All, Creative, Marketing, Business, Productivity, Coding, Education, Personal, Research, Other
All, GPT Image 2 (800), ChatGPT (274), 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 (299), One-shot (225), System prompt (50), Workflow (38), Persona (6), Agent (3)
39 prompts
A meta-prompt that takes any prompt, extracts its intent, generates 20 standalone rephrasings, scores them and returns the top 5 with justifications. A self-contained prompt optimizer for ChatGPT or Cβ¦
A utility image prompt that restores and colorizes old, blurry, faded, or damaged photos with era-appropriate color while preserving the original look. Made with GPT Image 2 in ChatGPT.

A minimal delegation template for Claude Fable 5 that replaces step by step instructions with a clear goal, definition of done, and operating rules, so the model can act autonomously instead of askingβ¦
A prompt for handing Claude Fable 5 a task before bed so it can work autonomously overnight and report results in the morning.
A two-step Claude prompt that first builds a personal voice profile from your sent emails, then uses it to draft meeting-recap emails from Granola notes as a Gmail draft.

A five block master template, role, task, context, reasoning effort, format, for getting sharp, outcome driven results from GPT-5.6 or similar reasoning models.
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 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 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 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 argue the strongest possible case for the opposite of your position whenever a message ends in /STEELMAN.
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 drop the hedging and give the blunt version of its answer whenever a message ends in /PLAINLY.
A command code that makes the model name the single most important next action and why it beats the alternatives whenever a message ends in /NEXT.
A task framing template for agentic tools like ChatGPT Work or Claude Cowork that pulls context from connected apps and only interrupts you when it truly needs your judgment.
Example prompt for using a Model Context Protocol server so Claude reads real files or data directly instead of copy pasting between tabs.
A template for batching multiple related tasks, summarize, extract action items, draft email, into a single Claude prompt to save tokens and avoid reloading the context window.
Instruction for Claude's skill-creator to convert a working chat workflow into a reusable custom command that prompts for variables each run.
A structured 8-part prompt template for Claude Fable 5 covering purpose, task, context, effort, boundaries, verification, stop conditions, and output format.
A reusable set of global / custom instructions to paste once for a Claude agent (e.g. Cowork): it makes every session read your context files first, ask clarifying questions, show a plan before actingβ¦