Reading Comprehension Question Set Generator
Generates a balanced text-dependent question set across literal, inferential, and evaluative levels with answer rationales.
Prompt
ROLE: You are a reading specialist who writes text-dependent questions that drive close reading. CONTEXT: Text: [TEXT_OR_EXCERPT]. Grade/reading level: [LEVEL]. Genre: [GENRE]. Comprehension focus: [FOCUS — e.g., author's purpose, theme, argument structure]. Number of questions: [N]. TASK: Build a text-dependent question set. 1. Write questions distributed across three tiers: literal (in the text), inferential (between the lines), evaluative (beyond the text / author's craft). 2. Every question must require returning to the text — no questions answerable from general knowledge alone. 3. For each question, cite the specific lines/paragraph it draws from and provide a model answer with the evidence. 4. Sequence questions to build from surface meaning toward deeper analysis (a 'staircase' of comprehension). 5. Add one writing-extension prompt synthesizing the discussion. OUTPUT FORMAT: Numbered question set, each tagged [Literal/Inferential/Evaluative] with: Question | Text Anchor | Model Answer. End with the writing extension. CONSTRAINTS: No questions that ignore the text. Match vocabulary and syntax to [LEVEL]. Evaluative questions must still be grounded in textual evidence. Avoid yes/no questions unless followed by 'how do you know?'.
How to use this prompt
- 1
Copy the prompt above and paste it into ChatGPT, Claude, or Gemini — or open it in the visual Studio to edit each part on a canvas and run it with your own key.
- 2
Replace any bracketed placeholders with your specifics. The more concrete your context and constraints, the sharper the result — see the 5-part prompt structure.
- 3
Run it, then refine. Ask the model to critique and improve its own answer with self-critique prompting.
Techniques in this prompt
Assigns the model an expert persona so it adopts the right vocabulary, depth, and standards for the task.
Learn this techniqueForces explicit intermediate reasoning instead of jumping to a conclusion, which improves accuracy on hard tasks.
Learn this techniquePins the response to a defined structure so it drops straight into your workflow.
Learn this techniqueRecommended models
Build on this prompt
Open it in the visual Studio to wire it into a full workflow with your own API key — or learn the craft behind prompts like this.
More in Education & Curriculum
Backward-Design Unit Planner
Builds a complete Understanding by Design unit working backward from enduring understandings to assessments to daily lessons.
Bloom's Taxonomy Objective Ladder
Generates a vertically aligned set of learning objectives across all six Bloom's levels with matched verbs and quick checks.
Differentiated Lesson Tiering Engine
Adapts one core lesson into three readiness tiers plus accommodations for IEP, ELL, and gifted learners without lowering the standard.
Socratic Seminar Question Architect
Designs a layered Socratic seminar with opening, core, and closing questions plus facilitation moves to keep discussion student-led.