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)
39 prompts
A framework for writing prompts that get good output on the first try, built from five parts most weak prompts are missing (goal, context, constraints, output format, examples), with a before/after exβ¦
A Seedance 2.0 video prompt that recreates an authentic ASMR-style camcorder packing vlog, with a full shot-by-shot storyboard and audio notes.

A two-stage GPT Image 2 storyboard plus Seedance 2.0 video prompt that turns a 12-panel sakuga-style anime sword-fight storyboard into a finished action sequence.

A verification prompt that has Claude Fable 5 spawn an independent fresh-context subagent to check its own work against a spec instead of self-grading.
A recurring analysis prompt for Claude Fable 5 that uses a persistent memory file so the model improves each time the task repeats.
A marketing campaign prompt for Claude Fable 5 that delegates each deliverable (landing page, emails, ads, calendar, hooks) to a parallel subagent from a single brief.
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 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.
A recurring scheduled task template for agentic tools such as ChatGPT Work or Claude Cowork to automate weekly competitive intelligence tracking.
A 4-step ChatGPT prompt chain, scope, map, tensions, synthesize, that forces staged research instead of a single flattened summary.
Instruction for Claude's skill-creator to convert a working chat workflow into a reusable custom command that prompts for variables each run.
A Claude / coding-agent prompt that runs a pre-launch security review of a vibe-coded app - security headers, OWASP vulnerabilities, credential/data leaks, Row Level Security, server-side validation, β¦

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 GPT Image 2 plus video workflow that adds hand-drawn 1970s Disney-style animal characters into a real photo without altering the subject.

A GPT Image 2 plus Seedance workflow that turns a character-sheet reference photo into a 30-second cinematic football boot commercial with a stadium goal-scoring sequence.

A Gemini vision workflow that turns any reference image into a reusable JSON style spec (colors, typography, composition, effects) you can inject to recreate the look.

A NotebookLM prompt that runs an adaptive easy-to-hard quiz from a single source, waiting for and grading your answers.
A short build recipe for vibe-coding a cinematic scroll-storytelling website with Claude, pairing two prompts with Three.js, GSAP ScrollTrigger, and Lenis.js.

Reusable starter prompts plus a planning-first workflow for vibe-coding a third-person 3D fantasy game with AI: scope the world and character in conversation before building.

A multi-tool workflow for creating a consistent animated character: design in Midjourney, stylize with GPT Image 2, storyboard, then generate the final video with Seedance 2.0.
