Doc To Markdown

What it does

When your agent uses it

• Convert document
• Docx to markdown
• Doc to markdown
• HTML to Markdown

Example prompts

• “convert document”
• “docx to markdown”
• “parse word”
• “/doc-to-markdown”

Requirements

• Python 3

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

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

What it can do on your machine

Read from SKILL.md and the folder at commit 91bed2b. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 6 files in scripts/ (Python, from the files we listed), which the agent can run.

  Shell commands in SKILL.md call:

  • uv
  • python
  • pip
  • brew

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use uv and pip, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Doc To Markdown loads about 2.5k tokens when it runs, and up to ~11k if it reads all its reference files. Until then it costs about 140 tokens; SKILL.md has 808 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~140

When it runs · the whole SKILL.md, loaded when a task matches

~2.5k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~11k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from daymade/claude-code-skills at commit 91bed2b, republished under its MIT licence (© daymade). 808 words, ~2,514 tokens.

name

doc-to-markdown

description

Converts DOCX/PDF/PPTX and saved HTML/HTM to high-quality Markdown with automatic post-processing. Fixes pandoc grid tables, simple tables, image paths, CJK bold spacing, attribute noise, and code blocks; for PDFs also strips OCR garbage blocks, repeated headers/footers/watermarks, and absolute image paths from pymupdf4llm output. Benchmarked best-in-class (7.6/10) against Docling, MarkItDown, Pandoc raw, and Mammoth. Trigger on "convert document", "docx to markdown", "parse word", "doc to markdown", "解析word", "转换文档", "HTML to Markdown".

disable-model-invocation

true

# 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

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

# 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

# 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

# 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

# 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

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

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

© daymade, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 21 other files (scripts, references, assets) in daymade-docs/doc-to-markdown of daymade/claude-code-skills.

• SKILL.md
• assets/obsidian-links/fixed.md
• assets/obsidian-links/legacy.md
• assets/obsidian-links/source.html
• assets/reader-pilot-evidence-template.json
• references/benchmark-2026-03-22.md
• references/conversion-examples.md
• references/heavy-mode-guide.md
• references/html-conversion.md
• references/obsidian-link-examples.md
• references/tool-comparison.md
• scripts/batch_html.py
• scripts/convert.py
• scripts/convert_path.py
• scripts/extract_pdf_images.py
• scripts/html_to_markdown.py
• scripts/merge_outputs.py
• … and 5 more

Open the folder on GitHubat commit 91bed2b