agentleFS
nisarthnisarth/claude-skills-store/skills/education/quiz-generator/SKILL.md

quiz-generator

Skill1 starsChanged 7 months agoMITView on GitHub

Generate quizzes and assessments with multiple choice, short answer, true/false, and matching questions, including rubrics, difficulty levels, and answer keys. Trigger with "create a quiz", "generate test questions", "make an assessment on", "quiz me on", "practice questions for", or when the user needs formative or summative assessment items.

13 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use chapter-content-generator, course-description-analyzer and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • vishalsachdevSkill

    chapter-content-generator

    This skill generates comprehensive chapter content for intelligent textbooks after the book-chapter-generator skill has created the chapter structure. Use this skill when a chapter index.md file exists with title, summary, and concept list, and detailed educational content needs to be generated at the appropriate reading level with rich non-text elements including diagrams, infographics, and MicroSims. (project, gitignored)

    Also in 4 projects that use this

  • vishalsachdevSkill

    course-description-analyzer

    This skill analyzes or creates course descriptions for intelligent textbooks by checking for completeness of required elements (title, audience, prerequisites, topics, Bloom's Taxonomy outcomes) and providing quality scores with improvement suggestions. Use this skill when working with course descriptions in /docs/course-description.md that need validation or creation for learning graph generation.

    Also in 4 projects that use this

  • dmccrearySkill

    book-installer

    Installs and configures intelligent-textbook infrastructure - scaffold a brand-new MkDocs Material textbook (init textbook), install any of 41 features (math, mascot, learning graph viewer, Google Analytics GA4, custom 404, kanban board), and generate book metrics. Routes to the appropriate installation guide.

    Also in 3 projects that use this

  • nek1987Skill

    faq-generator

    Generate faq generator operations. Auto-activating skill for Technical Documentation. Triggers on: faq generator, faq generator Part of the Technical Documentation skill category. Use when working with faq generator functionality. Trigger with phrases like "faq generator", "faq generator", "faq".

    Also in 4 projects that use this

  • +8 more from vishalsachdev

The file

Show its rules and text

We split this skill into the rules it gives an agent

16 rules. 0 are common, 16 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 11 edited versions we read keep these.

  • 16

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask about any specific learning objectives or standards the quiz should align to.

    line 43
  2. Distinctive:

    Content coverage: Ensure all key subtopics are represented proportionally.

    line 55
  3. Distinctive:

    Avoid "all of the above" and "none of the above."

    line 69
  4. Distinctive:

    Ensure options are parallel in length and grammatical structure.

    line 70
  5. Distinctive:

    Ask for specific, bounded responses (not open-ended essays).

    line 74
  6. Distinctive:

    Test one concept per statement — no compound statements.

    line 79
  7. Distinctive:

    Avoid negatives and double negatives.

    line 80
  8. Distinctive:

    Keep all items in the same category (do not mix dates with definitions).

    line 86
  9. Distinctive:

    Verify content accuracy for every question and answer.

    line 108
  10. Distinctive:

    Check that no question gives away the answer to another question.

    line 109
  11. Distinctive:

    Ensure reading level is appropriate (test the content, not reading ability, unless it is an ELA assessment).

    line 110
  12. Distinctive:

    Remove bias: no questions that advantage students based on background rather than knowledge.

    line 112
  13. Distinctive:

    Test what you taught: every question should map to a stated learning objective.

    line 167
  14. Distinctive:

    Write the answer key simultaneously with the questions to catch ambiguity early.

    line 168
  15. Distinctive:

    Avoid trick questions — the goal is to assess knowledge, not reading comprehension of tricky wording.

    line 170
  16. Distinctive:

    If generating questions from a specific text or source, note which section each question references.

    line 172

“Common” is measured: kept by at least 6 in 10 of the 11 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Quiz Generator

Generate well-crafted assessment items across multiple question types with varying difficulty levels, complete answer keys, scoring rubrics, and alignment to learning objectives.

Workflow

Step 1: Define Assessment Parameters

Clarify what the quiz should measure:

  • Confirm the topic, subtopics, and scope of content to assess.
  • Determine the purpose: formative (check understanding), summative (evaluate mastery), or diagnostic (identify gaps).
  • Identify the target audience and their level (grade, course, proficiency).
  • Agree on question types, count, and difficulty distribution.
  • Ask about any specific learning objectives or standards the quiz should align to.
  • Determine time constraints (e.g., 20-minute quiz vs. full-period exam).

Step 2: Design Question Distribution

Plan the quiz structure for balanced assessment:

  • Difficulty distribution (for "progressive" mode):
    • 30% easy: recall and basic comprehension.
    • 50% medium: application and analysis.
    • 20% hard: evaluation, synthesis, or multi-step reasoning.
  • Bloom's Taxonomy coverage: Include questions across at least 3 cognitive levels.
  • Content coverage: Ensure all key subtopics are represented proportionally.
  • Question type mix (for "mixed" mode):
    • 40-50% multiple choice (efficient, objective scoring).
    • 20-30% short answer (demonstrates understanding beyond recognition).
    • 10-20% true/false or matching (quick knowledge checks).
    • 10-20% extended response (deeper thinking, if appropriate).

Step 3: Write Questions by Type

Craft each question following assessment best practices:

Multiple Choice

  • Stem: clear, concise, and self-contained (answerable without reading options).
  • 4 options: one correct answer, 3 plausible distractors based on common misconceptions.
  • Avoid "all of the above" and "none of the above."
  • Ensure options are parallel in length and grammatical structure.
  • Randomize correct answer positions (not always B or C).

Short Answer

  • Ask for specific, bounded responses (not open-ended essays).
  • Specify expected length ("in 2-3 sentences" or "list three examples").
  • Provide clear scoring criteria for partial credit.

True/False

  • Test one concept per statement — no compound statements.
  • Avoid negatives and double negatives.
  • Balance true and false answers roughly equally.
  • Require a brief justification ("True or false? Explain your reasoning in one sentence.").

Matching

  • Provide more options than prompts to reduce guessing.
  • Keep all items in the same category (do not mix dates with definitions).
  • Limit to 6-8 items to avoid cognitive overload.

Essay / Extended Response

  • Provide a clear prompt with scope constraints.
  • Include a rubric with defined performance levels.
  • Specify what a strong answer includes (e.g., "Your response should reference at least two examples").

Step 4: Create Answer Key and Rubrics

Build comprehensive scoring materials:

  • Answer key: Correct answer for each question with brief explanation of why it is correct.
  • Distractor analysis: For multiple choice, note which misconception each distractor targets.
  • Partial credit guidelines: For short answer and essay, define what earns full, partial, and no credit.
  • Rubric (for extended response): 3-4 performance levels with specific descriptors.
  • Point values: Assign points reflecting question difficulty and cognitive demand.

Step 5: Review and Finalize

Quality-check the assessment:

  • Verify content accuracy for every question and answer.
  • Check that no question gives away the answer to another question.
  • Ensure reading level is appropriate (test the content, not reading ability, unless it is an ELA assessment).
  • Confirm the quiz is completable within the stated time limit (estimate 1-2 min per MC, 3-5 min per short answer).
  • Remove bias: no questions that advantage students based on background rather than knowledge.

Output Format

# Quiz: [Topic]

**Subject**: [Subject] | **Level**: [Grade/Course]
**Questions**: [Count] | **Time limit**: [Minutes] min
**Total points**: [Points]

---

## Questions

### Q1. [Question text] [Difficulty: Easy | Medium | Hard] [Points: X]
(a) [Option A]
(b) [Option B]
(c) [Option C]
(d) [Option D]

### Q2. [Short answer question] [Difficulty: Medium] [Points: X]
*Expected length: [2-3 sentences]*

[Continue for all questions...]

---

## Answer Key

| # | Answer | Explanation | Points |
|---|--------|-------------|--------|
| 1 | (c) | [Why this is correct; what misconception each distractor tests] | X |
| 2 | [Model answer] | [Scoring: full credit for..., partial for...] | X |

## Scoring Rubric (for extended response questions)

| Criteria | Excellent (4) | Proficient (3) | Developing (2) | Beginning (1) |
|----------|--------------|-----------------|-----------------|----------------|
| [Criterion] | [Description] | [Description] | [Description] | [Description] |

Examples

User: "Create a 15-question quiz on the American Revolution for 8th grade" Action: Generate a mix of MC (8), short answer (4), matching (1 set), and one extended response. Cover causes, key events, key figures, and outcomes. Progressive difficulty.

User: "Practice questions for AP Calculus AB — focus on integration" Action: Generate 10 progressive questions on definite/indefinite integrals, u-substitution, and area under curves. Include worked solutions in the answer key.

User: "Quick formative check on Python loops for beginners" Action: Generate 5 easy-medium questions: 2 MC on syntax, 2 code-prediction short answers, 1 fill-in-the-blank with a for loop. Include common error patterns as distractors.

Best Practices

  • Test what you taught: every question should map to a stated learning objective.
  • Write the answer key simultaneously with the questions to catch ambiguity early.
  • Distractors should reflect real student misconceptions, not obviously wrong answers.
  • Avoid trick questions — the goal is to assess knowledge, not reading comprehension of tricky wording.
  • For formative quizzes, include explanations with each answer so students learn from the assessment.
  • If generating questions from a specific text or source, note which section each question references.
  • Offer to generate parallel versions (Form A and Form B) for academic integrity.
  • For timed assessments, err on the side of fewer, higher-quality questions over many shallow ones.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.