Docx pptx extraction

Docx pptx extraction

Skill cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-opus-4-6/organize-messy-files/docx-pptx-extraction

Extract text from DOCX and PPTX files using python-docx and python-pptx for content analysis.From its SKILL.md

Install

npx -y skills add cxcscmu/SkillLearnBench --skill docx-pptx-extraction

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

SKILL.md

0.9 KB, 192 tokens by cl100k_base, as published. Nobody here has run it

DOCX and PPTX Text Extraction

DOCX Extraction

from docx import Document

def extract_docx_text(filepath, max_paragraphs=50):
    doc = Document(filepath)
    text = "\n".join(p.text for p in doc.paragraphs[:max_paragraphs])
    return text

PPTX Extraction

from pptx import Presentation

def extract_pptx_text(filepath, max_slides=5):
    prs = Presentation(filepath)
    text = ""
    for i, slide in enumerate(prs.slides[:max_slides]):
        for shape in slide.shapes:
            if shape.has_text_frame:
                text += shape.text_frame.text + "\n"
    return text

Tips

DOCX paragraphs include headings and body text
PPTX text is in shapes within slides
Always wrap in try/except for robustness

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.