[Document Processing] Convert Microsoft Word (.docx) files to Markdown with GFM support (tables, images, code blocks). Cross-platform.
[IMPORTANT] Use
TaskCreateto break ALL work into small tasks BEFORE starting — including tasks for each file read. This prevents context loss from long files. For simple tasks, AI MUST ATTENTION ask user whether to skip.
Goal: Convert Microsoft Word (.docx) files to Markdown with GFM support (tables, images, formatting).
Workflow:
Key Rules:
Be skeptical. Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence percentages (Idea should be more than 80%).
Convert Microsoft Word (.docx) files to Markdown format with GitHub-Flavored Markdown support.
This skill requires npm dependencies. Run one of the following:
# Option 1: Install via ClaudeKit CLI (recommended)
ck init # Runs install.sh which handles all skills
# Option 2: Manual installation
cd .claude/skills/docx-to-markdown
npm install
Dependencies: mammoth, turndown, turndown-plugin-gfm
# Basic conversion
node .claude/skills/docx-to-markdown/scripts/convert.cjs --input ./document.docx
# Specify output path
node .claude/skills/docx-to-markdown/scripts/convert.cjs -i ./doc.docx -o ./output.md
# Preserve images to folder
node .claude/skills/docx-to-markdown/scripts/convert.cjs -i ./doc.docx --images ./images/
| Option | Short | Description | Default |
|---|---|---|---|
--input | -i | Input DOCX file path | (required) |
--output | -o | Output markdown file path | {input}.md |
--images | Directory for extracted images | inline base64 | |
--help | -h | Show help message |
DOCX → mammoth → HTML → turndown → Markdown
The two-stage conversion (DOCX→HTML→MD) follows mammoth's official recommendation for best results.
Returns JSON on success:
{
"success": true,
"input": "/path/to/input.docx",
"output": "/path/to/output.md",
"stats": {
"images": 3,
"tables": 2,
"headings": 5
}
}
TaskCreate BEFORE startingfile:line evidence for every claim (confidence >80% to act)