markitdown

Convert PDFs, Word, Excel, HTML, and images with OCR into Markdown.

190|28|Updated Nov 16, 2025
One-click install
npx skills add https://github.com/smallnest/goskills --skill markitdown-smallnest
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: markitdown
Source: https://github.com/smallnest/goskills/tree/main/testdata/skills/markitdown
Command: npx skills add https://github.com/smallnest/goskills --skill markitdown-smallnest

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

MarkItDown helps you convert dozens of file formats into Markdown optimized for large language models and text analysis, reducing noise and token counts while preserving structure.

Core Features & Use Cases

  • Document conversion: Convert PDFs, DOCX, PPTX, XLSX, HTML, EPUB, CSV, JSON, and more to clean Markdown with preserved headings, tables, and links.
  • Media handling: OCR on images and transcription of audio to text to unlock content inside media files.
  • Web and data extraction: Convert web pages, YouTube transcripts, RSS feeds, and structured data into readable Markdown.
  • Batch processing: Process many files or archives in one go for scalable content preparation.

Quick Start

To convert a sample PDF to Markdown, run a simple command such as:

  • markitdown sample.pdf -o sample.md

Frequently Asked Questions about markitdown

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

FAQPage Schema
How do I convert PDF files to Markdown for use with language models?

Convert PDFs to Markdown using markitdown to extract text, tables, and structure in a format optimized for LLM processing. The tool preserves headings, lists, and hyperlinks while reducing token counts, making documents suitable for embedding and RAG indexing workflows.

Can I extract text from images and audio files into Markdown?

Yes, markitdown performs OCR on images to unlock text content and transcribes audio to text, converting both directly to Markdown. Optional LLM-powered image descriptions enhance context for AI processing.

What file formats does markitdown support for conversion?

Markitdown converts PDFs, DOCX, PPTX, XLSX, HTML, EPUB, CSV, JSON, XML, images with OCR, and audio transcripts to clean Markdown with preserved document structure and optimized formatting for language models.

How do I process multiple files or archives at once?

Markitdown supports batch processing to convert many files or archives in a single operation, enabling scalable content preparation for bulk document indexing and AI workflows without manual per-file conversion.

Does markitdown work with complex PDFs that require intelligent parsing?

Yes, markitdown includes advanced features like Azure Document Intelligence for handling complex PDFs with intricate layouts, ensuring accurate structure preservation and high-fidelity Markdown output for challenging document types.

Can I convert web pages and structured data to Markdown?

Markitdown converts web pages, YouTube transcripts, RSS feeds, and structured data formats into readable Markdown, extracting relevant content while maintaining links and formatting suitable for AI text analysis.