agent-browser

Automate web page navigation, form submission, and data extraction via Selenium WebDriver.

Updated Feb 2, 2026
One-click install
npx skills add https://github.com/zeketx/AgentsSDK_OpenAI_Lab --skill agent-browser-zeketx
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/zeketx/AgentsSDK_OpenAI_Lab/tree/main/skills/agent-browser
Command: npx skills add https://github.com/zeketx/AgentsSDK_OpenAI_Lab --skill agent-browser-zeketx

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires selenium, chromedriver, python, bash, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill streamlines web testing, form filling, and data extraction, enabling users to automate tasks like navigation, interactions, and screenshots with precision.

Core Features & Use Cases

  • Browser Automation: Navigate websites, interact with pages, fill forms, take screenshots, and test web applications.
  • Data Extraction: Extract information from web pages for analysis or record-keeping.
  • Use Case: Automate the process of scraping data from a product listing page, extracting details such as prices, availability, and descriptions, and saving them to a CSV file.

Quick Start

Start the agent-browser with the command: agent-browser open "https://example.com" to navigate to a webpage.

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 to extract product prices and descriptions into a CSV file?

Browser automation handles web testing and form filling by utilizing Selenium WebDriver through a Bash interface. It drives browser interactions to navigate websites, submit forms, and take screenshots for automated testing workflows.

Do I need Python and Selenium installed to use this browser automation Skill?

Yes, Python, Selenium, and ChromeDriver are required dependencies to execute browser automation. This Skill uses Selenium WebDriver through a Bash interface to navigate websites and perform interactions.

What is the best way to automate form filling and submission for web testing?

The best way to automate form filling is using a Selenium WebDriver interface that scripts navigation and form submission. This Skill automates these web interactions precisely for efficient web testing and data extraction.

Can I take screenshots during web page navigation using Selenium and Bash?

Yes, you can take screenshots during web page navigation. This Skill utilizes Selenium WebDriver through a Bash interface to automate website interactions, including capturing screenshots for web testing.

Does this web scraping tool work with browsers other than Chrome?

This web scraping tool utilizes Selenium WebDriver, which is compatible with various browsers. While ChromeDriver is a required dependency, the underlying Selenium framework supports multi-browser automation.

Why use a Bash interface for Selenium WebDriver instead of running Python scripts directly?

Using a Bash interface to run Selenium WebDriver scripts streamlines web testing and data extraction by simplifying execution commands. It allows users to trigger navigation, form filling, and scraping tasks efficiently.