skills.rest
arnaudjnn
arnaudjnnCOMMUNITY
Explore all skills by this author →
𝕏@arnaudjnnGitHub

agent-browser

Automate web browsing, form filling, data extraction, and screenshots via CLI.

1|21|Updated Feb 26, 2026
Search Tags:#testing#data extraction#form filling#web automation#scraping#browser
One-click install
npx skills add https://github.com/arnaudjnn/nanoclaw-railway --skill agent-browser-arnaudjnn
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/arnaudjnn/nanoclaw-railway/tree/main/container/skills/agent-browser
Command: npx skills add https://github.com/arnaudjnn/nanoclaw-railway --skill agent-browser-arnaudjnn

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill automates web browsing tasks, allowing agents to navigate websites, interact with elements, extract data, and take screenshots, streamlining online research and web application testing.

Core Features & Use Cases

  • Web Navigation: Open URLs, go back/forward, reload pages.
  • Element Interaction: Click, fill forms, type, hover, check/uncheck, select dropdowns.
  • Data Extraction: Get element text, HTML, values, attributes, page title, URL, and count elements.
  • Screenshots & PDF: Capture full-page screenshots or save pages as PDFs.
  • Authentication: Save and load browser state for seamless logins.
  • Use Case: Researching a topic by visiting multiple websites, filling out a contact form on a webpage, or extracting product details from an e-commerce site.

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 scraping and form filling without writing complex browser scripts?▼

Web automation is handled by executing CLI commands that navigate URLs, fill forms, and extract data using semantic locators. This allows you to automate browsing tasks, interact with elements, and take screenshots without managing complex browser scripts directly.

What is the best way to extract text and HTML from web pages during automated browsing?▼

Data extraction is supported by retrieving element text, HTML, values, and attributes directly from the page. You can also count elements, get the page title, and capture the current URL to gather comprehensive details during your browsing session.

Can I save and reuse authentication states for websites that require login?▼

Authentication state management is supported, allowing you to save and load browser states for seamless logins. This ensures that your web automation tasks can maintain authenticated sessions across multiple runs without repeatedly entering credentials.

Does web automation support taking full-page screenshots and saving pages as PDFs?▼

Screenshots and PDF generation are fully supported, enabling you to capture full-page screenshots or save web pages as PDFs. This is useful for archiving web application states or documenting research results during automated browsing.

What types of web element interactions are supported for automated form filling?▼

Element interaction includes clicking, typing, hovering, checking and unchecking boxes, and selecting dropdown options. These actions allow you to fully automate form filling and interact with various web components using semantic locators.

How do I navigate between multiple URLs when researching topics across different websites?▼

Web navigation is supported by opening URLs, moving back and forward, and reloading pages. This allows you to automate research across multiple websites seamlessly, extracting data and taking screenshots as you navigate.

Related Skills

Explore More Software Engineering Skills→
zhu1090093659zhu1090093659
80

agent-browser

Automate web browser navigation, form filling, and data extraction via CLI.

Community
Intermediate
trielofftrieloff

identify-page-structure

Map sections and content sequences from scraped webpages.

Community
Intermediate
amychina12amychina12

paper-standardizer

Standardize raw academic paper data into analysis-ready datasets with Python codebooks.

Community
Advanced
logeshv586-codelogeshv586-code

Agent Browser

Automate web interactions with a headless browser using Node.js.

Community
Advanced