markitdown

Convert PDFs, Word, Excel, and other files into Markdown.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/Yassire1/icath-article --skill markitdown-yassire1
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: markitdown
Source: https://github.com/Yassire1/icath-article/tree/main/.opencode/skills/markitdown
Command: npx skills add https://github.com/Yassire1/icath-article --skill markitdown-yassire1

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires openai, pdfplumber, python-docx, pandas, yt_dlp, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill enables users to convert diverse file formats into clean, structured Markdown, simplifying content review, editing, and integration with language models.

Core Features & Use Cases

  • Versatile Format Support: Converts PDFs, Word, PowerPoint, Excel, images, audio, HTML, CSV, JSON, XML, ZIP archives, EPUBs, and YouTube transcripts into Markdown.
  • AI-Enhanced Descriptions: Uses AI models via OpenRouter to generate detailed image descriptions, improving understanding of visual content.
  • Workflow Automation: Supports batch processing, recursive directory scan, and custom prompts for tailored conversions.
  • Use Case: Researchers can automatically extract text, tables, and figures from scientific papers, transforming them into token-efficient Markdown for AI analysis or notes.

Quick Start

Use the markitdown skill to convert a PDF report into Markdown format directly from the command line or within a Python script.

Frequently Asked Questions about markitdown

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

FAQPage Schema
How do I convert PDF and Word documents into Markdown for AI processing?

To convert PDFs and Word documents into Markdown, use a batch file conversion tool that extracts text, tables, and figures into clean, structured Markdown. This simplifies content review and prepares the extracted data for token-efficient language model integration.

How does AI image description work during document to Markdown conversion?

AI image description during document conversion uses OpenRouter models to generate detailed textual descriptions of visual content. This mechanism transforms images and diagrams into readable Markdown text, improving understanding of visual elements for language models.

Can I extract YouTube transcripts and Excel files into Markdown?

Yes, you can extract YouTube transcripts and Excel files into Markdown. The conversion supports diverse formats including CSV, JSON, XML, and EPUBs, transforming tabular data and video transcripts into structured text for improved content management.

What is the best way to batch convert scientific papers into Markdown?

The best way to batch convert scientific papers into Markdown is using a tool with recursive directory scanning and custom prompts. This approach automates text, table, and figure extraction from multiple files, creating token-efficient notes for AI analysis.

Do I need openai and pdfplumber dependencies for file conversion to Markdown?

You need openai and pdfplumber dependencies for extended format support during file conversion to Markdown. These libraries enable detailed content extraction from PDFs and provide AI capabilities for generating image descriptions within the converted documents.

Why does document to Markdown conversion not extract content from certain ZIP archives?

Document to Markdown conversion may not extract content from certain ZIP archives if optional dependencies are missing. Limitations arise when specific unpacking libraries are unavailable, preventing the tool from accessing nested files within the archive structure.