mcq-skill-improver

Evaluate MCQs against a standardized rubric and identify failure modes.

Updated May 16, 2026
One-click install
npx skills add https://github.com/simondhalliday/uoe-skills --skill mcq-skill-improver
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: mcq-skill-improver
Source: https://github.com/simondhalliday/uoe-skills/tree/main/skills/mcq-skill-improver
Command: npx skills add https://github.com/simondhalliday/uoe-skills --skill mcq-skill-improver

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires python, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill addresses the need for evaluating and improving the quality of MCQs generated by the mcq-generator, ensuring they meet high pedagogical standards.

Core Features & Use Cases

  • MCQ Evaluation: Assess the quality of MCQs against a standardized rubric.
  • Failure Analysis: Identify common failure modes and propose targeted improvements.
  • Skill Improvement Loop: Iteratively refine the mcq-generator skill for better MCQs.
  • Use Case: When you want to ensure the MCQs generated by mcq-generator are accurate, cover all necessary material, and adhere to educational standards.

Quick Start

Run the mcq-skill-improver skill to evaluate the MCQs in the 'mcq.csv' file and receive a detailed report on their quality.

Frequently Asked Questions about mcq-skill-improver

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

FAQPage Schema
How do I evaluate multiple choice questions against a standardized rubric?

You can evaluate multiple choice questions against a standardized rubric by running this skill to assess generated MCQs, identify common failure modes, and produce a detailed report on their educational quality.

What is the best way to improve MCQ generation quality for educational materials?

The best way to improve MCQ generation quality is using an iterative skill improvement loop that analyzes failure modes in generated questions and proposes targeted refinements to the mcq-generator.

How do I identify failure modes in generated MCQs?

You identify failure modes in generated MCQs by assessing them against a standardized rubric for pedagogical standards, which highlights inaccuracies and gaps in necessary material coverage.

Do I need Python to run an MCQ quality assessment?

Yes, you need Python installed because this skill relies on Python scripts to evaluate the generated MCQs and execute the standardized rubric assessment process.

What file format is required to analyze MCQ quality using this skill?

The skill requires an 'mcq.csv' file format containing the generated multiple choice questions, which it reads to perform the evaluation and output the quality report.