Doc to Markdown

Convert documents to high-quality markdown with intelligent multi-tool orchestration and automatic DOCX post-processing.

Architecture: Pandoc (best-in-class extraction) + 8 post-processing fixes (our value-add).

Quick Start

# DOCX → Markdown (one command, zero manual fixes)
uv run --with pymupdf4llm --with markitdown scripts/convert.py document.docx -o output.md --assets-dir ./media

# PDF → Markdown
uv run --with pymupdf4llm --with markitdown scripts/convert.py document.pdf -o output.md

# Saved HTML → Markdown (Pandoc required; no remote fetching)
uv run scripts/convert.py page.html -o page.md

# Run tests
uv run --with pytest pytest scripts/test_convert.py -v

Dual Mode

Tool Selection

Saved HTML And Website Manuals

For HTML/HTM, read references/html-conversion.md before converting. Use scripts/convert.py; the default converts the whole body and does not trim navigation. An explicit --html-selector selects exactly one tag, #id or .class. --html-heading-offset shifts parsed headings for assembly and rejects overflow beyond H6. Relative assets are not downloaded or copied.

Verify source href occurrences against the emitted Markdown AST, then rerun scripts/html_to_markdown.py after cleanup or merging. For manuals, map the book, chapters, lessons and internal headings before assembly; preserve code fences and reconcile rewritten anchors. Conversion success does not certify that figures are readable inside the recipient's actual Markdown reader.

DOCX Post-Processing (automatic)

When converting DOCX via pandoc, 8 cleanups are applied automatically:

PDF Post-Processing (automatic, 2026-08-30 起)

When converting PDF via pymupdf4llm, 3 cleanups are applied automatically (skip with --no-postprocess):

Heavy mode additionally prints a loud ⚠️ HEAVY MODE DEGRADED warning on stderr when one engine fails and the merge would otherwise silently degrade to single-engine output.

Known limits (learned from a 62-page Chinese research-report conversion, 2026-08-30):

• pymupdf4llm may emit duplicated paragraphs (source text layer has only one copy) — not auto-fixed; spot-check.
• Dotted TOC pages get detected as tables — rewrite the TOC manually if it matters.
• Cross-page tables are NOT merged (each page's fragment keeps its own header row) — merge manually.
• Table cells overlapped by diagonal watermarks can contain watermark character shards (dn, uFE, ...); the repeating-line stripper removes full lines only, not intra-cell shards. Watermark-heavy PDFs need cell-level rebuild (collect non-watermark spans per cell bbox).
• Complex infographics (dense in-image text) come out as images only; transcribing in-image text needs a VLM pass, not this tool.

CJK Bold Spacing — why and how

DOCX uses run-level styling (no spaces between bold/normal runs in CJK text). Markdown renderers need whitespace around ** to recognize bold boundaries.

Rule: if a **content** span contains any CJK character, ensure both sides have a space — unless already spaced or at line boundary. This handles CJK punctuation, emoji adjacency, and mixed content.

Before: 打开**飞书**，就可以    → some renderers fail to bold
After:  打开 **飞书** ，就可以  → universally renders correctly

Heavy Mode Workflow

Heavy Mode runs multiple tools in parallel and selects the best segments:

1. Parallel Execution: Run all applicable tools simultaneously
2. Segment Analysis: Parse each output into segments (tables, headings, images, paragraphs)
3. Quality Scoring: Score each segment based on completeness and structure
4. Intelligent Merge: Select best version of each segment across tools

Merge Criteria

Image Extraction

# Extract images with metadata
uv run --with pymupdf scripts/extract_pdf_images.py document.pdf -o ./extracted-images

# Generate markdown references file
uv run --with pymupdf scripts/extract_pdf_images.py document.pdf --markdown refs.md

Output:

• Images: extracted-images/img_page1_1.png, extracted-images/img_page2_1.jpg
• Metadata: extracted-images/images_metadata.json (page, position, dimensions)

Quality Validation

# Validate conversion quality
uv run --with pymupdf scripts/validate_output.py document.pdf output.md

# Generate HTML report
uv run --with pymupdf scripts/validate_output.py document.pdf output.md --report report.html

Quality Metrics

Merge Outputs Manually

# Merge multiple markdown files
python scripts/merge_outputs.py output1.md output2.md -o merged.md

# Show segment attribution
python scripts/merge_outputs.py output1.md output2.md -o merged.md --verbose

Path Conversion (Windows/WSL)

# Windows to WSL conversion
python scripts/convert_path.py "C:\Users\<windows-user>\Documents\file.pdf"
# Output: /mnt/c/Users/<windows-user>/Documents/file.pdf

Common Issues

"No conversion tools available"

# Install all tools
pip install pymupdf4llm
uv tool install "markitdown[pdf]"
brew install pandoc

FontBBox warnings during PDF conversion

• Harmless font parsing warnings, output is still correct

Images missing from output

• Use Heavy Mode for better image preservation
• Or extract separately with scripts/extract_pdf_images.py

Tables broken in output

• Use Heavy Mode - it selects the most complete table version
• Or validate with scripts/validate_output.py

Bundled Scripts

References

• references/benchmark-2026-03-22.md - 5-tool benchmark (Docling/MarkItDown/Pandoc/Mammoth/ours)
• references/heavy-mode-guide.md - Detailed Heavy Mode documentation
• references/tool-comparison.md - Tool capabilities comparison
• references/conversion-examples.md - Batch operation examples
• references/html-conversion.md - Saved HTML scope, link retention, assets and manual heading assembly

Next Step: Clean Up Converted Content

After converting documents to markdown, suggest cleanup:

Conversion complete: [N] files converted to markdown.

Options:
A) Clean up docs — run /daymade-docs:docs-cleaner to consolidate redundant content (Recommended if multiple files)
B) Check facts — run /fact-checker to verify claims in the converted content
C) No thanks — the markdown conversion is sufficient