skills.rest
redisread
redisreadCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

read

Fetch public URLs or local PDFs and convert them to Markdown or summaries.

Updated Feb 20, 2026
Search Tags:#web-scraping#content-summarization#pdf-conversion#wechat-articles#markdown-extraction#url-fetching#feishu-docs
One-click install
npx skills add https://github.com/redisread/product-stories --skill read-redisread
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: read
Source: https://github.com/redisread/product-stories/tree/main/.agents/skills/read
Command: npx skills add https://github.com/redisread/product-stories --skill read-redisread

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, playwright, beautifulsoup4, lxml, readability-lxml, html2text, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill eliminates the tedious manual work of copying content from web pages or PDFs, handling messy formatting, paywalls, and hard-to-extract content automatically.

Core Features & Use Cases

  • Privacy-First Content Fetching: Fetches any public URL or local PDF with default local extraction that never sends your data to third parties, with optional proxy support for JavaScript-heavy or paywalled pages.
  • Multi-Platform Support: Dedicated handlers for Feishu/Lark documents, WeChat public account articles, GitHub content, X/Twitter posts, and standard web pages.
  • Flexible Output Formats: Returns concise summaries for simple read requests, or clean structured Markdown for conversion, citation, saving, or downstream use.
  • Use Case: For example, if you need to reference a paywalled industry report or a WeChat product analysis article for a market research task, this Skill fetches the full content and converts it to usable Markdown in seconds.

Quick Start

Simply ask the AI to read a URL or PDF, for example: "Read this Stripe product blog post and summarize the key launch decisions" or "Convert this attached PDF to clean Markdown and save it to my research notes folder."

Frequently Asked Questions about read

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

FAQPage Schema
How do I convert web pages and PDFs to clean Markdown?▼

Converting web pages and PDFs to clean Markdown involves fetching the source content and using readability algorithms to extract text, stripping away messy formatting to deliver structured Markdown.

Can I extract content from WeChat public account articles and Feishu documents?▼

Yes, you can extract content from WeChat public account articles and Feishu documents using dedicated extraction handlers that parse platform-specific formatting into clean Markdown.

Does local URL fetching work for JavaScript-heavy or paywalled web content?▼

Local URL fetching defaults to privacy-first extraction, but you can enable optional opt-in proxy services to cascade requests for JavaScript-heavy or paywalled web content that local extraction fails to access.

What is the best way to summarize web content from a URL?▼

The best way to summarize web content from a URL is to fetch the page using local extraction algorithms and align the parsed text into concise summaries tailored to your specific intent.

How do I extract GitHub repositories and X/Twitter posts into structured text?▼

You extract GitHub repositories and X/Twitter posts into structured text by using dedicated extraction methods that fetch the public URL and convert the platform-specific layout into Markdown.

Are there limitations when fetching paywalled industry reports?▼

Fetching paywalled industry reports has limitations where local extraction fails, requiring optional proxy cascades to bypass paywalls, alongside guardrails for untrusted content handling and safe file saving.

Related Skills

Explore More Content & Communication Skills→
vibewatchvibewatch

fetch-url

Fetch URLs and extract readable text from HTML pages and PDFs.

Official
Intermediate
shynlee04shynlee04

web-search

Search the web and extract content via Tavily and Exa using the inference.sh CLI.

Community
Intermediate
eddmanneddmann
2

playwright

Render dynamic web pages with Playwright to capture HTML, text, and screenshots.

Community
Intermediate
aselimcaselimc

read-software-docs

Fetch and convert HTML documentation pages to Markdown.

Community
Intermediate