Prompt Encyclopedia
From Wikiprompt, the free prompt encyclopedia
Wikiprompt is a collaborative encyclopedia of AI prompts, featuring curated templates for various AI tools including ChatGPT, Midjourney, DALL-E, Claude, and more. It contains 3213 prompts by 225 community members.
Filters (2)▾
View
Category
All, Creative, Marketing, Business, Productivity, Coding, Education, Personal, Research, Other
Source
Uploaded
Model
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)
Sort
Style
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)
Prompt type
All, Creative generation (2567), Template (321), One-shot (226), System prompt (50), Workflow (39), Persona (6), Agent (3)
Quality
17 prompts
Research ★The Crucible: extract usable insight from contested or mystical sourcesA rigorous system prompt that reads a contested, foreign, mystical, ideological or overheated source and separates the real phenomenon and usable kernel from the metaphysical excess (the 'tailings'), with an assay, failure modes and per-session controls. For deep reading and study with Claude or ChatGPT.ProductivityPrompt Gauntlet: generate and rank 20 variations of any promptA 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 Claude.CodingScope boundary template to stop AI agents from reward hackingA guardrail template that scopes an autonomous coding agent's permissions and forces honest status reporting, reducing reward hacking behavior.Productivity/FAILHOW code: make ChatGPT predict how your plan goes wrong firstA 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.Productivity/NEXT code: make ChatGPT name the single most important next stepA 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.Productivity/PLAINLY code: make ChatGPT drop the hedging and be bluntA command code that makes the model drop the hedging and give the blunt version of its answer whenever a message ends in /PLAINLY.Productivity/STEELMAN code: make ChatGPT argue the opposite of your positionA command code that makes the model argue the strongest possible case for the opposite of your position whenever a message ends in /STEELMAN.Productivity/SOWHAT code: make ChatGPT cut the fluff and say why it mattersA command code that makes the model cut the fluff and explain why something actually matters whenever a message ends in /SOWHAT.Productivity/ATTACK code: make ChatGPT argue against what you just saidA 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.Productivity/HOLES code: make ChatGPT surface your unspoken assumptionsA 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.Productivity/ODDS code: make ChatGPT give an honest confidence levelA 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.
Luxury editorial campaign poster system prompt (PRIME Hydration)ProductivityClaude global instructions to set once (Cowork / custom instructions)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 acting, and never delete anything without approval - so your day-to-day prompts can stay short.ProductivityTurn ChatGPT into a Prompt GeneratorA ChatGPT prompt that turns the model into a prompt generator, producing 10 prompts for any task.ResearchNotebookLM: Expert interview mode (answer only from sources)A NotebookLM prompt that turns your notebook into a source-grounded expert that answers questions only from the uploaded materials.
Anti-AI writing-style rules for Claude / ChatGPT
Mentor experto para aprender cualquier habilidad desde cero
Luxury editorial campaign poster system prompt (PRIME Hydration)ProductivityClaude global instructions to set once (Cowork / custom instructions)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 acting, and never delete anything without approval - so your day-to-day prompts can stay short.ProductivityTurn ChatGPT into a Prompt GeneratorA ChatGPT prompt that turns the model into a prompt generator, producing 10 prompts for any task.ResearchNotebookLM: Expert interview mode (answer only from sources)A NotebookLM prompt that turns your notebook into a source-grounded expert that answers questions only from the uploaded materials.Anti-AI writing-style rules for Claude / ChatGPTMentor experto para aprender cualquier habilidad desde cero