Skip to content
Skillpedia
Misc101k · #608

od-media-generation

Lets your agent create and refine media like images and videos. It generates content and improves it until the desired result is met. Ideal for content creation projects.

What it does

This tool helps create images, videos, or audio. It uses your instructions to generate content and allows you to review and request improvements until you are satisfied.

When to use it

  • ✓Creating an image for a blog post.
  • ✓Generating a short video for social media.
  • ✓Producing audio for a podcast.

Example of what to ask your AI

“Create an image of a cat astronaut on Mars, with a 16:9 aspect ratio.”

Want more? Open the sections below.

How to use

The easiest way: copy the message below and paste it into Claude, ChatGPT, Cursor or any AI. It reads the skill and follows the instructions.

Skill link

https://github.com/nexu-io/open-design/blob/main/plugins/_official/scenarios/od-media-generation/SKILL.md

Ready-to-paste message

Use this skill to help me: https://github.com/nexu-io/open-design/blob/main/plugins/_official/scenarios/od-media-generation/SKILL.md Read the SKILL.md file at that link and follow its instructions for my task.
How it works

You describe what you want (image, video, or audio), and the tool uses that description to generate the content. Afterward, you can provide ratings and feedback for it to try again, improving the result.

Installation

Easiest way: copy the skill link and paste it into Claude, ChatGPT or Cursor asking it to follow the instructions.

In the terminal (Claude Code, Codex, Cursor), in your project folder:

npx skills add nexu-io/open-design --skill od-media-generation

Or download just the file:

curl -L https://raw.githubusercontent.com/nexu-io/open-design/main/plugins/_official/scenarios/od-media-generation/SKILL.md -o SKILL.md
Technical content (original SKILL.md)

Original text by the author, straight from GitHub.

od-media-generation (scenario)

This scenario plugin is the bundled default for projects whose metadata.kind is image, video, or audio. The web client and the daemon both look up defaultScenarioPluginIdForKind(kind) from @open-design/contracts and, when no other plugin is applied, bind this scenario at project / run creation time.

Default pipeline

{
  "stages": [
    { "id": "discovery", "atoms": ["discovery-question-form"] },
    { "id": "plan",      "atoms": ["todo-write"] },
    { "id": "generate",  "atoms": ["media-image", "media-video", "media-audio", "live-artifact"] },
    {
      "id": "critique", "atoms": ["critique-theater"],
      "repeat": true,
      "until": "critique.score>=4 || iterations>=3"
    }
  ]
}

The generate stage lists all three media atoms even though a single run only calls one of them. Picking the right atom is the agent's job:

  • metadata.kind === 'image' → media-image
  • metadata.kind === 'video' → media-video
  • metadata.kind === 'audio' → media-audio

If the user picks this plugin manually without a media-typed project, prefer media-image and explain the assumption in the first reply.

Atom call shape

Every media atom takes the same kernel of inputs and returns a media artifact reference that live-artifact can wrap:

  • prompt — the rendered useCase.query after input substitution.
  • aspect — one of 1:1 / 16:9 / 9:16 / 4:3 / 3:4. Default 16:9. The contracts MediaAspect union enumerates the legal values.
  • provider — left blank by default so the daemon picks the user's configured provider for this media kind (see Settings → Media providers). Only set this when the user names a provider explicitly.

After the media atom returns:

  1. Save the binary into <cwd>/media/<timestamp>.<ext>.
  2. Call live-artifact to register a preview surface pointing at the saved file. The preview is what the user sees in the right pane.

Critique loop

critique-theater reads the artifact, scores it across the standard five dimensions, and emits a critique.score signal. The until clause stops the loop at score ≥ 4 or three iterations, whichever comes first. Use the critique notes to drive the next media call's prompt, not to re-pick the media atom.

Replace, do not extend

Enterprise editions that need a different default for media work should ship a sibling scenario plugin and add the right mapping in @open-design/contracts/scenario-defaults, not patch this manifest.

FAQ

How does the AI know whether to create an image, video, or audio?

It usually deduces from the type of project you are creating. If unsure, it might ask or assume you want an image.

What is 'critique-theater'?

It's a step where the AI evaluates what it created. You can also give your opinion so it can improve the result.

Can I choose the quality or style?

You can influence the style through your description (prompt). The quality is evaluated, and the AI tries to improve based on your ratings.

Details

Original description by the author

Default reference pipeline for image, video, and audio projects — routes through media-image / media-video / media-audio atoms based on the project kind, wraps the output in a live artifact, and devloops on critique-theater until the score converges.

repo: nexu-io/open-design

Popularity

GitHub stars
101k
Ranking position
#608
License
Apache-2.0
Updated
10/16/2026

Is this skill useful?

0

Sign in to vote.

Comments

  • …

More skills from this repository

Similar skills