agent-browser

Automate web browser interactions for AI agents via a command-line interface.

Updated Feb 14, 2026

Search Tags:#data extraction #browser automation #web scraping #form filling #web interaction #AI agent tool

Ready to run

npx skills add https://github.com/b9b4ymiN/JellyCore --skill agent-browser-b9b4ymin

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/b9b4ymiN/JellyCore/tree/main/nanoclaw/container/skills/agent-browser
Command: npx skills add https://github.com/b9b4ymiN/JellyCore --skill agent-browser-b9b4ymin

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill automates web browsing tasks, allowing AI agents to navigate websites, interact with elements, extract information, and even fill out forms, mimicking human interaction with a browser.

Core Features & Use Cases

Web Navigation: Open URLs, go back/forward, reload pages.
Element Interaction: Click, type, fill forms, check/uncheck, select dropdowns, hover, upload files.
Data Extraction: Get element text, HTML, attributes, page title, URL, and count elements.
Screenshots & PDF Generation: Capture screenshots of the entire page or specific elements, and save pages as PDFs.
Authentication: Save and load browser session state for authenticated access.
Use Case: An AI agent needs to research a topic online, gather data from multiple product pages, and then fill out a contact form on one of those pages.

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 browser interactions for an AI agent?▼

To automate web browser interactions for an AI agent, use this Skill to control a headless browser instance via command-line, enabling navigation, form filling, and data extraction. It mimics human browsing behavior to execute complex workflows.

Can I extract data and fill out forms during web scraping?▼

Yes, you can extract data and fill out forms during web scraping. This Skill supports element interaction like typing, checking, and selecting dropdowns, alongside data extraction for element text, HTML, and attributes.

How does browser automation handle authentication for gated content?▼

Browser automation handles authentication for gated content by saving and loading browser session state. This allows your automated workflows to maintain authenticated access across multiple browsing sessions without repeated logins.

What is the best way to capture screenshots and generate PDFs from web pages?▼

The best way to capture screenshots and generate PDFs from web pages is using this Skill's built-in capture functions. You can screenshot the entire page or specific elements, and save web pages directly as PDF files.

Does headless browser automation support complex navigation workflows?▼

Yes, headless browser automation supports complex navigation workflows including opening URLs, moving back and forward, and reloading pages. It locates elements semantically to interact with dynamic web content reliably.

Are there limitations when using a headless browser for web interaction?▼

Limitations when using a headless browser for web interaction include its operation via a command-line interface, which requires controlling a browser instance programmatically rather than through a graphical user interface.