Run3 Extract DOCX Content and Structure

Skill cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-haiku-4-5/organize-messy-files/run3_Extract-DOCX-Content-and-Structure

[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.

Install

npx -y skills add cxcscmu/SkillLearnBench --skill run3_Extract-DOCX-Content-and-Structure

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

What its author says it does

Copied from the file, not written here

Use this skill to extract text and structure from Word documents (.docx files) to determine their subject for classification into the correct folder.

SKILL.md

1.5 KB, as published. Nobody here has run it

When to use this skill

When you need to read content from .docx files
Before sorting Word documents into subject folders
When document filenames are generic or unclear

How to extract DOCX content

Using python-docx

from docx import Document

def extract_docx_content(docx_path):
    doc = Document(docx_path)
    content = []
    
    for para in doc.paragraphs:
        if para.text.strip():
            content.append(para.text)
    
    # Also extract from tables if present
    for table in doc.tables:
        for row in table.rows:
            for cell in row.cells:
                if cell.text.strip():
                    content.append(cell.text)
    
    return "\n".join(content)

Using markitdown

python -m markitdown input.docx > output.md

Key information to extract

Document title/heading: Top of document (usually styled as heading)
First paragraph: Introduces the document's main topic
Section headers: Reveal subject areas covered
Keywords and technical terms: Identify the subject domain

Subject indicators

Use same keyword patterns as PDF and PPTX extraction
Pay attention to document structure and headings
Read first page thoroughly as it typically establishes the subject

Store extracted content

Retain the full text for subject classification analysis.