PluginBench
Skill
Pass
Audit score 90

imagegen

nexu-io/open-design

Generate and edit images using OpenAI's Image API for UI mockups, icons, illustrations, and visual assets.

What is imagegen?

This skill leverages OpenAI's Image API to generate and edit images for project assets. Use it when you need to create UI mockups, icons, illustrations, social cards, and visual references without external design tools.

  • Generate images from text descriptions using OpenAI's Image API
  • Create UI mockups and wireframe visuals
  • Design icons and illustrations for projects
  • Produce social media cards and promotional graphics
  • Edit and refine existing images
  • Generate visual references for design work

How to install imagegen

npx skills add https://github.com/nexu-io/open-design --skill imagegen
Prerequisites
  • OpenAI API key configured
  • Access to OpenAI's Image API
Claude Code
Cursor
Windsurf
Cline

How to use imagegen

  1. 1.Install the skill using the provided npm command
  2. 2.Configure your OpenAI API credentials
  3. 3.Ask the agent to generate an image using trigger phrases like 'generate image', 'create image', or 'icon design'
  4. 4.Provide a detailed description of the image you want to create
  5. 5.Review the generated image and request edits if needed

Use cases

Good for
  • Creating mockups for a new web application interface
  • Generating icon sets for a mobile app
  • Producing social media graphics and promotional cards
  • Creating visual references for design documentation
  • Designing illustrations for marketing materials
Who it's for
  • Product designers
  • UI/UX developers
  • Marketing and content teams
  • Project managers needing quick visual assets
  • Developers prototyping applications

imagegen FAQ

What image formats does this skill support?

The skill uses OpenAI's Image API, which generates images in standard formats. Refer to OpenAI's documentation for specific format support.

Can I edit images after they're generated?

Yes, the skill supports image editing capabilities through OpenAI's Image API for refining and modifying generated images.

What types of images work best?

The skill works well for UI mockups, icons, illustrations, social cards, and visual references. Complex or highly specific designs may require iterative refinement.

Do I need design experience to use this?

No, you can describe what you want in natural language and the AI will generate appropriate visuals. More detailed descriptions typically yield better results.

How do I access the upstream resources?

Visit https://github.com/openai/skills to inspect the upstream README and access the full workflow with original assets and scripts.

Full instructions (SKILL.md)

Source of truth, from nexu-io/open-design.


name: imagegen description: | Generate and edit images using OpenAI's Image API for project assets — UI mockups, icons, illustrations, social cards, and visual references. triggers:

  • "generate image"
  • "create image"
  • "image gen"
  • "openai image"
  • "icon design"
  • "mockup" od: mode: image category: image-generation upstream: "https://github.com/openai/skills"

imagegen

Curated from OpenAI's skills repository.

What it does

Generate and edit images using OpenAI's Image API for project assets — UI mockups, icons, illustrations, social cards, and visual references.

Source

How to use

This catalogue entry advertises the skill in Open Design so the agent discovers it during planning. To run the full upstream workflow with its original assets, scripts, and references, install the upstream bundle into your active agent's skills directory:

# Inspect the upstream README for exact paths
open https://github.com/openai/skills

Then ask the agent to invoke this skill by name (imagegen) or with one of the trigger phrases listed in this skill's frontmatter.