agent-browser

Automate browser interactions for web testing, form filling, and data extraction.

Updated Feb 13, 2026
One-click install
npx skills add https://github.com/fbrier/agentic-chat-application-fred --skill agent-browser-fbrier
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/fbrier/agentic-chat-application-fred/tree/main/.claude/skills/agent-browser
Command: npx skills add https://github.com/fbrier/agentic-chat-application-fred --skill agent-browser-fbrier

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates complex browser interactions, eliminating the need for manual navigation, form filling, and data extraction from websites.

Core Features & Use Cases

  • Web Navigation: Open URLs, navigate back/forward, and reload pages.
  • Form Interaction: Fill text fields, select dropdowns, check/uncheck boxes, and submit forms.
  • Data Extraction: Extract text, HTML, attributes, and structured data from web pages.
  • Screenshots & Recording: Capture screenshots of pages or full-page captures, and record video of interactions.
  • Use Case: Automate the process of logging into a web application, filling out a multi-step form, and then extracting the confirmation details.

Quick Start

Use the agent-browser skill 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 form filling and data extraction from a web page?

Automate web form filling and data extraction by operating a browser via command-line interface, which supports navigation, element interaction via selectors, and structured data extraction. This allows deterministic execution of multi-step web interactions without manual input.

Can I capture full-page screenshots while performing browser automation?

Capture full-page screenshots during browser automation by executing specific command-line instructions. The automation skill supports taking screenshots of pages, capturing full-page content, and recording video of interactions as you navigate and interact with web elements.

How does browser automation handle complex element interaction and state management?

Browser automation handles element interaction by targeting elements via selectors or semantic locators, managing page state, and manipulating network requests. It supports filling text fields, selecting dropdowns, and submitting forms through a deterministic command-line interface.

What is the best way to extract structured data from web pages without manual navigation?

The best way to extract structured data without manual navigation is using a command-line browser automation tool. It enables you to open URLs, interact with elements via selectors, and extract text, HTML, and attributes from web pages deterministically.

Does this browser automation approach work for logging into web applications and completing multi-step forms?

This browser automation approach works for logging into web applications and completing multi-step forms by automating text field entries, dropdown selections, and form submissions. It manages navigation and state to execute these complex workflows deterministically.

How do I manipulate network requests during web testing and web scraping?

Manipulate network requests during web testing and web scraping by utilizing the automation skill's built-in network request manipulation capabilities. This allows you to control and modify request behaviors directly via the command-line interface during page interactions.