exam-analyzer

Crop exam PDF questions into separate WebP images organized by exam name.

7|2|Updated Feb 1, 2026
One-click install
npx skills add https://github.com/1000ssam/skills-for-teachers --skill exam-analyzer
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: exam-analyzer
Source: https://github.com/1000ssam/skills-for-teachers/tree/main/skills/exam-analyzer
Command: npx skills add https://github.com/1000ssam/skills-for-teachers --skill exam-analyzer

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pymupdf, pillow, numpy, and includes scripts (resource) components.

What problem does it solve?

Processing and organizing large volumes of exam PDFs is time-consuming and error-prone; manual cropping of individual questions is labor-intensive and inconsistent.

Core Features & Use Cases

  • Automatically analyze 수능/모평/학평 PDFs to identify and crop each question as a separate image.
  • Support keyword-driven matching when a textbook is available, or natural-language topic specification when it isn't.
  • Output organized crops in WebP format, grouped by exam name for easy review and archiving.

Quick Start

Process the provided exam PDFs to crop each question into separate images.

Frequently Asked Questions about exam-analyzer

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automatically crop exam questions from a PDF into separate images?

You can crop exam questions from a PDF into separate images by processing the file with automated page segmentation. The tool identifies each question and exports it as a WebP image organized by exam name.

Can I extract specific exam questions from a PDF using natural language topics?

Yes, you can extract exam questions using natural language topic specification. When a textbook is unavailable, this flexible analysis feature matches questions based on your descriptive topic input.

Does exam-analyzer work with Korean national exams like 수능 and 모평?

Yes, this tool works with Korean national exams including 수능, 모평, and 학평. It automatically analyzes these assessment PDFs to identify and crop each question into separate WebP images.

What Python dependencies are required to process and crop exam PDFs?

Processing and cropping exam PDFs requires the Python packages pymupdf, pillow, and numpy. These dependencies handle PDF text extraction, image processing, and array operations for robust page segmentation.

What is the best way to organize cropped exam questions for archiving?

The best way to organize cropped exam questions for archiving is grouping the output WebP images by exam name. The tool automatically structures the output crops this way during the page segmentation process.

How does keyword-driven matching work when extracting exam questions?

Keyword-driven matching works by extracting precise keywords from an available textbook to identify relevant questions in the exam PDF. This enables accurate targeted matching when you have a specific textbook reference.