← Back to Skills Marketplace

Browser

Name: Browser
Author: pshotts

by pshotts · GitHub ↗ · v1.0.0

cross-platform ✓ Security Clean

14635

Downloads

Stars

260

Active Installs

Versions

Install in OpenClaw

/install browser

Description

Uses a headless browser to navigate web pages, interact with elements, and extract clean, readable text content from URLs.

README (SKILL.md)

SKILL: Browser

This skill uses a headless browser (Puppeteer) to render web pages and extract clean, readable content.

Puppeteer Browser Automation

This is a custom skill generated by OpenClaw to handle headless web browsing. It utilizes the Puppeteer library to navigate to websites, interact with DOM elements, click buttons, and scrape data for the agent's context.

Usage

openclaw browser read \x3Curl> - Renders the page and returns its text content.

Usage Guidance

This skill appears benign for rendering and reading web pages. Before installing, be aware that it opens arbitrary URLs with Puppeteer using disabled browser sandbox flags, so it is safest to run it in a container or otherwise isolated environment, especially for unknown websites.

Capability Analysis

Type: OpenClaw Skill Name: browser Version: 1.0.0 The skill provides a standard headless browser utility using Puppeteer to extract text content from URLs. The code in index.js is straightforward and functional, and the documentation in SKILL.md and README.md accurately describes its purpose without any indicators of malicious intent, data exfiltration, or prompt injection.

Capability Assessment

ℹ Purpose & Capability

The stated purpose is to render web pages and extract readable text, which matches the included Puppeteer code.

✓ Instruction Scope

The usage is scoped to a single command, `read <url>`, and the code only navigates to that URL and prints page text.

ℹ Install Mechanism

The README declares a Puppeteer dependency, but the provided artifacts include no install spec, package manifest, or lockfile to pin or verify it.

ℹ Credentials

Launching a headless browser is purpose-aligned, but the code disables Chromium sandboxing while rendering arbitrary URLs.

✓ Persistence & Privilege

No credentials, persistent storage, background worker, or privileged account access are shown; the browser is closed after each run.

How to Use

Make sure OpenClaw is installed (local or Docker)
Run the install command in chat: /install browser
After installation, invoke the skill by name or use /browser
Provide required inputs per the skill's parameter spec and get structured output

Version History

v1.0.0

- Initial release of the Browser skill. - Uses Puppeteer to render web pages and extract clean, readable content. - Supports headless web browsing, DOM interaction, and data scraping. - Provides a command to read and return text from a specified URL.

Metadata

Slug browser

Version 1.0.0

License —

All-time Installs 273

Active Installs 260

Total Versions 1

Frequently Asked Questions

What is Browser?

Uses a headless browser to navigate web pages, interact with elements, and extract clean, readable text content from URLs. It is an AI Agent Skill for Claude Code / OpenClaw, with 14635 downloads so far.

How do I install Browser?

Run "/install browser" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Browser free?

Yes, Browser is completely free (open-source). You can download, install and use it at no cost.

Which platforms does Browser support?

Browser is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Browser?

It is built and maintained by pshotts (@pshotts); the current version is v1.0.0.

More Skills