agent-browser

Automate web browser interactions including navigation, form filling, data extraction, and screenshots.

Updated Feb 22, 2026
One-click install
npx skills add https://github.com/nutterbrand/nanoclaw --skill agent-browser-nutterbrand
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/nutterbrand/nanoclaw/tree/main/container/skills/agent-browser
Command: npx skills add https://github.com/nutterbrand/nanoclaw --skill agent-browser-nutterbrand

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates web browsing tasks, allowing for research, interaction with web applications, and data extraction without manual intervention.

Core Features & Use Cases

  • Web Navigation: Open, close, and navigate between web pages.
  • Element Interaction: Click, fill forms, type, hover, check/uncheck, and select options using element references or semantic locators.
  • Data Extraction & Screenshots: Extract text, HTML, attributes, and take screenshots or save pages as PDFs.
  • Authentication: Save and load browser authentication states for seamless access to logged-in sessions.

Quick Start

Use the agent-browser skill to open the URL https://www.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 form filling and data extraction?

Automate web browser interactions by targeting elements via CSS selectors or semantic roles to navigate, fill forms, extract data, and capture screenshots without manual intervention. This handles dynamic web applications reliably.

Can I save and reuse authentication states for web automation tasks?

Yes, you can save and load browser authentication states for web automation. This allows seamless access to logged-in sessions during navigation, data extraction, and dynamic web application testing.

What is the best way to scrape dynamic web application content?

Scraping dynamic web application content requires precise element targeting using CSS selectors or semantic locators. This approach automates navigation and extracts text, HTML, and attributes reliably from interactive pages.

How do I capture screenshots and save web pages as PDFs during web scraping?

Capture screenshots and save pages as PDFs during web scraping by automating browser navigation to the target URL. The automation interacts with the page and extracts visual or document outputs directly.

Do I need CSS selectors to interact with web elements for automated testing?

Yes, precise element targeting via CSS selectors or semantic roles and attributes is required for reliable execution. Automated testing and form filling depend on these locators to interact with web elements accurately.