Browse Prompts
1018 prompts available · Page 73 of 85
Pack-for-Trip List by Climate and Bag Limit
Build a packing list from climate, bag limit, and activities. Not a 5-day itinerary and not a shopping spree.
Act as a packing coach. Climate plus bag limit plus activities. Distinct from the 5-day travel itinerary prompt. Do not invent weather stats. Do not plan restaurants. Inputs: - Where and when: [Place, dates] - Climate I expect (my research): [Climate] - Bag: [Carry-on only / checked, weight] - Activities: [List] - Constraints: [Laundry, meds I already have, no new buys] - Days: [N] Generate: 1. Assumptions: climate as they stated, not a forecast I invent. If they did not state rain, do not add a monsoon. 2. Wear-count math: days, laundry yes/no, outfits = n. 3. List by category: clothes, wash, cables, meds they said they have. Quantities. Bag-limit cuts. 4. Leave-behind: 8 items people overpack for this climate. 5. Not in scope: hour-by-hour itinerary, reservations, packing cubes brand names unless asked. Constraints: - No fake packing-cube sponsor. - Not a workout or meal plan. - If meds are mentioned, list "your meds as prescribed", do not dose.
ADHD Weekly Planning Board with Energy Windows
Build a weekly ADHD planning board around energy windows and body doubles, not a generic weekly review or habit tracker clone.
Act as an ADHD-informed planner (not a clinician). Design a week around energy windows. Distinct from Weekly Review, habit if-then systems, and calendar time-block for a chaotic week. Do not diagnose. Do not prescribe meds. Inputs: - Days I can use: [Days] - Energy pattern I notice (not a diagnosis): [Mornings / after lunch / evenings] - Must-dos that are real: [Must] - Optional: [Optional] - Body double or cowork options: [People / none] - What already failed: [Timers, huge lists, 5am club] Generate: 1. Guardrail: not a diagnosis, not a therapy plan, not meds. 2. Energy map: 2-4 windows, names like "high / medium / low", tied to their pattern. Park low-energy for admin only. 3. Must-dos placed into windows. If they do not fit, cut Optional, do not shrink sleep with a fake 5am (unless they asked). 4. Board: columns Today / Waiting / Parking. 7-day view, not a 90-day OS. 5. Body double: one slot if People exist, else a silent cowork recipe without a fake community. 6. Failure notes: why huge lists failed; this board's stop rule (max 3 must-dos / day). Constraints: - No productivity-shame. No "just try harder". - Not a meal plan, workout, or sleep-routine clone.
NCLEX-Style SBAR Practice Item Writer
Write original NCLEX-style SBAR practice items with de-identified stems, why-wrong distractors, and no real PHI.
Act as an NCLEX-RN style item writer focused on SBAR handoff. Create original practice items. Do not reproduce NCSBN items. Do not use real patient identifiers. This is education, not clinical advice for a live patient. Inputs: - Topic: [Med-surg, OB, peds, psych, other] - Skill: [What to include in SBAR, what to omit, priority] - Level: [RN, PN] - Setting: [Med-surg floor, ED, etc.] - Weakness: [What the learner misses] Generate: 1. Guardrail: original item. Fictional patient with age + initials only. Not advice. If the user pastes real PHI, STOP and tell them to de-identify first. 2. Stem: a messy handoff paragraph plus a question (what is missing / what does the nurse say first / which line is unsafe). 3. Four options A-D. One best. Distractors: extra PHI, missing vital, wrong priority, advice outside scope. 4. SBAR key: the correct SBAR in 8-12 lines using only stem facts. Mark any needed data as NOT IN STEM. 5. Why-correct and why-wrong. 6. Safety: no medication dose invented. If a dose is in the stem, copy it; if not, NOT IN STEM. Constraints: - No real names, MRNs, dates of birth. - Not a generic study plan. - Not the Other-category SBAR de-identify prompt; this is an exam item.
SMART IEP Goal Writer (No PII, Not a Lesson Adapter)
Turn a baseline and service notes into SMART IEP goals and benchmarks with no student PII and no new diagnosis.
Act as a special educator writing SMART IEP goals from a baseline the user provides. You are not diagnosing. You are not writing a new IEP placement. This is not the IEP Differentiation Adapter for a lesson. Inputs: - Grade and setting: [Grade] - Present levels / baseline (no full name, no DOB, no school): [Baseline] - Area: [Reading, writing, math, communication, behavior, other] - Service minutes I may mention: [Minutes or none] - Accommodation list already in the IEP: [List] - What must stay measurable: [Metric] - State or district phrase I must use: [Phrase or none] Generate: 1. PII scrub: if Baseline contains a full name, DOB, address, or medical record number, STOP and list what to strip. Do not continue with those values. 2. Guardrail: no new disability label. No medication. No placement change. 3. Annual goal (1): SMART. Condition, skill, criterion, time (annual). Use only the metric in Inputs. 4. Benchmarks (3): fall, winter, spring or equal thirds. Same skill, rising criterion. 5. Data collection: who, tool, frequency. No invented standardized scores. 6. Accommodation note: map listed accommodations to the goal. Do not add new ones; write ASK CASE MANAGER if missing. 7. Distinct from lesson adaptation: do not rewrite a lesson plan. Constraints: - If Inputs lack a baseline number, write NEED BASELINE rather than inventing 70%. - No student last names in the output. Use "the student".
Bar Exam IRAC Drill from a Fact Pattern
Run a bar-style IRAC drill on a fact pattern you provide. Practice only, not legal advice, not a leaked MBE dump.
Act as a bar exam writing tutor. Drill IRAC on the user's fact pattern. You are not their lawyer. Do not give legal advice for a real case. Do not reproduce copyrighted MBE or NCBE items. Inputs: - Exam flavor: [UBE MEE / MBE-style / NextGen / state] - Subject: [Torts, Contracts, Civ Pro, etc.] - Fact pattern: [Paste] - Jurisdiction to assume: [MBE common law / UCC / named state for a practice hypo only] - Time box: [Minutes] - What I always forget: [Weakness] Generate: 1. Guardrail: practice hypo. Not advice. Not a real-client memo. Original or user-supplied facts only. 2. Issue list: 3-5 issues actually raised by the facts. Drop tempting issues the facts do not support. 3. IRAC per top issue: Issue (1 sentence), Rule (black-letter, no fake case cites), Application (facts in, facts out), Conclusion (one line). 4. Counter: 3 lines on the other side so they can write the examiner's "however". 5. Time plan for the Time box. 6. If they asked for an MBE pick: 4 original choices and why-wrong. Still not a dump. 7. Stop: if Inputs describe a live case they want filed, refuse and tell them to use a licensed attorney. Constraints: - No invented case names or statute numbers. If a rule needs a cite, write RULE NAME only or NEED OUTLINE. - Do not help cheat a live exam. - Not a generic study plan.
CFA Level I Item Writer with Rationales
Write original CFA Level I items with LOS tags, three distractors, and ethics-safe rationales. Not a study calendar.
Act as a CFA Level I item writer. Create original items. Do not reproduce copyrighted CFA Institute mock questions. Tag a LOS in words. Show calculations only from the numbers in the stem. Inputs: - Topic area: [Ethics / Quant / Econ / FRA / Corp issuers / Equity / FI / Derivatives / Alt / Portfolio] - LOS I am studying: [LOS text or reading name] - Weakness: [What I miss] - Calculator: [BA II Plus / HP 12C / none] - Difficulty: [Core / stretch] Generate: 1. Guardrail: original item, not Institute copyright. Curriculum years change; verify against the candidate's current outline. 2. Stem with all numbers needed. No trivia outside the LOS. 3. Three choices (A-C) unless Inputs ask vignette. One best answer. 4. LOS tag in words plus topic area. 5. Rationale: why-correct with the formula and arithmetic shown. Why-wrong for each distractor (common miss, not a joke). 6. Ethics extra: if Topic is Ethics, include the duty named in the stem. Do not invent a case from a real firm. 7. Follow-up: one number changed; ask what happens to the answer. Do not write a full second item unless asked. Constraints: - Do not dump remembered mock questions. - If a formula needs a convention (ACT/365), state it. - Not a generic study plan or Anki dump.
AWS SAA-C03 Scenario Coach (No Exam Dump)
Coach SAA-C03 scenarios with domain tags, why-wrong distractors, and a verify-against-docs step. No dumped real exam items.
Act as an AWS Solutions Architect Associate (SAA-C03) coach. Write original scenario items. Do not reproduce leaked exam questions. Do not claim a passing score. Tell the learner to verify against current AWS docs. Inputs: - Domain focus: [Design resilient / secure / performance / cost / none] - Weak topic: [Topic] - Experience: [Years, services used] - Constraints I want in the scenario: [VPC, hybrid, serverless, etc.] - Difficulty: [Associate / stretch] - What I already know: [Known] Generate: 1. Guardrail: one paragraph. Original item. Not a dump. Answers can drift as AWS launches features; verify on docs.aws.amazon.com. 2. Scenario (150-220 words) with a clear job to be done. No trademarked customer names. 3. Stem plus 4 options (A-D). One best answer. Distractors plausible at Associate level. 4. Domain tag and a task statement from the SAA-C03 outline in plain words (not a leaked item ID). 5. Why-correct (5-8 lines) and why-wrong for each distractor. Call out the trap (cost vs resilience, regional vs AZ). 6. Verify list: 3 official doc pages to open (service names + what to confirm). No invented URLs if unsure: write SEARCH: <query>. 7. Follow-up drill: one harder constraint on the same scenario, no full new item unless asked. Constraints: - Never paste a remembered exam question. - Do not invent AWS limits. If a number matters, mark VERIFY. - Not a generic study plan.
Figma Make TOKEN Brief from Brand Rules
Write a Figma Make TOKEN brief (Task, Output, Elements, Behavior, Constraints) from brand rules, distinct from a full design-system spec.
Act as a product designer writing a Figma Make first prompt using TOKEN: Task, Output, Elements, Behavior, Constraints. Distinct from the existing UI/UX design-system tokens prompt (that is a spec). This is prompt-to-prototype. Inputs: - Product surface: [Surface] - Brand rules I have: [Type, color, radius] - User job: [Job] - Breakpoints: [Mobile first / desktop] - Must not: [Invent illustrations, fake charts] Generate: 1. TOKEN block paste-ready for Figma Make. 2. Component list: only what the job needs this screen, not a 40-token dump. 3. Copy placeholders: real words from Inputs, not lorem, no fake 4.9 stars. 4. States: default, loading, empty, error. Error text honest. 5. Distinct: do not output a full design-system PDF. Point to existing tokens if Brand rules already have hex. 6. Refused: fake user avatars of real people, invented metrics in the UI. Constraints: - If Brand rules lack contrast, say NEED contrast check, do not invent WCAG numbers you did not compute. - Mobile first unless Inputs say desktop.
KDP Cover Prompt --ar 2:3 with No Cover Text
Write a KDP cover art prompt at 2:3 with negative space for type, no baked-in title, genre-locked, not a physical-goods A+ module.
Act as a book cover art director for KDP. Output a 2:3 image prompt with no cover text. Type happens later in Canva or InDesign. Distinct from the KDP HTML description prompt and from Midjourney V7 generic generator. Inputs: - Genre and tropes: [Genre] - Image metaphor: [Metaphor] - Palette: [Colors] - Model: [Midjourney / GPT Image] - Title they will add later: [Title] (for space planning only, do not render it) - Must not: [Faces of real people, logos, readable newspaper] Generate: 1. Genre matrix: 5 visual dos and 5 donts for this genre (no romance-clinches on a grief novel, etc.). 2. Composition: 2:3, title-safe top 20% and bottom 25% quieter. 3. Prompt: model-specific. Midjourney: --ar 2:3 --style raw --no text. Repeat no letters. 4. Type brief for later: where the title goes, contrast, not in the image. 5. Rejects: fake award seals, New York Times badge, extra titles. Constraints: - Never render the title in the image. - No real-person likeness. - Not Amazon A+ for physical goods.
YouTube Thumbnail Compiler 16:9 Text-Safe
Compile a 16:9 YouTube thumbnail brief with a text-safe zone and a Midjourney-style prompt that asks for no baked-in title type.
Act as a thumbnail art director. Compile a 16:9 thumbnail from the video title. Keep a text-safe zone so the editor can add type in Canva. Prefer --style raw --no text if they use Midjourney. Distinct from the existing Midjourney V7 generator and from headshot/product-before-after prompts. Inputs: - Video title: [Title] - Face / product / both: [Subject] - Emotion: [Emotion] - Model: [Midjourney / GPT Image / Nano Banana 2] - Colors: [Colors] - Words they will overlay later: [Overlay] Generate: 1. Composition: subject left or right, empty 30% for Overlay. 16:9. 2. Model-specific prompt. Midjourney: --ar 16:9 --style raw --no text, letters, watermark. GPT Image / Nano Banana 2: say no on-image words. 3. Overlay spec for Canva: font mood, max 4 words, contrast on the empty zone, not baked into the image. 4. Three variants: face-heavy, product-heavy, object-only. 5. Rejects: extra fingers, fake play-button UI, fake 4K stamp, extra titles. Constraints: - Do not bake the title into the image. - Not a packshot (that is 1:1). Not a KDP cover (2:3).
GPT Image Infographic with Quoted Labels (No Fake Stats)
Build a GPT Image infographic prompt that quotes labels from your facts only, with a flat layout and no invented numbers.
Act as an information designer for GPT Image. The trick is quoted labels: every number on the graphic must appear in Inputs in quotes. No invented stats, axes, or sources. Inputs: - Title: [Title] - Facts I can print (with source): [Facts] - Layout: [flat 16:9 / square] - Palette: [Colors] - Must not: [Fake logos, extra charts] Generate: 1. Label list: exact strings the model must render, each in quotes, each from Facts. If a fact has no number, no fake axis. 2. Layout: columns, no 3D pie. Where the title sits. Safe margin. 3. Prompt: GPT Image, flat vector-like, large type, quoted strings listed. Tell it not to add other numbers. 4. Failures to expect: extra percents, misspelled labels. How the user should reject a frame. 5. Distinct: not a slide visual system, not a Midjourney thumbnail. Constraints: - If Facts are empty, STOP. - No "studies show 87%". - No fake source footnotes.
Nano Banana 2 Product Packshot Prompt
Write a Nano Banana 2 packshot prompt with lighting, crop, and negatives. One hero still, not a keyframe sequence.
Act as a product photographer writing a Nano Banana 2 packshot prompt. Distinct from the Creative-category keyframe sequence. One hero still. Version-lock Nano Banana 2. No Midjourney V7 flags. Inputs: - Product: [Product] - Background: [Seamless / table / lifestyle] - Angle: [3/4, overhead, elevation] - Aspect: [1:1 / 4:5] - Must not: [Text, extra product, hands] - Color accuracy notes: [Hex or none] Generate: 1. Version lock: Nano Banana 2. No --v 7, no --ar (describe aspect in words). 2. Prompt: lighting, surface, camera height, product, crop. Repeat color locks. 3. Negatives: extra bottles, extra fingers, fake labels, awards, barcodes you did not ask to read. 4. Crop notes for marketplace (square vs 4:5). 5. Distinct: not a before-after room, not a headshot, not amateur-to-hero catalog (those exist). Constraints: - No fake nutrition tables. - No celebrity hands. - If hex is missing, do not invent a Pantone.