agent-browser

Automate browser navigation, data extraction, and testing via Chrome DevTools Protocol.

1|Updated Oct 29, 2011
One-click install
npx skills add https://github.com/alanzoppa/dotfiles --skill agent-browser-alanzoppa
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/alanzoppa/dotfiles/tree/main/opencode/skills/agent-browser
Command: npx skills add https://github.com/alanzoppa/dotfiles --skill agent-browser-alanzoppa

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires node, and includes scripts (resource) components.

What problem does it solve?

Automates browser interactions to simplify web navigation, form filling, data scraping, and testing processes, reducing manual effort and increasing accuracy.

Core Features & Use Cases

  • Web Navigation and Interaction: Open URLs, click elements, fill forms, and extract page data for tasks like QA testing or web scraping.
  • Session Management and Authentication: Save and reuse login states and profiles, automating repetitive login procedures.
  • Screenshot and Visual Verification: Capture page images for quality assurance and UI testing.
  • Use Case: Automate login to a web app, perform search operations, and extract key information like user data or page titles for analysis.

Quick Start

Use the agent-browser to open a webpage, then take a snapshot to verify its content, and interact with elements by referencing their element refs.

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 browser testing with Chrome DevTools Protocol?

Automate web scraping and browser testing with Chrome DevTools Protocol by controlling browser navigation, filling forms, and extracting data. This approach enables reliable interaction with dynamic web pages while capturing visual screenshots for quality assurance.

Do I need Node.js to run automated browser control workflows?

Yes, you need Node.js installed as a prerequisite to run automated browser control workflows. The environment utilizes Node.js to execute scripts that interface with the Chrome DevTools Protocol for navigation, data extraction, and session management.

Can I persist login sessions for automated web scraping tasks?

Yes, you can persist login sessions for automated web scraping tasks. The session management feature saves and reuses login states and browser profiles, allowing you to automate repetitive manual login procedures across multiple runs.

What is the best way to extract data from dynamic web pages for QA automation?

The best way to extract data from dynamic web pages for QA automation is using browser control to open URLs, interact with elements by referencing their refs, and capture page snapshots. This visual verification ensures accurate data extraction from changing content.

How do I perform visual verification during automated web testing?

Perform visual verification during automated web testing by capturing page screenshots after navigation and interaction. This allows you to verify page content, UI changes, and element states directly for quality assurance and regression testing purposes.