Run3 Extract PPTX Content and Structure

Skill cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-haiku-4-5/organize-messy-files/run3_Extract-PPTX-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-PPTX-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, slide titles, and content from PowerPoint presentations to accurately determine their subject matter for classification.

SKILL.md

1.6 KB, as published. Nobody here has run it

When to use this skill

When you need to read the actual content from .pptx files
Before sorting presentations into subject folders
When filenames don't clearly indicate the presentation topic

How to extract PPTX content

Using markitdown for structured extraction

python -m markitdown input.pptx > output.md

Using Python with python-pptx

from pptx import Presentation

def extract_pptx_content(pptx_path):
    prs = Presentation(pptx_path)
    content = []
    
    for slide_num, slide in enumerate(prs.slides, 1):
        slide_text = f"--- SLIDE {slide_num} ---\n"
        
        for shape in slide.shapes:
            if hasattr(shape, "text"):
                slide_text += shape.text + "\n"
        
        content.append(slide_text)
    
    return "\n".join(content)

Key information to extract

Title slide: Main topic of presentation
Slide titles: Each slide's heading indicates content areas
Body text: Bullet points and paragraphs contain subject keywords
First 5 slides: Usually establish the presentation's main subject

Subject indicators to look for

Look for the same keyword patterns as PDF extraction
Note technical terms, proper nouns, and repeated concepts
Section headers often reveal the subject area

Store extracted content

Keep the full extracted text for analysis during subject classification.