review-cheatsheet

Extract text from cheat-sheet images and compare it against Korean Markdown documents.

282|23|Updated Jan 3, 2026
One-click install
npx skills add https://github.com/team-attention/stanford-cs146s-kr --skill review-cheatsheet
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: review-cheatsheet
Source: https://github.com/team-attention/stanford-cs146s-kr/tree/main/.claude/skills/review-cheatsheet
Command: npx skills add https://github.com/team-attention/stanford-cs146s-kr --skill review-cheatsheet

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill analyzes cheat-sheet images using Gemini Vision to verify the content against the corresponding Korean Markdown document, ensuring consistency and accuracy.

Core Features & Use Cases

  • Image-to-text verification: Extracts text from cheat-sheet images and compares it to the translated md.
  • Quality checks: Detects textual, numerical, and contextual discrepancies, including diagrams and graphs.
  • Use Case: QA teams can validate weekly cheat-sheets before release by running batch checks across week1, week2, etc.

Quick Start

Use the review-cheatsheet skill to validate a single cheat-sheet: /review-cheatsheet week1/deep-dive-llms/tokenization Validate an entire week: /review-cheatsheet --all

Frequently Asked Questions about review-cheatsheet

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

FAQPage Schema
How do I verify image-to-text accuracy in a cheatsheet against a markdown document?

To verify cheatsheet accuracy, this skill analyzes cheat-sheet images with Gemini Vision and compares the extracted content against the corresponding Korean Markdown document to detect textual, numerical, and contextual discrepancies.

Can I batch validate multiple weekly cheatsheets before release?

Yes, QA teams can batch validate weekly cheat-sheets before release by running an --all command across week1, week2, etc., to ensure text accuracy, technical correctness, and contextual consistency across the entire batch.

What repository layout is required to verify cheatsheet content with Gemini Vision?

Verifying cheatsheet content with Gemini Vision requires a repository layout containing public/cheatsheets and docs directories, alongside Gemini Vision access to perform image analysis and validate the corresponding Korean Markdown document.

Does image analysis detect contextual discrepancies in diagrams and graphs?

Yes, image analysis with Gemini Vision detects textual, numerical, and contextual discrepancies, including issues within diagrams and graphs, ensuring visual cheat-sheet elements match the translated markdown content accurately.

How do I validate a single chapter in a weekly cheatsheet?

You validate a single cheatsheet chapter by specifying its directory path, such as week1/deep-dive-llms/tokenization, which triggers the skill to analyze that specific image and verify its content against the corresponding Korean Markdown document.