agent-browser

Automate web research, navigation, and data extraction by controlling a browser.

Updated May 7, 2026

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

Ready to run

npx skills add https://github.com/Bartunek/nanoclaw --skill agent-browser-bartunek

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automate web research, navigation, and data extraction by controlling a browser to perform tasks across sites and collect results.

Core Features & Use Cases

Navigate pages, snapshot the DOM, and interact with elements using references from snapshots
Fill forms, submit data, capture screenshots, and verify content for testing and automation
Extract data across multiple pages or sites and assemble results for reporting

Quick Start

Open a URL and let agent-browser automate tasks such as navigation, element interaction, and data extraction.

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 data extraction across multiple sites?▼

Automate web scraping and data extraction by controlling a browser runtime to navigate pages, interact with elements, and assemble captured data across multiple sites. It requires a browser-automation environment to execute these navigation and interaction commands.

Can I use browser automation for form filling and web testing?▼

Browser automation supports form filling and web testing by navigating to pages, interacting with elements using DOM snapshot references, and submitting data. You can verify content and capture screenshots to validate visual checks and form behavior.

How do I interact with page elements during web automation tasks?▼

Interact with page elements during web automation by taking a DOM snapshot and using the specific element references from that snapshot. This allows precise interaction for clicking, typing, and submitting data across navigated pages.

What is the best way to extract data from multiple pages and capture screenshots?▼

The best way to extract data and capture screenshots is using browser automation to navigate across multiple pages, snapshot the DOM, and interact with elements. This approach assembles extracted data and visual captures into assembled reporting results.

Do I need a specific runtime to perform headless browser automation?▼

Headless browser automation requires a compatible browser-automation runtime to function. The skill relies on this external runtime to handle navigation, wait conditions, state management, and element interaction without a graphical interface.

How does state management work when automating navigation across multiple pages?▼

State management during multi-page navigation works by maintaining browser session data and applying wait conditions between page transitions. This ensures elements are fully loaded before attempting interactions or data extraction on subsequent pages.