Markdown Converter

Markdown Converter

Convert files to Markdown using uvx markitdown — no installation required.

Basic Usage

# Convert to stdout
uvx markitdown input.pdf

# Save to file
uvx markitdown input.pdf -o output.md
uvx markitdown input.docx > output.md

# From stdin
cat input.pdf | uvx 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

-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

# Convert Word document
uvx markitdown report.docx -o report.md

# Convert Excel spreadsheet
uvx markitdown data.xlsx > data.md

# Convert PowerPoint presentation
uvx markitdown slides.pptx -o slides.md

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

# Use Azure Document Intelligence for better PDF extraction
uvx 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

When To Use

• When converting PDF, Word, PowerPoint, Excel, HTML, or other supported formats to Markdown
• When preparing documents for LLM processing or text analysis pipelines
• When extracting text content from images (OCR), audio (transcription), or ZIP archives
• When converting YouTube URLs or EPubs to readable Markdown

Boundaries

• Not for Markdown-to-other-format conversion (e.g., Markdown to PDF)
• Not for editing or reformatting existing Markdown files
• Not for web scraping or crawling — operates on local files, stdin, or single URLs
• Skip Azure Document Intelligence (-d) unless standard PDF extraction is insufficient

Output

• Markdown text preserving document structure: headings, tables, lists, and links
• Written to stdout by default, or to a file with -o flag
• One Markdown output per input file or URL

Verification

• Output contains recognizable document structure (headings, tables) matching the source
• uvx is available in the environment (no pre-installation required)
• For Azure Document Intelligence, endpoint is reachable and credentials are valid
• Output file is non-empty when -o is used

Sibling skills

• fetchmd — sister format-to-markdown tool. Use this skill for file inputs (PDF, .docx, .pptx, .xlsx, image OCR); use fetchmd for web inputs (URLs or HTML).