webfetch

Fetch web pages and local documents into Markdown using Jina AI Reader and markitdown.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/larsboes/pai-marketplace --skill webfetch
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: webfetch
Source: https://github.com/larsboes/pai-marketplace/tree/main/marketplace/plugins/content/skills/webfetch
Command: npx skills add https://github.com/larsboes/pai-marketplace --skill webfetch

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Convert web pages and local documents into clean Markdown so AI tools and note-taking workflows can operate on a single, consistent format.

Core Features & Use Cases

  • Fetch web pages and render them as Markdown using Jina AI Reader for fast, reliable extraction.
  • Convert local documents (PDF, DOCX, PPTX, HTML) to Markdown with markitdown to enable offline processing.
  • Optional AI summarization, entity extraction, and batch processing for large sets of content.
  • Use Case: turn a research article and its references into a searchable Markdown summary for your knowledge base.

Quick Start

Fetch a URL with webfetch.js fetch <url> to convert it to Markdown.

Frequently Asked Questions about webfetch

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

FAQPage Schema
How do I convert web pages to Markdown for AI knowledge bases?

Converting web pages to Markdown uses Jina AI Reader to fetch URLs and extract clean text. This produces a consistent Markdown format that AI tools and note-taking workflows can process directly.

Can I convert local PDF and DOCX files to Markdown offline?

Local PDF, DOCX, PPTX, and HTML files convert to Markdown using markitdown. This enables offline document processing so content teams can standardize local files without web requests.

Does webfetch support batch processing for multiple URLs and documents?

Batch processing supports converting large sets of URLs and local documents into Markdown in a single workflow. Optional AI summarization and entity extraction can also be applied across the entire batch.

What is the best way to extract entities from research articles?

Entity extraction from research articles is handled during the Markdown conversion process. After fetching the article URL or local file, optional AI summarization and entity extraction identify key data points for your knowledge base.

Do I need any external dependencies to convert HTML to Markdown?

No external dependencies are required. The Skill operates independently using Jina AI Reader for URLs and markitdown for local files, requiring no additional packages or setup to convert HTML to Markdown.