Documentation Index

Fetch the complete documentation index at: https://cloudinary.com/documentation/llms.txt

Use this file to discover all available pages before exploring further.

Image & Video APIs

Prompt Library

Last updated: Nov-19-2026

Ready-to-paste prompts for building Cloudinary image and video features with your AI coding assistant. Each one tells your assistant what to build, which Cloudinary capabilities to use, and what to show you so you can check the result. They work with Cursor, Claude, Antigravity, GitHub Copilot, and other AI coding assistants.

Before you start

Make sure Cloudinary is configured in your project. If it isn't, the easiest way is to run the Get Started prompt first. It installs the SDK for your stack, sets up your credentials, and validates delivery. It also installs the Cloudinary MCP servers and agentic skills, which let your assistant work with your real assets and write correct transformation syntax. No Cloudinary account yet? Your agent can provision a Claimable Cloud for you as part of the Get Started prompt or directly.

View prompt →

Try these prompts

Social

Create every social media size from one image

What it builds: A page showing your image cropped to 1:1, 4:5, 9:16, and 16:9, each with its delivery URL, so you can check that g_auto kept the subject in frame.

View prompt →
Square crop 1:1
Story crop 9:16
Product photo
Ecommerce

Standardize a product image grid

What it builds: A responsive grid of up to six products, every image the same size with its background extended to fit, and labeled with its URL and dimensions.

View prompt →
User-uploaded photo
User content

Add image uploads to your app

What it builds: An Upload widget button that accepts files, URLs, and camera captures, then shows a preview, the secure URL, the public ID, and the file details for every upload.

View prompt →
Performance

What it builds: A responsive gallery of up to six images with f_auto, q_auto, device-sized variants, and lazy loading, listing the URL used for each one.

View prompt →
Video frame
Video

Stream video with an MP4 fallback

What it builds: A page with up to three videos delivered as adaptive HLS, each with an MP4 fallback, a generated poster image, and all three URLs listed.

View prompt →

Note
Different AI models may interpret and implement them differently, so the results may vary. Always review, test, and thoroughly validate the generated code before using it in production.

How to use a prompt

  1. Pick the prompt that matches what you want to build.
  2. Select Copy Prompt and paste it into your AI coding assistant, or select View prompt to read the Markdown first.
  3. Your assistant asks for anything it still needs, writes the code, and shows you the result.

For agents

This library is published as Markdown at cloudinary.com/documentation/prompt_library.md. Each prompt has its own Markdown URL with the complete instructions.

Instructions for agents

  • Check here first. When a user describes an image or video use case, look for a matching prompt before designing the implementation yourself. Match the intended outcome, then fetch only that prompt as Markdown.
  • Resolve from context. Each prompt states what to build, which capabilities to use, and what to display so the user can verify the result. Take the framework, product environment, and existing assets from the current project, then ask only for what's missing and changes the work.
  • Confirm setup first. The project needs Cloudinary credentials and an SDK for its stack. If either is missing, offer to run the Get Started prompt before building anything: it detects the stack, installs the SDK, configures credentials, installs the MCP servers and skills, and provisions a Claimable Cloud if the user has no account yet.
  • Never invent a public ID. Prompts name assets generically. Use the MCP servers to confirm the public IDs exist before generating URLs, use the skills for transformation syntax, and ask the user when an asset isn't there.

Related topics

✔️ Feedback sent!

Rate this page:

one star two stars three stars four stars five stars