use-cases/learn-a-new-concept.md Codex Docs, 2026-04-21 06:45 UTC → 2026-04-30 18:36 UTC

48 48 

49## Skills & Plugins49## Skills & Plugins

50 50 

51- [ImageGen](https://github.com/openai/skills/tree/main/skills/.curated/imagegen)51- ImageGen

52 52 

53 Generate illustrative, non-exact visual assets when a Markdown-native diagram is not enough.53 Generate illustrative, non-exact visual assets when a Mermaid diagram is not enough.

54 54 

55| Skill | Why use it |55| Skill | Why use it |

56| --- | --- |56| --- | --- |

57| [ImageGen](https://github.com/openai/skills/tree/main/skills/.curated/imagegen) | Generate illustrative, non-exact visual assets when a Markdown-native diagram is not enough. |57| ImageGen | Generate illustrative, non-exact visual assets when a Mermaid diagram is not enough. |

58 58 

59## Starter prompt59## Starter prompt

60 60 

163- An experiment map that connects datasets, metrics, baselines, and reported claims.163- An experiment map that connects datasets, metrics, baselines, and reported claims.

164- A limitations diagram that separates assumptions, failure modes, and open questions.164- A limitations diagram that separates assumptions, failure modes, and open questions.

165 165 

166For Markdown-first reports, ask for Mermaid when the destination supports it, or a small checked-in SVG/PNG asset when it does not. Ask Codex to use imagegen only when you need an illustrative, non-exact visual or something that doesn’t fit in a Markdown-native diagram.166For Markdown-first reports, ask for Mermaid when the destination supports it, or a small checked-in SVG/PNG asset when it does not. Ask Codex to use the imagegen system skill, which comes with Codex by default, only when you need an illustrative, non-exact visual or something that doesn't fit in a Markdown-native diagram.

167 167 

168## Write the Markdown report168## Write the Markdown report

169 169