skills.rest
yhslgg-arch
yhslgg-archCOMMUNITY
Explore all skills by this author →
GitHub

url-reader

Converts arbitrary URLs to Markdown with Firecrawl, Jina, Playwright fallbacks and local images.

187|33|Updated Feb 5, 2026
Search Tags:#markdown#firecrawl#playwright#url#jina#web-scraping#content-extraction
One-click install
npx skills add https://github.com/yhslgg-arch/url-reader --skill url-reader
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: url-reader
Source: https://github.com/yhslgg-arch/url-reader/tree/main
Command: npx skills add https://github.com/yhslgg-arch/url-reader --skill url-reader

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires firecrawl, playwright, requests, and includes scripts (resource) components.

What problem does it solve?

The Skill automates reading and converting content from arbitrary URLs into clean Markdown, saving time by removing manual copying and formatting.

Core Features & Use Cases

  • Platform-aware extraction: detects sources like 微信公众号, 小红书, 今日头条, 抖音, 淘宝, 天猫, 京东, 百度, 知乎, 微博, B站 and selects the best read strategy.
  • Three-tier strategy: Firecrawl (primary) → Jina (fallback) → Playwright (last-resort) with automatic fallbacks and error handling.
  • Local saves: formats content as Markdown and downloads embedded images to a local folder for offline use.
  • Use Case: Save a long article from a social platform as a single Markdown document with all images downloaded locally.

Quick Start

Provide a URL and I will fetch the content, convert it to Markdown, and download images to a local folder.

Frequently Asked Questions about url-reader

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

FAQPage Schema
How do I convert a web page URL to Markdown with local images?▼

To convert a web page URL to Markdown, the tool fetches the content, transforms the text into clean Markdown, and automatically downloads embedded images to a local folder for offline use.

Can I extract content from WeChat or Xiaohongshu URLs?▼

Yes, extracting content from WeChat or Xiaohongshu URLs is supported through platform-aware detection, which identifies the source and applies the best reading strategy for that specific platform.

Do I need a Firecrawl API key to extract web content to Markdown?▼

A Firecrawl API key is required as the primary method for web content extraction to Markdown, but the tool provides automatic fallbacks via Jina or Playwright if the primary method fails.

What is the best way to scrape dynamic web pages to Markdown when Firecrawl fails?▼

The best way to scrape dynamic web pages to Markdown when Firecrawl fails is using the automatic fallback strategy, which retries the extraction using Jina, and then switches to Playwright as a last resort.

Does URL content extraction work for e-commerce platforms like Taobao and JD?▼

URL content extraction works for e-commerce platforms like Taobao, Tmall, and JD through platform detection, formatting the extracted product details and descriptions into structured Markdown output.

Related Skills

Explore More Content & Communication Skills→
LuisSambranoLuisSambrano
7

firecrawl

Scrape dynamic web pages, capture screenshots, parse PDFs, and crawl URLs via the Firecrawl API.

Community
Intermediate
cas-bigdatalabcas-bigdatalab
541

docx_text_extract

Extract text from DOCX files to plain text using Python's zipfile and xml libraries.

Official
Basic
Chris-Chai-MinjaeChris-Chai-Minjae

scrapling

Automate web scraping with HTTP fetching, stealth browser automation, and spider crawling.

Community
Advanced
parcadeiparcadei
3.9k

firecrawl-scrape

Scrape web pages and extract content via Firecrawl MCP into Markdown, HTML, or plain text.

Community
Intermediate