Skip to content
FunCoding

document-converter

Convert Office documents (PPTX, DOCX, XLSX, PDF, HTML, CSV, JSON, XML, images) to Markdown using Microsoft MarkItDown. Provides the agent with conversion strategies for academic and research workflows.

Star
859
Last commit
Aug 20, 2026

skills/document-converter/SKILL.md

View on GitHub

Document Converter (MarkItDown)

Convert Office and structured documents to Markdown for LLM consumption using Microsoft MarkItDown.


Overview

MarkItDown is a Microsoft open-source tool that converts a wide range of document formats into clean Markdown text. This is essential for academic research workflows where source materials arrive in diverse formats (PDFs from journals, PPTX from conferences, DOCX from collaborators, XLSX data tables).


Supported Formats

FormatExtensionsNotes
PDF.pdfText extraction; scanned PDFs require OCR
Word.docxParagraphs, tables, lists, headings preserved
PowerPoint.pptxSlide-by-slide with speaker notes
Excel.xlsx, .xlsSheet-by-sheet, tables as Markdown tables
HTML.html, .htmCleaned content extraction
CSV.csvConverted to Markdown table
JSON.jsonPretty-printed structured output
XML.xmlStructured text extraction
Images.jpg, .png, .gif, .bmp, .tiffOCR text extraction (requires optional deps)
Audio.mp3, .wavTranscription (requires optional deps)
ZIP.zipRecursively converts contained files

MCP Tool Usage

When the markitdown-mcp server is configured, use the convert_to_markdown tool:

Tool: convert_to_markdown
Parameters:
  uri: "file:///absolute/path/to/document.pptx"

The uri parameter accepts:

  • Local files: file:///path/to/file.docx
  • HTTP URLs: https://example.com/paper.pdf

Important

  • Always use absolute paths with the file:// URI scheme for local files.
  • The tool returns the full Markdown text content of the converted document.
  • For large documents, the output may be substantial. Consider summarizing or extracting relevant sections after conversion.

CLI Fallback

If the MCP server is not available, use the CLI directly via shell:

# Convert a single file
markitdown document.pptx

# Save output to file
markitdown document.pptx > output.md

# Convert from URL
markitdown https://example.com/paper.pdf

Academic Research Workflows

1. Conference Presentation Analysis

Convert a PPTX to Markdown, then analyze the content:

  1. Convert the presentation with convert_to_markdown
  2. The output preserves slide structure and speaker notes
  3. Summarize key findings, methodology, and conclusions

2. Paper Review from PDF

  1. Convert the PDF to Markdown
  2. Extract sections: Abstract, Introduction, Methods, Results, Discussion
  3. Cross-reference with literature library

3. Data Table Extraction

  1. Convert XLSX to Markdown tables
  2. Each sheet becomes a separate section
  3. Use the extracted tables for analysis or comparison

4. Batch Literature Processing

When processing multiple documents:

  1. Convert each document individually
  2. Extract metadata (title, authors, date) from the content
  3. Add to the literature library with library_add_paper

Output Quality Notes

FormatQualityCaveats
DOCXExcellentComplex layouts may lose formatting
PPTXGoodDiagrams/charts become text descriptions
XLSXGoodMerged cells may not render perfectly
PDFVariableDepends on PDF type (text vs scanned)
HTMLGoodJavaScript-rendered content not captured
CSVExcellentDirect table conversion

When to Use This Skill

  • User uploads or references an Office document (PPTX, DOCX, XLSX)
  • User wants to analyze content from a PDF
  • User needs to extract text from images (OCR)
  • User wants to convert a document for inclusion in notes or workspace
  • User asks to read, summarize, or analyze a non-Markdown file
  • Batch processing of research materials in mixed formats

When NOT to Use

  • File is already Markdown or plain text
  • User wants to edit the original document format (use appropriate editor)
  • User needs pixel-perfect layout preservation (use the original format)
  • File is a scanned PDF without OCR support configured

Troubleshooting

IssueSolution
markitdown not foundRun pip install 'markitdown[all]'
MCP tool not availableEnsure markitdown-mcp is installed and configured in openclaw.json
Empty output from PDFPDF may be scanned/image-only; needs OCR dependencies
Encoding errorsEnsure file is not corrupted; try re-saving from source application
Large file timeoutConvert via CLI instead of MCP for very large files

Installation

Local (macOS/Linux)

pip install 'markitdown[all]' markitdown-mcp

Verify

markitdown --help

Docker

MarkItDown is pre-installed in the Research-Claw Docker image.

Similar Skills

Featured

pdf

Read and edit PDFs: extract text and tables, merge, split, rotate, and fill forms.

ANanthropics/skills181k1,119 new stars in the last 7 days

Featured

canvas-design

Create posters and visual art as PNG or PDF, guided by a design philosophy.

ANanthropics/skills181k1,119 new stars in the last 7 days

Featured

docx

Create and edit Word docs with TOC, page numbers, headers and more.

ANanthropics/skills181k1,119 new stars in the last 7 days

Featured

doc-coauthoring

Co-write specs, proposals and decision docs through a structured, iterative workflow.

ANanthropics/skills181k1,119 new stars in the last 7 days

Featured

xlsx

Read and edit spreadsheets: add columns, compute formulas, format, and clean messy data.

ANanthropics/skills181k1,119 new stars in the last 7 days

Featured

pptx

Create and edit slide decks, generate slides from templates, and extract text.

ANanthropics/skills181k1,119 new stars in the last 7 days