Menu
Convert Word documents (.docx) to clean Markdown with image extraction and pandoc cleanup
The review-first prompt is selected by default. You can switch to a direct command or download a local copy.
Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
A direct command skips the review prompt. Inspect the source before running it.
npx skills add https://github.com/fabioc-aloha/Alex_Plug_In --skill docx-to-mdThe command stays on one line. Scroll horizontally to inspect it before copying.
Prefer a local copy? Download the files currently available to SkillsMP.
Create and maintain ASCII visual dashboards for project tracking with parallel lane progress bars
Store and manage voice samples for TTS cloning โ portable, version-controlled audio references
Clear documentation through visual excellence
Showing SKILL.md
Based on SOC occupation classification
| name | docx-to-md |
| description | Convert Word documents (.docx) to clean Markdown with image extraction and pandoc cleanup |
| tier | extended |
| inheritance | inheritable |
| applyTo | **/*.docx,**/*word*,**/*docx* |
| muscle | .github/muscles/docx-to-md.cjs |
Ingest Word documents into your Markdown workflow โ clean, linted, version-control ready
Convert .docx files into clean, linted Markdown with extracted images, normalized headings, and cleaned table formatting. The reverse converter for ingesting external documents into a Markdown-based workflow.
| Content Type | Status | Notes |
|---|---|---|
| Headings | โ | Hierarchy normalized to start at H1 |
| Bold/Italic | โ | Converted to Markdown syntax |
| Links | โ | Preserved as Markdown links |
| Images | โ | Extracted to images/ folder |
| Tables | โ | Cleaned and aligned |
| Lists | โ | Ordered, unordered, nested |
| Code blocks | โ ๏ธ | Detected if styled as code |
| Footnotes | โ | Converted to Markdown footnotes |
| Comments | โ ๏ธ | Stripped with --strip-comments |
| Track changes | โ | Accept/reject before converting |
| Embedded objects | โ | Extract manually |
| Feature | Details |
|---|---|
| Image extraction | Embedded images saved to images/ folder with sequential naming |
| Pandoc cleanup | Removes escaped brackets, span classes, trailing backslashes |
| Table normalization | Aligns columns, adds proper separators |
| Heading fix | Normalizes hierarchy to start at H1 |
| Frontmatter | Optional YAML frontmatter with title and date |
| Comment stripping | Removes Word review comments |
# Basic conversion
node .github/muscles/docx-to-md.cjs report.docx
# With frontmatter and heading normalization
node .github/muscles/docx-to-md.cjs spec.docx --add-frontmatter --fix-headings
# Strip review comments
node .github/muscles/docx-to-md.cjs reviewed.docx --strip-comments
# Custom output path
node .github/muscles/docx-to-md.cjs input.docx output/document.md
# Debug mode (keeps raw pandoc output)
node .github/muscles/docx-to-md.cjs input.docx --debug
# Full cleanup pipeline
node .github/muscles/docx-to-md.cjs spec.docx --add-frontmatter --fix-headings --strip-comments --clean-tables
| Option | Default | Description |
|---|---|---|
--extract-images | true | Extract images to images/ folder |
--no-extract-images | - | Keep images as raw base64 in markdown |
--add-frontmatter | off | Generate YAML frontmatter with title/date |
--clean-tables | true | Normalize table column widths |
--no-clean-tables | - | Keep pandoc raw table output |
--fix-headings | off | Normalize heading hierarchy to start at H1 |
--wrap N | 0 | Wrap lines at N characters (0 = no wrap) |
--strip-comments | off | Remove Word comment annotations |
--debug | off | Keep intermediate pandoc output |
The conversion follows a multi-stage cleanup:
.docx โ pandoc โ raw MD โ cleanup โ clean MD
โ
1. Escaped brackets removed
2. Trailing backslashes removed
3. Span classes stripped
4. Image attributes cleaned
5. Comments stripped (optional)
6. Headings normalized (optional)
7. Tables reformatted
8. Images extracted
9. Frontmatter added (optional)
| Pandoc Quirk | Before | After |
|---|---|---|
| Escaped brackets | \[text\] | [text] |
| Trailing backslashes | line\ | line |
| Span classes | {.underline} | (removed) |
| Image attributes | {width="5in"} | (removed) |
| Heading anchors | {#section-1} | (removed) |
| Excessive blank lines | \n\n\n\n | \n\n |
Embedded images are extracted to a sibling images/ folder:
input/
โโโ document.docx
โโโ document.md (output)
โโโ images/
โโโ image1.png
โโโ image2.png
โโโ image3.jpg
Image references in markdown are updated automatically:
# Convert with full cleanup
node .github/muscles/docx-to-md.cjs stakeholder-spec.docx \
--add-frontmatter --fix-headings --strip-comments
# Validate output
node .github/muscles/markdown-lint.cjs stakeholder-spec.md
# Review and commit
git add stakeholder-spec.md images/
git commit -m "docs: ingest stakeholder specification"
# Batch convert all Word docs
Get-ChildItem *.docx | ForEach-Object {
node .github/muscles/docx-to-md.cjs $_.FullName --add-frontmatter --fix-headings
}
| Problem | Cause | Solution |
|---|---|---|
| "pandoc not found" | pandoc not installed | winget install pandoc |
| Images missing | Extraction failed | Check images/ folder, re-run |
| Tables misaligned | Complex table structure | Manual cleanup may be needed |
| Headings start at H3 | Original doc structure | Use --fix-headings |
| Comments in output | Track changes not stripped | Use --strip-comments |
| Encoding issues | Non-UTF8 content | Re-save .docx as UTF-8 |
winget install pandoc).github/muscles/docx-to-md.cjs (v1.0.0)
Skill version: 2.0.0 | Last updated: 2026-04-14 | Category: document-conversion
The conversion follows a multi-stage cleanup:
.docx โ pandoc โ raw MD โ cleanup โ clean MD
โ
1. Escaped brackets removed
2. Trailing backslashes removed
3. Span classes stripped
4. Image attributes cleaned
5. Comments stripped (optional)
6. Headings normalized (optional)
7. Tables reformatted
8. Images extracted
9. Frontmatter added (optional)
| Pandoc Quirk | Before | After |
|---|---|---|
| Escaped brackets | \[text\] | [text] |
| Trailing backslashes | line\ | line |
| Span classes | {.underline} | (removed) |
| Image attributes | {width="5in"} | (removed) |
| Heading anchors | {#section-1} | (removed) |
| Excessive blank lines | \n\n\n\n | \n\n |
Embedded images are extracted to a sibling images/ folder:
input/
โโโ document.docx
โโโ document.md (output)
โโโ images/
โโโ image1.png
โโโ image2.png
โโโ image3.jpg
Image references in markdown are updated automatically:
# Convert with full cleanup
node .github/muscles/docx-to-md.cjs stakeholder-spec.docx \
--add-frontmatter --fix-headings --strip-comments
# Validate output
node .github/muscles/markdown-lint.cjs stakeholder-spec.md
# Review and commit
git add stakeholder-spec.md images/
git commit -m "docs: ingest stakeholder specification"
# Batch convert all Word docs
Get-ChildItem *.docx | ForEach-Object {
node .github/muscles/docx-to-md.cjs $_.FullName --add-frontmatter --fix-headings
}
| Problem | Cause | Solution |
|---|---|---|
| "pandoc not found" | pandoc not installed | winget install pandoc |
| Images missing | Extraction failed | Check images/ folder, re-run |
| Tables misaligned | Complex table structure | Manual cleanup may be needed |
| Headings start at H3 | Original doc structure | Use --fix-headings |
| Comments in output | Track changes not stripped | Use --strip-comments |
| Encoding issues | Non-UTF8 content | Re-save .docx as UTF-8 |
winget install pandoc).github/muscles/docx-to-md.cjs (v1.0.0)
Skill version: 2.0.0 | Last updated: 2026-04-14 | Category: document-conversion