skills.rest
OiAnthony
OiAnthonyCOMMUNITY
Explore all skills by this author →
GitHub

read

Fetch URLs and PDFs and convert content into Markdown or summaries.

8|Updated Jan 19, 2026
Search Tags:#web scraping#pdf extraction#wechat#markdown conversion#feishu#source summarization#url reading
One-click install
npx skills add https://github.com/OiAnthony/.agents --skill read-oianthony
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: read
Source: https://github.com/OiAnthony/.agents/tree/main/skills/read
Command: npx skills add https://github.com/OiAnthony/.agents --skill read-oianthony

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill removes the friction of opening, copying, and cleaning content from web pages, PDFs, Feishu docs, and WeChat articles by fetching the source and turning it into readable Markdown or concise summaries.

Core Features & Use Cases

  • URL and PDF reading: Fetches public web pages and PDFs, then returns grounded summaries, quotes, citations, or clean Markdown depending on what the user asked for.
  • Source-specific routing: Uses dedicated handling for GitHub raw content, Feishu documents, WeChat articles, and PDF extraction to improve reliability across common document sources.
  • Workflow support: Saves converted output when requested and supports downstream research, quoting, translation, extraction, and learning tasks.
  • Use case: A user shares a report link and asks for the main points, then the Skill retrieves the page and gives a concise summary with key details.

Quick Start

Ask the read skill to fetch the URL or PDF and return the useful content as a concise summary or clean Markdown based on your request.

Frequently Asked Questions about read

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

FAQPage Schema
How do I extract text from a web article and convert it to Markdown?▼

To extract text from a web article and convert it to Markdown, you need a tool that fetches the URL and parses the HTML. This Skill performs web scraping and returns clean Markdown or grounded summaries from public web pages.

Can I extract content from WeChat posts and Feishu documents?▼

Yes, you can extract content from WeChat posts and Feishu documents. This Skill uses source-specific routing to reliably fetch and parse these specialized platforms, reformatting their content into usable text or citations.

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

The best way to summarize a PDF from a URL is using a tool with dedicated PDF extraction and source-grounded summarization. This Skill retrieves local or remote PDFs and extracts main points, quotes, or clean Markdown.

Does this tool work for fetching raw files from GitHub?▼

Yes, this tool works for fetching raw files from GitHub. It applies routing-aware fetching dedicated to GitHub raw content, ensuring reliable extraction of file contents and converting them into usable Markdown.

How do I safely extract content from untrusted web pages?▼

To safely extract content from untrusted web pages, the tool must apply safe handling during the routing-aware fetching process. This Skill securely retrieves untrusted page content and reformats it into sanitized Markdown or summaries.

Are there limitations when scraping dynamic web pages with Playwright?▼

While this Skill uses Playwright and BeautifulSoup for web scraping, limitations arise with highly dynamic pages requiring complex interactions. It focuses on source-grounded extraction of static text, summaries, and citations rather than automated browser workflows.

Related Skills

Explore More Education & Research Skills→
einargudnigeinargudnig

read

Fetch web pages and PDFs and convert them to Markdown.

Community
Advanced
gotalabgotalab
406

notion-research-documentation

Search Notion pages, synthesize findings, and publish structured research reports with citations.

Community
Basic
aivos-xieaivos-xie
1

llm-wiki

Parse Markdown documents into a structured knowledge base for cross-referencing and queries.

Community
Advanced
Quill-AgentQuill-Agent
3

nano-pdf

Edit PDF text via natural language prompts using the nano-pdf tool.

Community
Basic