Search prompts, categories, platforms and repositories
The AI prompt library
This library holds 520 original prompts for 25 AI platforms, grouped into 20 job-based categories. Use the filters to narrow by tool, category and difficulty, then open any prompt to fill in its variables and copy a version tuned for the model you use. Every page includes a worked example and the mistakes to avoid.
A video prompt for seamless fabric transition. It gives Runway and Pika a clear role, explicit constraints and a defined output, so the first answer is closer to usable. Fill in the variables, run it once, then use the verification notes on this page to review the result.
Cozy reading nook loop with a prompt built for Veo and Runway. It supplies context, constraints and an output contract, then asks the model to surface assumptions and gaps. Copy it, fill the details and treat the result as a structured draft, not a final answer.
This copy-ready video prompt helps you minimal kinetic typography background with fewer blank-page decisions. Paste it into Runway and Pika, fill the details, and you get a structured first draft you can edit. It is written for repeatable results and tells you what to check before publishing.
A video prompt for abstract liquid transition. It gives Runway and Pika a clear role, explicit constraints and a defined output, so the first answer is closer to usable. Fill in the context, run it once, then use the verification notes on this page to review the result.
This copy-ready video prompt helps you cinematic product loop for a hero section with fewer blank-page decisions. Paste it into Sora and Veo, fill the variables, and you get a structured first draft you can edit. It is written for repeatable results and tells you what to check before publishing.
A image prompt for playful 3D product render. It gives Midjourney and Leonardo a clear role, explicit constraints and a defined output, so the first answer is closer to usable. Fill in the variables, run it once, then use the verification notes on this page to review the result.
A image prompt for product hero shot on a stone plinth. It gives Midjourney and Flux a clear role, explicit constraints and a defined output, so the first answer is closer to usable. Fill in the variables, run it once, then use the verification notes on this page to review the result.
Write a product launch announcement email with a prompt built for ChatGPT and Claude. It supplies context, constraints and an output contract, then asks the model to surface assumptions and gaps. Copy it, fill the variables and treat the result as a structured draft, not a final answer.