skills.rest
hheydaroff
hheydaroffCOMMUNITY
Explore all skills by this author →
GitHub

lightpanda-browser

Fetch web pages, evaluate JavaScript, and extract readable content as markdown.

Updated Mar 9, 2026
Search Tags:#automation#content extraction#headless#web#javascript evaluation
One-click install
npx skills add https://github.com/hheydaroff/common-agent-skills --skill lightpanda-browser-hheydaroff
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: lightpanda-browser
Source: https://github.com/hheydaroff/common-agent-skills/tree/main/skills/lightpanda-browser
Command: npx skills add https://github.com/hheydaroff/common-agent-skills --skill lightpanda-browser-hheydaroff

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires puppeteer-core, @mozilla/readability, jsdom, turndown, turndown-plugin-gfm, and includes scripts (resource) components.

What problem does it solve?

Automates headless browsing tasks like fetching web pages, evaluating JavaScript, and extracting readable content without requiring a full browser setup.

Core Features & Use Cases

  • Page Fetching: Seamlessly retrieve webpage content in markdown or HTML formats for analysis.
  • Content Extraction: Extract readable text from web pages, ideal for summarization and archiving.
  • JavaScript Evaluation: Run custom scripts within the page context to gather dynamic data.
  • Use Case: Fetch and summarize articles from online sources efficiently for research or SEO audits.

Quick Start

Use the tool to fetch a webpage and extract its readable content into markdown format with a single command.

Frequently Asked Questions about lightpanda-browser

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

FAQPage Schema
How do I extract readable content from web pages using headless automation?▼

Headless automation extracts readable content from web pages by fetching HTML, evaluating JavaScript, and parsing the DOM. It uses Mozilla Readability to isolate article text and converts it into markdown format for analysis or archiving.

Can I evaluate JavaScript on dynamic web pages for data scraping?▼

Yes, you can evaluate JavaScript on dynamic web pages for data scraping. The tool uses puppeteer-core to execute custom scripts within the page context, allowing you to gather dynamic data generated by client-side frameworks.

Do I need a full browser setup to fetch webpage content into markdown?▼

No, a full browser setup is not needed to fetch webpage content into markdown. The tool simplifies headless web browsing to retrieve and parse pages directly, using dependencies like jsdom and turndown without requiring a complete browser installation.

What is the best way to automate content extraction for SEO audits?▼

Automating content extraction for SEO audits is best handled by fetching web pages and extracting readable text into markdown. This enables efficient analysis of online sources by leveraging Mozilla Readability and puppeteer-core for automated headless browsing.

Does this approach support webpage testing alongside content extraction?▼

Yes, this approach supports webpage testing alongside content extraction. It simplifies headless web browsing to fetch, evaluate, and extract content, making it suitable for automated webpage testing and dynamic data gathering without a full browser setup.

Related Skills

Explore More Content & Communication Skills→
AIDotNetAIDotNet
84

puppeteer

Automate headless Chrome tasks for PDF generation, screenshots, and web scraping.

Official
Intermediate
IndianBoy42IndianBoy42

paper-extraction

Extract structured equations, sections, references, and figures from academic PDFs into Markdown or data.

Community
Intermediate
junghan0611junghan0611
6

medium-extractor

Extract readable Markdown from Medium articles using Freedium and Scribe fallbacks.

Community
Intermediate
richardnguyen0715richardnguyen0715

scrapling

Scrape static and JavaScript-rendered web content with stealth and Cloudflare bypass.

Community
Advanced