Docx pptx extraction
Skill cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-opus-4-6/organize-messy-files/docx-pptx-extraction
[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
npx -y skills add cxcscmu/SkillLearnBench --skill docx-pptx-extractionAssembled 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
Extract text from DOCX and PPTX files using python-docx and python-pptx for content analysis.
SKILL.md
0.9 KB, 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