How do I install the Markitdown skill?

Run npx skillmds@latest add tomevault-io/markitdown-5 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Markitdown safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Markitdown?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Markitdown free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Markitdown?

tomevault-io (@tomevault-io) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Markitdown by tomevault-io — Agent Skill

Name: Markitdown
Author: tomevault-io

Markitdown

CLI for converting files to Markdown using Microsoft's markitdown. Use when converting PDF, DOCX, PPTX, XLSX, HTML, images, audio, or other file formats to Markdown for text analysis or LLM processing. Triggered by requests involving file-to-markdown conversion, document text extraction, or preparing files for LLM input. Use when this capability is needed.

tomevault-io Updated Sep 17, 2026

File contents

markitdown

Command-line tool for converting various file formats to Markdown. Built by Microsoft for LLM and text analysis pipelines.

Basic Usage

markitdown document.pdf                    # Convert, output to stdout
markitdown document.pdf -o output.md       # Convert, write to file
cat document.pdf | markitdown              # Convert from stdin
markitdown document.pdf > output.md        # Redirect stdout to file
markitdown < document.pdf                  # Redirect stdin

Supported Formats

Converted without any extras: HTML, CSV, JSON, XML, plain text, ZIP (iterates contents), EPub, Jupyter notebooks (.ipynb), RSS feeds, Wikipedia URLs, Bing SERP results.

With extras installed: PDF, DOCX, PPTX, XLSX, XLS, Outlook MSG, images (EXIF metadata + optional LLM captioning), audio (EXIF metadata + optional transcription), YouTube URLs (transcript extraction).

Options

markitdown -v                              # Show version
markitdown -o FILE                         # Write output to file instead of stdout
markitdown -x .pdf                         # Hint file extension (useful with stdin)
markitdown -m application/pdf              # Hint MIME type
markitdown -c UTF-8                        # Hint charset
markitdown --keep-data-uris                # Keep base64-encoded data URIs in output (truncated by default)

Azure Document Intelligence

For higher-quality extraction using cloud OCR:

markitdown -d -e "https://your-endpoint.cognitiveservices.azure.com" document.pdf

Plugins

Third-party plugins extend format support via the markitdown.plugin entry point:

markitdown --list-plugins                  # List installed plugins
markitdown -p document.xyz                 # Enable plugins for conversion

Common Patterns

Convert a file and pipe to another tool

markitdown report.pdf | wc -w                       # Word count
markitdown report.pdf | head -50                     # Preview first 50 lines

Batch convert multiple files

for f in *.pdf; do markitdown "$f" -o "${f%.pdf}.md"; done

Convert from URL (via curl)

curl -sL "https://example.com/doc.pdf" | markitdown -x .pdf

Convert and process with stdin extension hint

When piping content, provide an extension hint so markitdown can select the right converter:

cat unknown_file | markitdown -x .docx

Converted and distributed by TomeVault — claim your Tome and manage your conversions.

---name: markitdown-5description: CLI for converting files to Markdown using Microsoft's markitdown. Use when converting PDF, DOCX, PPTX, XLSX, HTML, images, audio, or other file formats to Markdown for text analysis or LLM processing. Triggered by requests involving file-to-markdown conversion, document text extraction, or preparing files for LLM input. Use when this capability is needed.---# markitdownCommand-line tool for converting various file formats to Markdown. Built by Microsoft for LLM and text analysis pipelines.## Basic Usage```bashmarkitdown document.pdf # Convert, output to stdoutmarkitdown document.pdf -o output.md # Convert, write to filecat document.pdf | markitdown # Convert from stdinmarkitdown document.pdf > output.md # Redirect stdout to filemarkitdown < document.pdf # Redirect stdin```## Supported FormatsConverted without any extras: HTML, CSV, JSON, XML, plain text, ZIP (iterates contents), EPub, Jupyter notebooks (.ipynb), RSS feeds, Wikipedia URLs, Bing SERP results.With extras installed: PDF, DOCX, PPTX, XLSX, XLS, Outlook MSG, images (EXIF metadata + optional LLM captioning), audio (EXIF metadata + optional transcription), YouTube URLs (transcript extraction).## Options```bashmarkitdown -v # Show versionmarkitdown -o FILE # Write output to file instead of stdoutmarkitdown -x .pdf # Hint file extension (useful with stdin)markitdown -m application/pdf # Hint MIME typemarkitdown -c UTF-8 # Hint charsetmarkitdown --keep-data-uris # Keep base64-encoded data URIs in output (truncated by default)```### Azure Document IntelligenceFor higher-quality extraction using cloud OCR:```bashmarkitdown -d -e "https://your-endpoint.cognitiveservices.azure.com" document.pdf```### PluginsThird-party plugins extend format support via the `markitdown.plugin` entry point:```bashmarkitdown --list-plugins # List installed pluginsmarkitdown -p document.xyz # Enable plugins for conversion```## Common Patterns### Convert a file and pipe to another tool```bashmarkitdown report.pdf | wc -w # Word countmarkitdown report.pdf | head -50 # Preview first 50 lines```### Batch convert multiple files```bashfor f in *.pdf; do markitdown "$f" -o "${f%.pdf}.md"; done```### Convert from URL (via curl)```bashcurl -sL "https://example.com/doc.pdf" | markitdown -x .pdf```### Convert and process with stdin extension hintWhen piping content, provide an extension hint so markitdown can select the right converter:```bashcat unknown_file | markitdown -x .docx```---> Converted and distributed by [TomeVault](https://tomevault.io/claim/fprochazka) — claim your Tome and manage your conversions.

Frequently asked questions