markitdown

Convert PDFs, Office files, HTML, images, and more into Markdown text.

2|1|Updated Feb 5, 2026
One-click install
npx skills add https://github.com/dalehurley/phpbot --skill markitdown-dalehurley
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: markitdown
Source: https://github.com/dalehurley/phpbot/tree/main/skills/markitdown
Command: npx skills add https://github.com/dalehurley/phpbot --skill markitdown-dalehurley

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Converts a wide range of documents into Markdown text, reducing manual reformatting and content extraction work.

Core Features & Use Cases

  • Converts PDFs, Word (docx), PowerPoint (pptx), Excel (xlsx), HTML, images (OCR), audio, CSV, JSON, XML, ZIP, EPUB, and more into clean Markdown.
  • Image OCR and audio transcription support to extract text into Markdown.
  • Preserves structure such as headings, lists, and tables where supported; handles archives by iterating contents.
  • Example: turn a 100-page PDF into a Markdown document with headings and bullet lists.

Quick Start

Run the convert.py script with the path to your file to generate Markdown output.

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 to Markdown text?

To convert PDF and Word documents to Markdown, run the conversion script with your file path. It transforms PDFs, docx, and other formats into clean Markdown, preserving headings, lists, and tables.

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

Yes, you can extract text from images and audio files into Markdown. The conversion applies OCR for images and transcription for audio, turning spoken or visual content into formatted text.

What file formats are supported for Markdown conversion?

Supported formats for Markdown conversion include PDF, Word, PowerPoint, Excel, HTML, CSV, JSON, XML, ZIP, and EPUB. It handles archive files by iterating through their contents to extract text.

Do I need to manually install dependencies to convert PowerPoint and Excel files?

No, you do not need to manually install dependencies to convert PowerPoint and Excel files. The tool supports automatic installation of required packages to ensure conversion proceeds without manual setup.

Does document conversion preserve tables and lists from the original files?

Yes, document conversion preserves structural elements like tables and lists from the original files. It formats the extracted content into clean Markdown, maintaining the document's structural hierarchy where supported.