Claude Skill MartBrowse skillsWhat is a Skill?
 
← Back to list

Doc to Markdown

Converts DOCX, PDF, and PPTX files into clean Markdown with eight automatic post-processing fixes.

Docs & OfficeIntermediate★ 1,323⑂ 212AI score 9/10Last updated: Aug 8, 2026

What it does

Turns Word (DOCX), PDF, PowerPoint (PPTX) and Excel (XLSX) files into Markdown. Instead of relying on a single converter, it picks the best tool per format (Pandoc, pymupdf4llm, MarkItDown) and then applies eight automatic cleanups:

  • Broken pandoc grid tables → pipe tables or blockquotes
  • Nested image paths (media/media/) flattened, absolute paths made relative
  • Pandoc attribute noise ({width="..."}) stripped
  • CJK bold spacing fixed so **bold** renders everywhere
  • Indented dashed code blocks → fenced blocks with language detection
  • Escaped brackets and double-bracket links repaired

It also offers a Quick mode and a Heavy mode that runs several tools in parallel and merges the best segment-by-segment output, plus scripts for quality validation (text/table/image retention with an HTML report), PDF image extraction, and Windows↔WSL path conversion.

Who it's for

  • Teams migrating internal Word docs into Git-based wikis or docs sites
  • Researchers turning PDFs into clean text for LLM ingestion
  • Anyone working with Chinese/Japanese/Korean documents where bold markers break
  • Writers who need reliable table and image preservation, not just raw text

Examples

  1. "Convert this proposal.docx to markdown" → produces output.md with intact tables and a ./media folder of extracted images.
  2. "Pull all the figures out of this PDF" → extract_pdf_images.py exports images plus a metadata JSON with page and position.
  3. "Check whether the conversion lost anything" → validate_output.py reports text/table/image retention and can emit an HTML report.

· · · Install guide · · ·

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the daymade-docs/doc-to-markdown folder from the GitHub repo daymade/claude-code-skills into my ~/.claude/skills/doc-to-markdown/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/daymade/claude-code-skills.git && mkdir -p ~/.claude/skills && cp -r claude-code-skills/daymade-docs/doc-to-markdown ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal.
  2. Install the underlying tools: brew install pandoc (macOS; use choco/scoop on Windows), then pip install uv pymupdf4llm and uv tool install "markitdown[pdf]".
  3. Clone the repo: git clone https://github.com/daymade/claude-code-skills.git
  4. Create the skills folder: mkdir -p ~/.claude/skills
  5. Copy the skill in: cp -r claude-code-skills/daymade-docs/doc-to-markdown ~/.claude/skills/
  6. Restart Claude Code and try a prompt like "convert this docx to markdown".
  7. (Optional) Verify the install: uv run --with pytest pytest ~/.claude/skills/doc-to-markdown/scripts/test_convert.py -v
View source on GitHub ↗License: MIT