Agent Browser

Name: Agent Browser
Availability: InStock
Author: amitabhainarunachala

Automate web browser interactions for AI agents via CLI.

1|Updated Feb 14, 2026

Search Tags:#data extraction #browser automation #web scraping #form filling #ui testing #headless browser

Ready to run

npx skills add https://github.com/AmitabhainArunachala/clawd --skill agent-browser-amitabhainarunachala

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: Agent Browser
Source: https://github.com/AmitabhainArunachala/clawd/tree/main/skills/agent-browser
Command: npx skills add https://github.com/AmitabhainArunachala/clawd --skill agent-browser-amitabhainarunachala

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates web interactions, enabling AI agents to navigate websites, fill forms, extract data, and perform UI testing programmatically.

Core Features & Use Cases

Web Navigation: Open URLs, go back/forward, reload, and close the browser.
Element Interaction: Click, type, fill forms, hover, check/uncheck, select dropdowns, and drag-and-drop elements using unique references.
Data Extraction: Snapshot pages to get interactive elements, text, HTML, attributes, titles, URLs, and bounding boxes.
Screenshots & PDF: Capture screenshots of full pages or specific elements, and save pages as PDFs.
Session Management: Save and load authentication states, manage multiple browser sessions, and control cookies/local storage.

Quick Start

Use the Agent Browser skill to open the URL https://example.com and take a 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 browser interactions for AI agents?▼

Automating web browser interactions for AI agents is achieved by programmatically handling navigation, form submission, data extraction, and UI testing. This Skill supports headless or headed execution, element interaction via CSS selectors, and state management for authentication persistence.

Do I need Node.js to run headless browser automation tasks?▼

Yes, Node.js is required to run headless browser automation tasks with this Skill. It specifically requires the agent-browser CLI and a Node.js environment to execute commands for web navigation, element interaction, and session management.

How do I extract data and take screenshots from web pages programmatically?▼

To extract data and take screenshots from web pages programmatically, you can use this Skill to snapshot interactive elements, text, HTML, and attributes. It also captures full-page or element-specific screenshots and saves pages as PDFs.

Can I save and load authentication states for web scraping sessions?▼

Yes, you can save and load authentication states for web scraping sessions. This Skill provides session management to control cookies and local storage, enabling authentication persistence across multiple browser automation runs.

What is the best way to fill forms and perform UI testing using semantic locators?▼

The best way to fill forms and perform UI testing using semantic locators is through this Skill's element interaction features. It supports clicking, typing, hovering, selecting dropdowns, and drag-and-drop using unique references like CSS selectors.