Md to docx
A curated collection of agent skills for your AI agents - engineering craft, prompt engineering, design, growth marketing, ...
npx -y skills add mouadja02/skills --skill md-to-docxAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 8 stars8 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Convert Markdown files to professionally formatted Word (.docx) documents with embedded PNG images — pure JavaScript, no external tools required
SKILL.md
2.7 KB, 641 tokens by cl100k_base, as published. Nobody here has run it
Markdown to Word (.docx) Skill
Convert Markdown (.md) files into professionally formatted Word (.docx) documents with embedded PNG images. Uses pure JavaScript via the docx and marked npm packages — no Pandoc, LibreOffice, or any native binary required.
How to Convert
# Install dependencies (one-time, from the scripts folder)
cd skills/md-to-docx/scripts && npm install
# Convert (run from workspace root)
node skills/md-to-docx/scripts/md-to-docx.mjs <input.md> [output.docx]
If output.docx is omitted, it defaults to <input-basename>.docx in the current directory.
Skill Folder Contents
| File | Purpose |
|---|---|
SKILL.md | This instruction file |
scripts/md-to-docx.mjs | Node.js Markdown-to-Word converter |
scripts/package.json | Dependencies (docx, marked) |
Prerequisites
| Requirement | Version | Notes |
|---|---|---|
| Node.js | 18+ | Required runtime |
docx | 9+ | Pure JS Word document generator |
marked | 15+ | Markdown parser |
No native binaries. No system-level installs. Works on Windows, macOS, and Linux.
Features
The converter:
- Extracts YAML front-matter — uses
title,date,version,audiencefor the title page - Generates a title page — with project name, subtitle, date, version, and audience
- Generates a table of contents — built from H1-H3 headings
- Embeds PNG images — resolves
references relative to the input.mdfile, reads the PNG, and embeds it inline in the Word document - Styled output — Calibri font, colored headings (
#1F3864), styled tables with alternating row colors, code blocks in Consolas - Handles all Markdown elements — headings, paragraphs, tables, code blocks, lists, images, links, horizontal rules
Image Embedding
The converter automatically embeds PNG images referenced in the Markdown:
The image path is resolved relative to the input Markdown file. The PNG is read, dimensions are extracted from the PNG header, and the image is scaled to fit within 6 inches width while preserving aspect ratio.
If an image file is not found, a placeholder [Image not found: <path>] is inserted.
Front-Matter Format
---
title: Project Name — Project Summary
date: 2025-01-15
version: 1.0
audience: Engineering Team, Architects, Stakeholders
---
The title is split on — or – into main title and subtitle for the title page.
Gives 0 of the 12 instructions most pdf office docs skills give in 641 tokens
Counted across 635 of the 690 authors here whose files we hold, read 2026-08-06
- extract text using pdfplumberin 92 of 635, across 25 files
- create PDFs using reportlabin 83 of 635, across 16 files
- read FORMS.md to fill out PDF formsin 80 of 635, across 13 files
- OCR scanned PDFs using pytesseractin 77 of 635, across 10 files
- merge or split PDFs using qpdfin 70 of 635, across 3 files
- use Excel formulas instead of hardcoded calculated valuesin 68 of 635, across 12 files
- unpack edit xml and repack existing documentsin 63 of 635, across 8 files
- document sources for hardcoded valuesin 61 of 635, across 9 files
- write minimal python code without unnecessary commentsin 59 of 635, across 7 files
- run the recalculation script after adding or modifying formulasin 58 of 635, across 6 files
- fix all identified formula errors and recalculatein 58 of 635, across 6 files
- format years as text stringsin 57 of 635, across 5 files
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.