agent-browser

Automates browser navigation, form filling, screenshots, and data extraction via command-line interface.

1|Updated Dec 20, 2018

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

Ready to run

npx skills add https://github.com/parkerhendo/home-config --skill agent-browser-parkerhendo

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/parkerhendo/home-config/tree/main/dotfiles/claude/skills/agent-browser
Command: npx skills add https://github.com/parkerhendo/home-config --skill agent-browser-parkerhendo

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill automates browser interactions, streamlining tasks like web testing, form filling, data extraction, and capturing screenshots, saving significant manual effort.

Core Features & Use Cases

Web Navigation: Open URLs, navigate back/forward, and reload pages.
Interactive Control: Click elements, fill forms, check/uncheck boxes, and select dropdown options using element references or semantic locators.
Data & Content: Extract text, HTML, attributes, and take screenshots or save pages as PDFs.
Use Case: Automate the process of logging into a web application, filling out a complex form, and then taking a screenshot of the confirmation page.

Quick Start

Use agent-browser 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 scraping and form filling without manual effort?▼

Browser automation streamlines web scraping and form filling by programmatically navigating URLs, interacting with elements, and extracting content. This Skill executes these interactions via a command-line interface, enabling deterministic task execution and state management for data extraction workflows.

Can I capture screenshots and save web pages as PDFs during web testing?▼

Yes, you can capture screenshots and save web pages as PDFs during web testing. The automation script navigates to the target URL and retrieves visual captures of the web page, applying deterministic execution to ensure consistent visual testing and content retrieval results.

What is the best way to extract text and HTML attributes from web pages?▼

The best way to extract text and HTML attributes from web pages is through automated browser interactions. This Skill targets elements using semantic locators or references, retrieving the specified content and attributes directly from the rendered page state for accurate data extraction.

Does browser automation support complex interactions like checking boxes and selecting dropdown options?▼

Browser automation fully supports complex interactions like checking boxes and selecting dropdown options. It provides interactive control mechanisms to click elements, fill forms, and toggle checkboxes, allowing you to automate intricate web application workflows like logging in and submitting complex forms.

How do I navigate back, forward, and reload pages when automating browser tasks?▼

To navigate back, forward, and reload pages when automating browser tasks, you use the built-in web navigation controls. This Skill manages the browser state, allowing you to open URLs and traverse page histories deterministically to execute multi-step web testing and data extraction sequences.