skills.rest
yonatangross
yonatangrossCOMMUNITY
Explore all skills by this author →
𝕏@yonyonizGitHub

browser-content-capture

Capture content from JavaScript-rendered, login-protected, and multi-page sites.

3|Updated Dec 27, 2025
Search Tags:#authentication#playwright#web-scraping#browser-automation#spa-extraction#documentation-crawl
One-click install
npx skills add https://github.com/yonatangross/create-yg-app --skill browser-content-capture
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: browser-content-capture
Source: https://github.com/yonatangross/create-yg-app/tree/main/.claude/skills/browser-content-capture
Command: npx skills add https://github.com/yonatangross/create-yg-app --skill browser-content-capture

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This skill enables reliable extraction of content from web pages that rely on JavaScript rendering, user authentication, and multi-page navigation, which standard fetchers often miss.

Core Features & Use Cases

  • SPA content extraction: Retrieve visible text from JavaScript-rendered sites and documentation.
  • Authenticated access: Handle login-protected pages using Playwright MCP or Claude Chrome extension.
  • Multi-page crawls: Traverse sidebars, pagination, and documentation trees to capture complete content.

Quick Start

  1. Navigate to a target URL using mcp__playwright__browser_navigate.
  2. Wait for the main content selector with mcp__playwright__browser_wait_for.
  3. Extract the content with mcp__playwright__browser_evaluate and process it as needed.

Frequently Asked Questions about browser-content-capture

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

FAQPage Schema
How do I extract content from JavaScript-rendered SPA pages?▼

SPA content extraction retrieves visible text from JavaScript-rendered sites by navigating to the target URL, waiting for the main content selector to load, and evaluating the page to capture dynamic content.

Can I scrape login-protected documentation sites with Playwright?▼

Login-protected documentation sites can be scraped using Playwright MCP or the Claude Chrome extension to manage authenticated browser sessions, allowing access to restricted content.

What is the best way to crawl multi-page documentation trees?▼

Multi-page documentation crawls traverse sidebars, pagination, and documentation trees to capture complete content across multiple pages using browser automation tools.

Does browser automation work for extracting content behind authentication?▼

Browser automation handles authenticated access by maintaining login sessions through Playwright MCP or the Claude Chrome extension, enabling reliable extraction from login-protected pages.

Why does standard fetching miss dynamic web page content?▼

Standard fetching misses dynamic web page content because it cannot execute JavaScript rendering, handle user authentication, or perform multi-page navigation, which browser automation solves.

What are the limitations of using Playwright for web scraping?▼

Playwright web scraping requires browser automation setup and depends on selectors matching page structure, meaning changes to dynamic content layouts may break extraction workflows.

Related Skills

Explore More Software Engineering Skills→
oakossoakoss
14

chrome-devtools

Automate and debug live Chrome browser sessions via the Model Context Protocol.

Official
Advanced
devskaledevskale
1

markdown-converter

Convert diverse document formats into Markdown using the markitdown tool.

Community
Intermediate
mburumaxwellmburumaxwell
240

agent-browser

Automate browser interactions for UI testing and content extraction.

Community
Intermediate
DaddyElonMusk69DaddyElonMusk69

scrapling

Scrape JavaScript-rendered and Cloudflare-protected web pages via CLI or Python.

Community
Advanced