Skip to main content
skill CX Codex

markdown-converter · steipete — Claude Code skill: what it does, how to install

Converts documents, spreadsheets, PDF, media, and structured data into Markdown via uvx without manual parser setup.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add steipete/agent-scripts --skill markdown-converter -a claude-code
Open on GitHub

What markdown-converter does

The skill executes uvx --from "markitdown[all]" markitdown directly in the CLI. The initial run caches the required dependencies, making subsequent conversions faster. Generated output retains structural document elements including headings, tables, lists, and links.

Format support covers Office files like docx, pptx, and xlsx, web markup and data in HTML, CSV, JSON, and XML, plus EPub books and ZIP archives. For images, it extracts EXIF metadata and OCR text, while audio inputs receive EXIF extraction and transcription.

Standard conversion relies on local tooling, but complex scanned PDFs can struggle. Passing the -d flag activates Azure Document Intelligence with the -e endpoint argument. If text encoding is detected incorrectly, specify the charset manually with -c UTF-8.

What it helps with

  • convert Word, PowerPoint, and Excel files into clean Markdown
  • extract text and EXIF from images and audio files
  • turn HTML, CSV, JSON, and XML data into formatted tables and text
  • process scanned PDF documents using Azure Document Intelligence

Example prompts for the agent

  • Convert report.docx to Markdown and save it to report.md
  • Turn data.xlsx into a Markdown table using uvx markitdown
  • Extract text from scan.pdf using markitdown with the -d flag

How to install markdown-converter

1Skills CLI (Vercel)

npx skills add steipete/agent-scripts --skill markdown-converter -a claude-code

2Manually: put the files in place

~/.claude/skills/markdown-converter/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/markdown-converter/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about markdown-converter

How to install markdown-converter in Claude Code?

Run npx skills add steipete/agent-scripts --skill markdown-converter -a claude-code in your terminal.

What does markdown-converter do?

It runs the markitdown utility through uvx to convert office files, PDFs, media, and data feeds into structured Markdown.

How to fix encoding errors or poor scan extraction?

Pass -c UTF-8 to force the correct character set, or supply -d and an endpoint with -e to run Azure Document Intelligence on tricky scans.

Source text

SKILL.md · MIT
---
name: markdown-converter
description: "Markdown conversion: PDF, Office, HTML, data, OCR, audio, ZIP, YouTube."
---

# Markdown Converter

Convert files to Markdown using `uvx --from "markitdown[all]" markitdown` — no installation required.

## Basic Usage

```bash
# Convert to stdout
uvx --from "markitdown[all]" markitdown input.pdf

# Save to file
uvx --from "markitdown[all]" markitdown input.pdf -o output.md
uvx --from "markitdown[all]" markitdown input.docx > output.md

# From stdin
cat input.pdf | uvx --from "markitdown[all]" markitdown
```

## Supported Formats

- **Documents**: PDF, Word (.docx), PowerPoint (.pptx), Excel (.xlsx, .xls)
- **Web/Data**: HTML, CSV, JSON, XML
- **Media**: Images (EXIF + OCR), Audio (EXIF + transcription)
- **Other**: ZIP (iterates contents), YouTube URLs, EPub

## Options

```bash
-o OUTPUT      # Output file
-x EXTENSION   # Hint file extension (for stdin)
-m MIME_TYPE   # Hint MIME type
-c CHARSET     # Hint charset (e.g., UTF-8)
-d             # Use Azure Document Intelligence
-e ENDPOINT    # Document Intelligence endpoint
--use-plugins  # Enable 3rd-party plugins
--list-plugins # Show installed plugins
```

## Examples

```bash
# Convert Word document
uvx --from "markitdown[all]" markitdown report.docx -o report.md

# Convert Excel spreadsheet
uvx --from "markitdown[all]" markitdown data.xlsx > data.md

# Convert PowerPoint presentation
uvx --from "markitdown[all]" markitdown slides.pptx -o slides.md

# Convert with file type hint (for stdin)
cat document | uvx --from "markitdown[all]" markitdown -x .pdf > output.md

# Use Azure Document Intelligence for better PDF extraction
uvx --from "markitdown[all]" markitdown scan.pdf -d -e "https://your-resource.cognitiveservices.azure.com/"
```

## Notes

- Output preserves document structure: headings, tables, lists, links
- First run caches dependencies; subsequent runs are faster
- For complex PDFs with poor extraction, use `-d` with Azure Document Intelligence
- If automatic charset detection picks the wrong encoding for a text file, pass `-c UTF-8` (or the known charset)

© steipete · MIT · steipete/agent-scripts

Similar skills

All skills for Writing and docs →

markdown-converter by other authors comes first.

From the same set4

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor