agent-browser

Automate web browser interactions via command-line interface for navigation, form filling, and data extraction.

61|9|Updated Mar 9, 2026
One-click install
npx skills add https://github.com/jonathanmalkin/jules --skill agent-browser-jonathanmalkin
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/jonathanmalkin/jules/tree/main/.claude/skills/agent-browser
Command: npx skills add https://github.com/jonathanmalkin/jules --skill agent-browser-jonathanmalkin

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, fill forms, extract data, and perform complex online tasks programmatically.

Core Features & Use Cases

  • Web Navigation: Open URLs, go back/forward, reload pages.
  • Form Interaction: Fill text fields, select dropdowns, check boxes, click buttons.
  • Data Extraction: Scrape text, HTML, attributes, and structured data from web pages.
  • Screenshots & PDFs: Capture full-page screenshots or save pages as PDFs.
  • Session Management: Run multiple isolated browser sessions concurrently.
  • Use Case: An AI agent needs to sign up for a new service. It uses agent-browser to open the signup page, fill in the required fields (name, email, password), select options from dropdowns, check terms and conditions, and finally click the submit button.

Quick Start

Use the agent-browser skill to open the website https://example.com and take a full-page screenshot.

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 with a headless browser for AI agents?

Automate web scraping by using a command-line interface to navigate pages, extract text, HTML, and attributes, and capture structured data. This tool supports headless execution for deterministic data extraction tasks programmatically.

What is the best way to fill out web forms programmatically using browser automation?

Fill out web forms programmatically by targeting text fields, selecting dropdowns, checking boxes, and clicking buttons. The automation tool controls these interactions to complete form submissions end to end.

Can I run multiple isolated browser sessions concurrently for web automation?

Yes, you can run multiple isolated browser sessions concurrently. The session management feature supports running separate instances simultaneously to execute independent navigation and data extraction tasks.

How do I take full-page screenshots and generate PDFs during web navigation?

Take full-page screenshots and generate PDFs by issuing command-line instructions during web navigation. The automation tool captures the current page state and saves it as an image or PDF document.

Does browser automation work for deterministic web-based tasks without manual intervention?

Yes, browser automation works for deterministic web-based tasks without manual intervention. It provides a programmatic command-line interface to handle navigation, form filling, and data scraping in headless or headed execution modes.