All, Creative, Marketing, Business, Productivity, Coding, Education, Personal, Research, Other
All, GPT Image 2 (800), ChatGPT (298), Model-agnostic (247), Seedance 2.0 (242), Nano Banana Pro (226), Gemini Nano Banana (210), Gemini Nano Banana Pro (182), Grok Imagine (83), Claude (61), Gemini (44), Midjourney v7 (29), Nano Banana 2 (27), Veo 3 (25), Gemini Nano Banana 2 (24), GPT Image 1.5 (24), Midjourney (21), NotebookLM (20), Midjourney v8.1 (14), ChatGPT / Gemini (12), Kling AI 3.0 Turbo (12)
All, cinematic (198), photorealistic (115), editorial (106), portrait (96), commercial (39), fashion (38), minimalist (31), studio (31), luxury (30), product-photography (29), lifestyle (28), golden-hour (26), surreal (25), miniature (23), infographic (21), 3d-render (20), poster (20), candid (19), monochrome (19), macro (18)
All, Creative generation (2567), Template (321), One-shot (226), System prompt (50), Workflow (39), Persona (6), Agent (3)
117 prompts
One-shot prompt recreating the Star Wars Duel of the Fates lightsaber battle in 3D. Posted as a same-prompt model comparison.

One-shot prompt for a detailed medieval castle siege with a battering ram, siege tower, and archers. Posted as a which-model-did-it-better comparison.

A command code that makes ChatGPT or Claude point out the assumptions and gaps you have not stated out loud whenever a message ends in /HOLES.
A command code that makes the model drop the hedging and give the blunt version of its answer whenever a message ends in /PLAINLY.
A command code that makes the model state its honest confidence level, high, medium or low, and what would change it, whenever a message ends in /ODDS.
A command code that makes the model cut the fluff and explain why something actually matters whenever a message ends in /SOWHAT.
A command code that makes the model predict the most likely way a plan goes wrong before you commit to it, whenever a message ends in /FAILHOW.
A command code that makes the model argue the strongest possible case for the opposite of your position whenever a message ends in /STEELMAN.
A command code you paste once at the start of a chat so that any message ending in /ATTACK gets argued against as hard as the model honestly can, instead of getting agreement.
A one-shot prompt that builds a full 3D, explorable recreation of Hogwarts you can fly through on a broom. Posted as a which-model-did-it-better comparison.

A one-line coding prompt for an AI agent (Claude, etc.) to generate a polished Crossy Roadβstyle game as a single self-contained HTML file using three.js. Great as a model/vibe-coding benchmark.

A Claude/ChatGPT prompt that runs the Feynman technique as a loop: simple explanation, you teach it back, it finds gaps and re-teaches until you've mastered it.
A Claude/ChatGPT prompt that surfaces the 5 highest-leverage resources to learn any topic fast, with rationale and audience fit for each.
A Claude/ChatGPT prompt that maps any topic into a 5-level progression from beginner to advanced, with milestones and exercises per level.
A Claude/ChatGPT prompt that drills you with progressively harder questions on a topic, grading answers and re-teaching only your gaps.
A Claude/ChatGPT prompt that condenses any topic into a one-page, review-optimized cheat sheet with bullets, diagrams and examples.
A Claude/ChatGPT prompt that builds a focused 20-hour, 10-session learning plan for any topic using the 80/20 principle, with resources and reviews.
A ChatGPT prompt that has the model role-play as a business idol answering your questions.
Business strategy ChatGPT prompt inspired by the Limitless theme: The Coma: Preparing for Key Personnel Loss.
Business strategy ChatGPT prompt inspired by the Limitless theme: The Brokerage Firm: Breaking into New Industries.