skills.rest
BoChao1Zhang
BoChao1ZhangCOMMUNITY
Explore all skills by this author →
GitHub

jina-reader

Fetch and convert web content into Markdown, text, or JSON via Jina AI Reader.

Updated Aug 27, 2026
Search Tags:#markdown#api#fetch#web-content#urls#jina-reader
One-click install
npx skills add https://github.com/BoChao1Zhang/dotfiles --skill jina-reader-bochao1zhang
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: jina-reader
Source: https://github.com/BoChao1Zhang/dotfiles/tree/main/dot_codex/skills/jina-reader
Command: npx skills add https://github.com/BoChao1Zhang/dotfiles --skill jina-reader-bochao1zhang

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Fetch, crawl, and search web content through Jina AI Reader. Use when Codex needs to convert URLs, PDFs, JavaScript-rendered pages, or search results into LLM-friendly Markdown/text/JSON with r.jina.ai or s.jina.ai; when the user says scrape, crawl, fetch this page, read this webpage, use Jina Reader, jina.ai crawler, or wants higher-rate authenticated Jina requests.

Core Features & Use Cases

  • Fetch and parse web pages into Markdown or structured text for LLMs.
  • Support reading from URLs, PDFs, and dynamic pages, enabling search-grounded content retrieval.
  • Use Case: Retrieve a long article, extract key sections, and produce a summary suitable for knowledge bases or training data.

Quick Start

Use the bundled script to fetch a URL and save the readable content to a file.

Frequently Asked Questions about jina-reader

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

FAQPage Schema
How do I convert web pages into Markdown for LLMs?▼

To convert web pages into Markdown for LLMs, fetch URLs using Jina AI Reader endpoints to extract readable text. It parses standard web pages, PDFs, and JavaScript-rendered content into structured Markdown or JSON outputs suitable for language models.

Can I scrape JavaScript-rendered pages without a headless browser?▼

Yes, you can scrape JavaScript-rendered pages without configuring a headless browser. Jina AI Reader handles dynamic content fetching directly through its reader endpoints, returning clean Markdown or text without requiring client-side execution setup.

Do I need an API key to fetch URLs with Jina Reader?▼

You need a Jina API key to fetch URLs with Jina Reader if you require higher-rate authenticated requests. Accessing the reader endpoints without a key may work but supports configurable headers for authentication and caching when a key is applied.

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

The best way to extract text from a PDF URL is passing the link directly to the Jina AI Reader. It fetches and parses the PDF document content, converting it into copy-friendly Markdown or structured text for immediate use in LLM applications.

Does Jina Reader support converting search results into structured text?▼

Jina Reader supports converting search results into structured text using the s.jina.ai endpoint. It retrieves and parses search query outputs into LLM-friendly Markdown or JSON, providing grounded content retrieval for knowledge bases.

Related Skills

Explore More Software Engineering Skills→
mikkermikker
102

visit-webpage

Convert web pages to markdown and download embedded images.

Community
Advanced
xukrutdonutxukrutdonut

docstrange

Convert PDFs and images to Markdown, JSON, CSV, or HTML with confidence scores.

Community
Basic
Kingly-AgencyKingly-Agency

rag-implementation

Build RAG pipelines that ground LLM responses with retrieved external knowledge.

Official
Advanced
appautomatonappautomaton
18

html-to-markdown

Converts HTML or live web pages into structured Markdown with metadata and link inventories.

Official
Intermediate