markitdown

Convert PDF, DOCX, PPTX, XLSX, images, audio, HTML, CSV, JSON, XML, ZIP, EPUB, and YouTube URLs to Markdown.

1|Updated Jan 14, 2026
One-click install
npx skills add https://github.com/Sologa/codex-pipeline --skill markitdown-sologa
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: markitdown
Source: https://github.com/Sologa/codex-pipeline/tree/main/.codex/skills/markitdown
Command: npx skills add https://github.com/Sologa/codex-pipeline --skill markitdown-sologa

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill streamlines the process of converting a wide variety of file formats into Markdown, making content easily digestible and processable by LLMs.

Core Features & Use Cases

  • Universal Conversion: Supports over 15 file types including PDFs, Office documents, images (with OCR), audio (with transcription), HTML, CSV, JSON, XML, ZIP, and YouTube URLs.
  • LLM-Friendly Output: Generates token-efficient Markdown, ideal for inputting into language models.
  • AI Enhancement: Offers optional AI-powered image descriptions and OCR for scanned documents.
  • Use Case: Convert a complex research paper in PDF format, along with its embedded images and tables, into a clean Markdown document suitable for analysis by an AI.

Quick Start

Use the markitdown skill to convert the file named 'report.docx' into a markdown file.

Frequently Asked Questions about markitdown

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

FAQPage Schema
How do I convert a PDF to Markdown for LLM input?

You can convert a DOCX file to Markdown by using markitdown to extract text and structure from Office documents into a token-efficient format, creating clean output ideal for language model processing.

Can I transcribe audio files into text for LLM processing?

Yes, you can transcribe audio files into text for LLM processing. The conversion supports audio transcription, transforming spoken content into Markdown text representations suitable for AI input.

Does converting images to Markdown support OCR for scanned documents?

Converting images to Markdown supports OCR for scanned documents. It also offers AI-enhanced image descriptions via Azure Document Intelligence or OpenRouter to extract text from visual content.

What is the best way to extract text from a YouTube URL for AI analysis?

The best way to extract text from a YouTube URL for AI analysis is using a file conversion tool that processes video URLs directly into Markdown, providing a token-efficient text representation of the content.

What file formats are supported when converting documents to Markdown?

Supported file formats for converting documents to Markdown include PDF, DOCX, PPTX, XLSX, images, audio, HTML, CSV, JSON, XML, ZIP, and EPubs, ensuring broad content compatibility.