Menu
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/lamm-mit/scienceclaw --skill docxThe command stays on one line. Scroll horizontally to inspect it before copying.
Prefer a local copy? Download the files currently available to SkillsMP.
Based on SOC occupation classification
Showing SKILL.md
| name | docx |
| description | Extract text, tables, headings, and metadata from Microsoft Word .docx files |
| metadata | null |
Microsoft Word document processing toolkit for extracting text, tables, headings, and metadata from .docx files. Useful for analyzing scientific manuscripts, grant applications, protocols, and supplementary documents shared in Word format.
Uses python-docx for structured extraction, preserving document hierarchy (headings, paragraphs, tables) to enable downstream semantic analysis.
# Extract everything from a .docx file
python3 skills/docx/scripts/docx_extract.py --file /path/to/manuscript.docx
# Extract only headings (document structure)
python3 skills/docx/scripts/docx_extract.py --file /path/to/protocol.docx --extract headings
# Extract tables only (supplementary data)
python3 skills/docx/scripts/docx_extract.py --file /path/to/supplementary.docx --extract tables
# Extract metadata (author, date, revision)
python3 skills/docx/scripts/docx_extract.py --file /path/to/grant.docx --extract metadata
{
"file": "/path/to/manuscript.docx",
"text": "Introduction\n\nProtein aggregation is a hallmark...",
"headings": [
"Abstract",
"Introduction",
"Methods",
"Results",
"Discussion",
"References"
],
"tables": [
[["Sample", "Concentration", "Activity"], ["WT", "1 uM", "100%"]]
],
"metadata": {
"author": "Jane Smith",
"title": "Novel Drug Discovery Approach",
"created": "2024-01-10T09:30:00",
"modified": "2024-02-01T14:22:00",
"revision": "5"
}
}
pip install python-docx