SolidMITCommunity

Doc to Markdown

Converts DOCX, PDF, PPTX, and XLSX to high-quality markdown with automatic post-processing — fixing tables, image paths, code blocks, and CJK bold spacing that raw converters miss.

Entry verified April 21, 2026

The short answer

Combines Pandoc (best-in-class extraction) with eight post-processing fixes applied automatically. Benchmarked at 7.6/10 against Docling, MarkItDown, Pandoc raw, and Mammoth.

When to use it

When someone sends a .docx brief, PDF research paper, or PowerPoint deck and you need clean markdown to edit, paste into Claude, or publish. Quick mode is fast enough for drafts; Heavy mode runs multiple tools in parallel and merges the best segments for final documents with complex layouts.

Setup

  1. 1

    Install doc-to-markdown via the daymade-skills marketplace.

  2. 2

    Requires Python with uv — the skill runs scripts/convert.py with pymupdf4llm and markitdown as extras.

  3. 3

    Quick command: uv run --with pymupdf4llm --with markitdown scripts/convert.py document.docx -o output.md --assets-dir ./media.

  4. 4

    Add --heavy for complex layouts; tests run via uv run --with pytest pytest scripts/test_convert.py -v.

Example

You: /doc-to-markdown brief.docx
Claude: [produces brief.md — headings preserved, 2 tables converted, 1 footnote inline]

Source & attribution

Author
daymade
Licence
MIT
Type
Community

Reused under a permissive licence. Preserve attribution when forking.

Caveats

Complex layout (multi-column, floats) loses fidelity. Review tables specifically.

New skills, explained plainly.

One short email when a new Claude Code skill is worth installing — and when to skip the hype. No spam.

56 skills across 10 categories, all licence-verified.