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.
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)
143 prompts
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 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.
Instruction for Claude's skill-creator to convert a working chat workflow into a reusable custom command that prompts for variables each run.
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.
Example prompt for using a Model Context Protocol server so Claude reads real files or data directly instead of copy pasting between tabs.
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¦
Has ChatGPT strip a plan down using the 80/20 principle, flagging what to remove, reduce, and keep, useful when a plan feels bloated, expensive, slow or too complicated.
A prompt framing technique that adds a real audience, a deadline, and a consequence to force ChatGPT or Claude to produce a careful, audited answer instead of generic filler.
An 11-block scaffold for writing high-leverage prompts to Claude agents, covering task framing, context files, effort, scope control, delegation, evidence, memory, and reporting. Use it as a reusable β¦

Forces Claude to organize multi-part work by naming each required output and its order, so answers arrive structured and ready to use.
Lets Claude pick its own method instead of micromanaged steps, describing the destination and quality bar rather than the driving directions.
A compact, direct prompt formula that states goal, audience, tone and output format up front to avoid wasting tokens, adaptable to any writing task with Claude.
Compresses a bloated Claude chat into a clean handoff so a fresh conversation starts with only the context that still matters, avoiding context rot.
Forces Claude to clarify the task before answering by asking the highest-impact questions first, reducing bad first drafts.
Asks Claude to generate five genuinely different approaches with tradeoffs before recommending one, preventing it from locking onto the first plausible path.
Pushes back against Claude's tendency to agree, asking it to test the premise as a hypothesis and state disagreement plainly.
Turns Claude into its own reviewer by asking it to audit unsupported claims, weak assumptions, hallucinations and missing edge cases before you trust the answer.
A ChatGPT prompt that turns bullet points into prose in a chosen tone and author's style.