web-scraper

Scrape blog and news articles from websites into JSON, Markdown, and HTML.

Updated Oct 23, 2025

Search Tags:#RSS #articles #sitemap #blog #scrape #web-scraper

Ready to run

npx skills add https://github.com/tyroneross/blog-content-scraper --skill web-scraper

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: web-scraper
Source: https://github.com/tyroneross/blog-content-scraper/tree/main/skills/web-scraper
Command: npx skills add https://github.com/tyroneross/blog-content-scraper --skill web-scraper

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill automates scraping of blog and news content from websites, answering requests to extract articles, discover RSS feeds, parse sitemaps, or generate AI-ready content with compact token counts.

Core Features & Use Cases

Smart extraction: Automatically detects whether a URL yields a single article or a listing of multiple articles.
Batch processing & discovery: Handles multiple URLs, supports RSS/sitemap discovery, and stores results for downstream use.
LLM-ready outputs: Outputs Markdown, HTML previews, and tokenized data for AI workflows.

Quick Start

Run the scraper against a URL (e.g., https://techcrunch.com) to save results as JSON, Markdown, and HTML to your workspace.