skills.rest
StephaniePhenex
StephaniePhenexCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

Agent Browser

Automate web browser interactions via a headless Rust CLI with Node.js fallback.

Updated Mar 10, 2026
Search Tags:#data extraction#browser automation#web scraping#form filling#web interaction#headless browser
One-click install
npx skills add https://github.com/StephaniePhenex/openclaw-workspace --skill agent-browser-stephaniephenex
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: Agent Browser
Source: https://github.com/StephaniePhenex/openclaw-workspace/tree/main/skills/agent-browser
Command: npx skills add https://github.com/StephaniePhenex/openclaw-workspace --skill agent-browser-stephaniephenex

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates web browser interactions, allowing AI agents to navigate websites, extract information, and perform actions programmatically, eliminating the need for manual browsing.

Core Features & Use Cases

  • Web Navigation: Open URLs, go back/forward, reload pages.
  • Data Extraction: Snapshot pages to get interactive elements, text, HTML, attributes, and more.
  • Form Interaction: Fill forms, click buttons, check/uncheck boxes, upload files.
  • State Management: Save and load browser session states for authentication.
  • Use Case: An AI agent can use this skill to log into a web application, fill out a complex form, and then save the session state to avoid re-authentication in future interactions.

Quick Start

Use the agent-browser skill to open the URL https://example.com.

Frequently Asked Questions about Agent Browser

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate web scraping and form filling with a headless browser?▼

You can automate web scraping and form filling by issuing structured commands to navigate URLs, click elements, type text, and snapshot page content. This headless browser approach enables AI agents to perform web interaction without manual input.

Can I save and load browser session states to avoid re-authentication during web automation?▼

Yes, web automation can save and load browser session states. This state management feature preserves authentication tokens, allowing agents to resume logged-in sessions and skip redundant login steps during subsequent web interactions.

What is the best way to extract interactive elements and text from web pages programmatically?▼

The best way to extract interactive elements and text is by taking page snapshots. Snapshots capture HTML attributes, text content, and interactive elements, enabling automated data extraction for AI agents to process web page structures efficiently.

Does browser automation work without a graphical interface for generating PDFs and screenshots?▼

Yes, browser automation works without a graphical interface using a headless Rust-based CLI with a Node.js fallback. This enables automated screenshotting and PDF generation from web pages directly from the command line.

How do I manipulate network requests during headless web interaction?▼

Headless web interaction supports network request manipulation, allowing you to intercept and modify network traffic. This enables AI agents to control data flow, simulate conditions, and extract information during automated browser sessions.

Related Skills

Explore More Software Engineering Skills→
am-willam-will
1.0k

Agent Browser

Automate web interactions with a Rust-based headless browser CLI.

Community
Advanced
mupengi-botmupengi-bot
11

data-scraper

Fetch HTML from URLs and extract structured data into JSON or Markdown.

Community
Intermediate
aresbitaresbit
46

agent-browser

Automate browser navigation, form filling, and data extraction via CLI.

Community
Intermediate
shades-of-webshades-of-web

agent-browser

Automates web page navigation, form filling, and data extraction using Python libraries like selenium and pyppeteer.

Official
Intermediate