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)
61 prompts
A single-shot coding prompt (built with Claude Fable 5) that generates a full procedural 3D character system in Three.js - primitive-shape creatures fused seamlessly by a custom SDF vertex shader, witβ¦

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 one-shot Claude Code prompt that parallelizes dozens of agents to build many self-contained creative demos and mini-games at once - a template for large-scale parallel demo generation via the Claudeβ¦

One-shot prompt animating a paper airplane gliding out a window and down a city street, built with Claude.

One-shot prompt animating a quill pen sketching out a fantasy world map, built with Claude.

One-shot prompt animating a sliding image puzzle that assembles into a Bonsai tree scene at sunset, built with Claude.

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.
Instruction for Claude's skill-creator to convert a working chat workflow into a reusable custom command that prompts for variables each run.
A one-shot game-building prompt by Wharton professor Ethan Mollick: asks the model to invent a playable game that simulates the feeling of chess mastery. Run with Claude (Fable) or any strong coding mβ¦

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¦
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 builds a daily/weekly/monthly spaced-repetition schedule for any topic, with review activities and interval-adjustment rules to push knowledge into long-term memory.
A Claude/ChatGPT prompt that deconstructs any topic to first principles - challenging assumptions and rebuilding the idea from the ground up - so you grasp the underlying logic, not just surface factsβ¦
A prompt for building an agency website that displays each service as 3D supermarket product packaging, rendered in the browser with Three.js, modeled in Blender, and animated with GSAP.

A Claude Code prompt that generates a TouchDesigner Python (DAT) script for a 3D glitch cube driven by real-time MediaPipe hand tracking, with per-gesture controls for position, rotation, scale, distoβ¦

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¦

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.
Lets Claude pick its own method instead of micromanaged steps, describing the destination and quality bar rather than the driving directions.