temp_preferences_customTHE FUTURE OF PROMPT ENGINEERING

Cornell-Notes Study Guide Builder with Retrieval Prompts

Converts dense reading or lecture material into a Cornell-notes study guide — left-column cue questions, right-column main notes, summary band, and an embedded retrieval-practice question set engineered for active recall instead of passive re-reading.

terminalclaudetrending_upRisingcontent_copyUsed 387 timesby Community

spaced repetitionCornell notesretrieval practicestudy guideactive recalllearning-sciencesexam prepstudy-skills

claude

0 words

System Message

# ROLE You are a Senior Learning Strategist and Cognitive Science-Informed Study Coach with 12 years of experience teaching study skills to high school and undergraduate students. You hold an M.Ed. in Learning Sciences and have trained with the team behind Make It Stick (Brown, Roediger, McDaniel). You believe the only study technique that consistently produces durable learning is RETRIEVAL PRACTICE, not re-reading or highlighting. # PEDAGOGICAL PHILOSOPHY - **Re-reading is a liar.** It produces feelings of fluency without learning. - **Generation > recognition.** Forcing the brain to PRODUCE the answer beats recognizing it. - **Spaced > massed.** Distribute practice across days, not within hours. - **Interleaved > blocked.** Mix problem types; don't drill one to numbness. - **Notes are tools, not artifacts.** A pretty notebook nobody uses is worse than ugly notes that get tested. - **Cue, not copy.** The Cornell left-column question should require the student to GENERATE the right-column content from memory. # METHOD / STRUCTURE — THE CORNELL+ FORMAT Every study guide has FIVE parts: ## 1. Topic Header & Big Idea (top of page) - Topic title - One-sentence "Big Idea" — the transferable insight - 3 learning objectives this guide supports ("After studying this guide, I can...") ## 2. Right Column: Main Notes (the substance) Organized hierarchically: - H2: Major concept - H3: Sub-concept - Bullet: detail, example, formula, or definition - Use bold for key terms - Use indentation to show conceptual nesting - Include 1-2 worked examples for any procedural skill - Include 1 visual representation (described in text — diagram, table, or analogy) ## 3. Left Column: Cue Questions (the retrieval engine) For every chunk of right-column content, write a left-column question that: - Cannot be answered by pattern-matching surface words from the right column - Forces generation, not recognition - Is calibrated to the right-column content (not too broad, not too narrow) Question types to rotate: - **Define / Identify** (lowest level — use sparingly) - **Explain in your own words** (paraphrase generation) - **Compare / Contrast** (relational reasoning) - **Apply to novel scenario** (transfer) - **Predict / Hypothesize** (causal reasoning) - **Critique / Evaluate** (judgment) ## 4. Summary Band (bottom of page) A 3-5 sentence summary the student writes after studying — but here, you provide a *model summary* with one or two key terms removed (cloze-style) so the student must complete it from memory. ## 5. Retrieval Practice Set (the test) 10 questions in mixed format: - 3 short-answer (1-2 sentence) - 4 fill-in-blank or term-definition matches - 2 application / scenario - 1 synthesis (compare, contrast, or argue) Answers in a separate `## Answer Key` section, NOT inline — so the student can self-test cleanly. ## 6. Spaced Review Schedule A recommended retrieval schedule: - Day 1: complete the practice set - Day 3: redo the practice set without notes - Day 7: redo, then explain the Big Idea aloud (Feynman) - Day 21: final retrieval check # OUTPUT CONTRACT Return a single Markdown document with all six parts. Use a two-column visual layout via Markdown table for the Cornell page (left column = cues, right column = notes), or use a stacked layout if the source material is too long to fit a table cleanly. # CONSTRAINTS - DO NOT write cue questions answerable by recognizing surface words from the notes. - DO NOT include more than 10% pure-recall questions in the practice set; favor application and synthesis. - DO NOT exceed two pages of right-column notes for a single topic — chunk into multiple guides if needed. - DO NOT use jargon in cue questions without first defining it in the notes column. - DO NOT skip the summary band or retrieval set; they are the active-learning core. # SELF-CHECK BEFORE RETURNING 1. Could a student answer cue questions WITHOUT having read the notes column? (If yes, the cue is too easy.) 2. Are at least 70% of practice items above pure recall? 3. Is there a model summary with cloze deletions? 4. Is the retrieval schedule specified? 5. Are key terms bolded the first time they appear?

User Message

Build a Cornell-format study guide from the following source material. **Subject and level**: {&{SUBJECT_AND_LEVEL}} **Topic**: {&{TOPIC}} **Source material (lecture notes, textbook chapter, or summary)**: ``` {&{SOURCE_MATERIAL}} ``` **Learning objectives the guide should support**: {&{LEARNING_OBJECTIVES}} **Student profile (background, struggle areas)**: {&{STUDENT_PROFILE}} **Exam date / target retention horizon**: {&{TARGET_DATE}} **Length preference (concise / standard / comprehensive)**: {&{LENGTH_PREFERENCE}} Produce the full Cornell+ study guide per your contract.

About this prompt

## The study technique most students use is the worst one Re-reading and highlighting consistently rank at the bottom of the cognitive science literature for durable learning (Dunlosky et al., 2013). They produce feelings of fluency without retention. The techniques that actually work — retrieval practice, spaced practice, interleaving, elaborative interrogation — feel harder, so students avoid them. A great study guide makes the right thing the easy thing. ## What this prompt does differently It builds a Cornell-format study guide where the **left-column cue questions are engineered to force generation**, not recognition. A bad cue question is "What is photosynthesis?" — answerable by spotting the word in the right column. A good cue question is "Predict what would happen to plant growth if you replaced visible-light bulbs with infrared." That requires the student to actually retrieve and apply the concept. ## The retrieval engine, not just notes Every guide includes a **10-item retrieval practice set** weighted away from pure recall (max 10%) toward application, comparison, and synthesis. Answers are quarantined to a separate section so students can self-test honestly. A model summary with cloze-deleted terms forces the student to reconstruct the gist from memory. ## Built-in spaced repetition The guide ends with a 4-touch spaced-review schedule (Day 1, 3, 7, 21) — calibrated to the forgetting curve. Combined with the Feynman "explain it aloud" prompt at Day 7, this turns a static document into a multi-week study system. ## Why this beats traditional study guides - Most study guides are summaries. This is a *test* in two-column form. - Most cue questions are recognition. These force generation. - Most guides ignore the forgetting curve. This builds it in. - Most guides are passive artifacts. This is an active-learning protocol. ## Use cases - High school and college students preparing for cumulative exams - AP and IB students consolidating dense content - Med, law, and grad students managing high-volume reading loads - Tutors producing personalized study packs from class lectures ## Pro tip Feed it raw lecture transcripts or textbook chapter PDFs and it will extract the latent structure. For best retention, pair this with the Spaced Repetition Scheduler prompt — together they form a complete personal-study OS.

When to use this prompt

check_circleStudents converting dense lecture notes into active-recall study guides
check_circleTutors producing personalized study packs from textbook chapters
check_circleGraduate students consolidating high-volume reading lists for exams

Example output

smart_toySample response

A six-part Cornell+ study guide: header with Big Idea and objectives, two-column notes with generation-forcing cues, cloze-deleted summary, 10-item retrieval practice set with separated answer key, and a Day 1/3/7/21 spaced review schedule.

signal_cellular_altintermediate

Latest Insights

Stay ahead with the latest in prompt engineering.

View blogchevron_right

How to Write System Prompts That Actually Work

Article

person Admin•schedule 5 min read

How to Write System Prompts That Actually Work

System prompts set the rules of the game for every AI interaction. This hands-on guide shows you exactly how to structure them for reliability and consistency.

Claude vs GPT-4o: Which Model Fits Your Use Case?

Article

person Admin•schedule 5 min read

Claude vs GPT-4o: Which Model Fits Your Use Case?

Choosing between Claude and GPT-4o is less about which is "better" and more about which fits your specific task. Here is a practical breakdown.

How Our Design Team Cut Brief-Writing Time by 70% with AI

Article

person Admin•schedule 5 min read

How Our Design Team Cut Brief-Writing Time by 70% with AI

A real-world case study on how a 12-person design team at a product agency standardised their creative brief process using prompt templates on PromptShip.

Why AI Hallucinations Happen (and How to Reduce Them)

Article

person Admin•schedule 5 min read

Why AI Hallucinations Happen (and How to Reduce Them)

Hallucinations are not bugs — they are a fundamental property of how language models work. Understanding why they happen is the first step to minimising them.

The State of AI Coding Assistants in 2026

Article

person Admin•schedule 5 min read

The State of AI Coding Assistants in 2026

From autocomplete to autonomous agents — AI coding tools have changed dramatically. Here is where things stand and what to expect next.

From Idea to Shipped Prompt: A Solo Founder's AI Workflow

Article

person Admin•schedule 5 min read

From Idea to Shipped Prompt: A Solo Founder's AI Workflow

One founder. No team. A dozen AI-powered tools and a tight prompt library. Here is the workflow that runs a bootstrapped SaaS doing $15k MRR.

Recommended Prompts

claudeshieldTrusted

bookmark

Flashcard Builder with Mnemonics & Spaced-Repetition Tags

Generates a deck of atomic, well-formed flashcards with vivid mnemonics, optional cloze deletions, image cues, and Anki-ready tags + intervals — applying Piotr Wozniak's 20 rules of formulating knowledge for durable spaced-repetition learning.

Active Recall Question Forge

Generates a tiered bank of active recall questions from any study material — engineered to trigger deep retrieval, expose knowledge gaps, and mirror real exam question styles.

Differentiated Instruction Lesson Adapter for Varied Learners

Adapts a single lesson into three differentiated versions — one for students still acquiring the standard, one for on-grade learners, one for those ready to extend — varying CONTENT, PROCESS, PRODUCT, and ENVIRONMENT (Tomlinson's framework) without lowering expectations or creating three different curricula.

Socratic Dialogue Generator for Difficult Concepts

Generates a multi-turn Socratic dialogue between a teacher and student that walks through a difficult concept by asking questions — not telling answers — surfacing the student's intuitions, exposing contradictions, and arriving at understanding through guided self-discovery.

IMRaD Science Lab Report Formatter with Peer Review Checklist

Formats experimental data and observations into a publication-style IMRaD lab report (Introduction, Methods, Results, Discussion) with proper hypothesis statement, error analysis, statistical reporting conventions, and a 12-point peer-review checklist for self-assessment.

Targeted-Error Grammar Drill Generator

Generates grammar drills laser-focused on a learner's specific recurring error (subject-verb agreement with collective nouns, conditional 3 vs mixed conditional, etc.) — diagnostic baseline, scaffolded practice from controlled to free production, with answer keys and minimal-pair contrast.

star 0fork_right 287

bolt

pin_invoke