One-click install
npx skills add https://github.com/januarfonti/opencode-template-configured --skill browser-januarfonti
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: browser
Source: https://github.com/januarfonti/opencode-template-configured/tree/main/skills/browser
Command: npx skills add https://github.com/januarfonti/opencode-template-configured --skill browser-januarfonti

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires puppeteer-core, and includes scripts (resource) components.

What problem does it solve?

This Skill simplifies browser automation and scraping tasks, allowing you to efficiently start Chrome, navigate pages, execute JavaScript, take screenshots, and interactively pick DOM elements.

Core Features & Use Cases

  • Start Chrome: Launch Chrome with optional profile copying, enabling remote debugging.
  • Navigate: Move to specified URLs or open new tabs.
  • Evaluate JavaScript: Execute JavaScript on the active page.
  • Screenshot: Capture the current viewport and save as a temporary file.
  • Pick Elements: Visually select DOM elements by clicking on them.
  • Use Case: Automate browser tasks like testing web applications, scraping content, or automating UI interactions.

Quick Start

Run the 'start.js' script to launch Chrome for remote debugging. Then, navigate to a website using the 'nav.js' script.

Frequently Asked Questions about browser

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate browser tasks and web scraping using the Chrome DevTools Protocol?

You can automate browser tasks and web scraping using the Chrome DevTools Protocol by launching Chrome with remote debugging enabled, navigating to URLs, and executing JavaScript to interact with DOM elements. This approach allows you to automate UI interactions and scrape content efficiently.

Do I need Puppeteer to automate Chrome and execute JavaScript on web pages?

Yes, you need Puppeteer to interact with Chrome and perform scripting tasks. The automation relies on puppeteer-core to establish a connection with the Chrome DevTools Protocol for navigating pages and executing JavaScript.

Can I visually pick DOM elements by clicking on them during browser automation?

Yes, you can visually pick DOM elements by clicking on them directly within the browser. This feature allows you to interactively select specific elements on the active page during your UI automation or exploratory site analysis.

How do I take a screenshot of the current viewport during UI automation?

You can take a screenshot of the current viewport during UI automation by executing the screenshot function. The captured image is saved as a temporary file, allowing you to review the visual state of the active page.

Can I start Chrome with my existing profile when automating web scraping tasks?

Yes, you can start Chrome with optional profile copying when automating web scraping tasks. Launching Chrome with remote debugging enabled allows you to retain your existing profile configuration while performing browser automation.