.
Agent Memory
A universal memory architecture that provides AI agents with persistent identity, long-term context, and seamless cross-session continuity.
Featured*
