jina-reader

Extract clean markdown from web pages for LLM consumption.

65|9|Updated Jan 29, 2026
One-click install
npx skills add https://github.com/EthanAlgoX/MarketBot --skill jina-reader
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: jina-reader
Source: https://github.com/EthanAlgoX/MarketBot/tree/main/marketbot/skills/jina-reader
Command: npx skills add https://github.com/EthanAlgoX/MarketBot --skill jina-reader

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Extracts readable, clutter-free article content from noisy web pages so language models and analysts can consume meaningful text without navigation, ads, or boilerplate.

Core Features & Use Cases

  • LLM-optimized output: Produces sanitized markdown tailored for downstream summarization, analysis, or ingestion by models.
  • Zero-configuration: Works out of the box without an API key and supports higher-rate usage when JINA_API_KEY is provided.
  • Fast web extraction: Removes menus, sidebars, and ads to surface the main article text for news, research papers, and blog posts.

Quick Start

Use jina-reader to fetch and return clean markdown from https://example.com/article for immediate LLM analysis.

Frequently Asked Questions about jina-reader

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

FAQPage Schema
How do I extract clean markdown from web pages for LLM analysis?

To extract clean markdown from web pages for LLM analysis, you can use the jina-reader skill to fetch URLs and return sanitized text with navigation, ads, and boilerplate removed.

What is the best way to prepare news articles and blog posts for LLM ingestion?

The best way to prepare news articles and blog posts for LLM ingestion is to remove menus and sidebars using a web reader tool that returns LLM-optimized markdown.

Do I need an API key to extract web content into markdown?

You do not need an API key to extract web content into markdown because the tool works out of the box, though providing a JINA_API_KEY enables higher-rate access.

Can I use jina-reader for scraping research papers from public URLs?

Yes, you can use jina-reader for scraping research papers from public URLs, as it surfaces the main article text and returns sanitized markdown optimized for model consumption.

Why does web scraping output include so much boilerplate and navigation text?

Web scraping output includes boilerplate and navigation text because standard fetchers retrieve the entire page, whereas an LLM-optimized web reader removes the clutter to extract clean markdown.