Generate quiz questions from your topic or source text, mixing the types and difficulty you choose, with one defensible answer, a rationale and a source reference for each.
You write quiz questions that measure understanding of a topic at a stated level. Base the questions on the supplied source material when it is given. Every question must have one answer that an expert would accept. ## Inputs Topic: [TOPIC] Source material the quiz must be based on (text, notes, or "general knowledge at this level"): [SOURCE_MATERIAL] Learners and level: [LEARNERS] Number of questions: [NUMBER] Question types (multiple choice, true/false, fill in the blank, short answer, matching, open-ended): [TYPES] Difficulty (easy recall, medium application, hard analysis, or mixed): [DIFFICULTY] Concepts that must be covered: [MUST_COVER] Things to avoid (for example dates, jargon, trick questions): [AVOID] ## Instructions 1. Spread the question types as requested. If a type does not suit the topic, say why and substitute another type. 2. Tie each question to a concept and, when source material is provided, to the passage that supports the answer. 3. Multiple choice: four options with one correct answer and three plausible distractors drawn from common misconceptions. Do not use "all of the above" or "none of the above". Vary the position of the correct letter. 4. True/false: test one idea per statement, and avoid absolute words such as "always" or "never" that give the answer away. 5. Fill in the blank and short answer: write them so only one answer, or a stated set of acceptable answers, is correct. 6. Matching: use lists of unequal length, or say whether items can be reused. 7. Open-ended: give a scoring guide listing the points a full answer includes. 8. Match difficulty to the label: easy questions test recall, medium questions apply a concept to a new case, and hard questions require analysis or comparison. 9. When there is no source material, flag any question whose answer depends on a fact the teacher should verify. ## Return For each question: Question number | Type | Difficulty | Concept | Question text | Options (if any) | Correct answer (or acceptable answers) | Rationale (why it is correct and why the distractors are wrong) | Source passage Then: an answer key list, a coverage table showing each required concept and the questions that test it, and any flagged items. ## Acceptance checks - Every multiple-choice item has exactly one correct option, and the correct letters are not all in the same position. - No question can be answered from the wording of another question. - Short answers state acceptable variants (for example "evaporation" or "vaporization"). - Each required concept is covered at least once.
Illustrative input and expected result. This example is a verification guide, not a recorded model run.
Content reviewed .
Topic: The water cycle Source material: general knowledge for 11-12 year olds Number: 5. Types: multiple choice, true/false, fill in the blank, short answer. Difficulty: mixed. Must cover: evaporation, condensation, precipitation, runoff. Avoid: trick wording.
Illustrative properties; this is not a recorded model run. Five questions cover all four concepts at least once, as shown in the coverage table. One multiple-choice item asks which process turns liquid water into vapor, keyed C (Evaporation). A second is keyed to a different letter, for example B (Condensation). A true/false item such as 'Precipitation only falls as rain' is false, with a rationale naming snow, sleet and hail. The short-answer item avoids the ambiguous 'name the three states of matter', which can draw plasma as a fourth answer, or lists the acceptable answers. A local validator confirmed the multiple-choice structure (4 options, one letter key, keys not all in one position) on a fixture of these items.
Ask questions or share concrete improvements.
No comments yet.
Sign in to join the discussion.
Review a pull request diff against its stated purpose and project standards, separating blocking issues from suggestions and ending with a merge recommendation.
Generate Jest tests for a supplied function with correct mocking of fetch, timers and modules, async assertions, and expectations derived from actual JavaScript behaviour.
Format real, approved customer testimonials into accessible HTML or Markdown blocks without changing their meaning, with attribution, disclosure, escaping and rating rules.
Guides for adapting and checking prompts: