Document text extraction

Skill cxcscmu/SkillLearnBench/skills/b1-one-shot-gemini-3.1-pro-preview/organize-messy-files/document-text-extraction

[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 document-text-extraction

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

Extracts text from PDF, DOCX, and PPTX files using Python.

SKILL.md

1.1 KB, as published. Nobody here has run it

Document Text Extraction

Use libraries like PyMuPDF (fitz), python-docx, and python-pptx to extract text from documents.

Installation

pip install PyMuPDF python-docx python-pptx

Python Code Examples

PDF Extraction

import fitz

def extract_pdf(file_path):
    doc = fitz.open(file_path)
    text = ""
    # Just read the first few pages to save time/memory for classification
    for page in doc[:3]:
        text += page.get_text()
    return text

DOCX Extraction

from docx import Document

def extract_docx(file_path):
    doc = Document(file_path)
    return "\n".join([p.text for p in doc.paragraphs[:50]])

PPTX Extraction

from pptx import Presentation

def extract_pptx(file_path):
    prs = Presentation(file_path)
    text = ""
    for slide in prs.slides[:5]:
        for shape in slide.shapes:
            if hasattr(shape, "text"):
                text += shape.text + "\n"
    return text