$TLOGZ Prompt Flow
~/education/quiz-assessment-generator.md
$catquiz-assessment-generator.md

Quiz & Assessment Generator

Generate quizzes, tests, and assessments with varied question types, difficulty levels, and answer explanations.

Best
gpt-4o
Good
claude-sonnet-4, gemini-2.5-pro
Limited
claude-haiku, gpt-4o-mini
Updated
2026-05-22
workflow

You are an assessment designer. Generate a complete quiz or test.

Subject: {{subject}} Difficulty: {{level}} Question Count: {{questionCount || "10"}} Question Types: {{questionTypes || "Multiple choice and short answer"}} Purpose: {{purpose || "Formative assessment"}}

Assessment Structure

Instructions for Students

  • Time limit (if applicable)
  • Number of questions
  • Scoring guide
  • Passing threshold

Question Format

Q[N]. [Question Text]

  • Type: [Multiple choice / True-False / Short answer / Coding]
  • Bloom's Level: [Remember/Understand/Apply/Analyze/Evaluate/Create]
  • Difficulty: [Easy/Medium/Hard]
  • Estimated Time: [seconds/minutes]

MC Options:

A) [distractor] B) [correct answer] C) [distractor] D) [distractor]

Answer: [Correct option] Explanation: [Why this is correct + why distractors are wrong] Key Concept: [The core idea being tested]

Question Distribution

Bloom's LevelCountQuestion Numbers
Remember[N][Q#]
Understand[N][Q#]
Apply[N][Q#]
Analyze[N][Q#]
Evaluate[N][Q#]
Create[N][Q#]

Answer Key (Teacher Version)

Q1: [Answer] — [Explanation] — [Key concept] Q2: [Answer] — [Explanation] — [Key concept] ...

Scoring Rubric

Multiple Choice & True/False: 1 point each Short Answer: 2-3 points based on rubric:

  • 3 points: Complete answer with correct reasoning
  • 2 points: Correct answer, incomplete reasoning
  • 1 point: Partial understanding shown
  • 0 points: Incorrect or not attempted

Coding Questions: Graded on:

  • Correctness (40%)
  • Efficiency (20%)
  • Code quality (20%)
  • Edge cases handled (20%)

Common Misconceptions Addressed

For each major topic, note the common wrong answer and why students choose it:

  • Misconception: [wrong belief]
  • Why it's common: [root cause]
  • How to correct: [teaching strategy]

Remediation Suggestions

Based on wrong answers, recommend:

  • Students who missed Qs [N,N,N]: Review [topic]
  • Students who missed Qs [N,N,N]: Review [topic]
  • Students who scored below [threshold]: One-on-one review session

Output with bold question numbers, | table | for Bloom's distribution, --- between sections, and code for answer keys.

variables
^Enter
guide
how to use
  • Open the Quiz & Assessment Generator workflow in your AI chat interface.
  • Replace the variables in [brackets] with your specific inputs.
  • For best results, use gpt-4o as the target model.
  • Review the generated output and iterate by refining your inputs.
  • Save your final result and share it with your team.
best use cases
  • Quickly generate education-specific content with structured prompts.
  • Standardize education workflows across your team using a shared template.
  • Onboard new team members with a repeatable education process.
  • Automate quiz tasks with AI-powered education workflows.
  • Automate assessment tasks with AI-powered education workflows.
  • Automate testing tasks with AI-powered education workflows.
examples
  • Use Quiz & Assessment Generator to create a quiz project from scratch.
  • Adapt Quiz & Assessment Generator for a different education domain with custom variables.
  • Combine Quiz & Assessment Generator with other workflows in the education category for a complete pipeline.
  • Run Quiz & Assessment Generator with multiple AI models to compare output quality.
  • Schedule Quiz & Assessment Generator as a recurring education task.
variations
  • Simplified version: remove optional variables for faster results.
  • Advanced version: add custom validation steps after generation.
  • Batch version: run Quiz & Assessment Generator on multiple inputs sequentially.
  • quiz-focused variant: emphasize quiz best practices in the prompt.
  • assessment-focused variant: emphasize assessment best practices in the prompt.
common mistakes
  • Skipping variable customization — always replace [bracketed] placeholders.
  • Using the wrong AI model tier for complex outputs.
  • Not iterating on the first result — refinement improves quality significantly.
  • Ignoring quiz best practices when customizing the prompt.
  • Using gpt-4o outside its optimal use case for this workflow.
Remix