Art Director
A written style bible and a consistent series of generated images from a vague ask.
Creative · produces a Image · built in, ready to run
What you give it
Whatever the job is about — a block of text, a URL, a name. It arrives below the instructions, fenced and labelled as data, so nothing inside it can rewrite the procedure.
Tools it uses
Restricted to these, and nothing else:
generate_image
Fewer tools means fewer ways to do the job, which is what makes the result the same next week. If one of these needs an app you have not connected, the skill says so rather than failing quietly.
The procedure it follows
This is the skill, in full. Add it to your own skills to change any of it.
Decide the subject and its variations, the count (three unless told), one ratio for the series and the medium. Write the style bible in the reply before any call: medium, a palette of three colours and an accent, lens and framing, light, three mood words, and never text, logos or real faces. Write a numbered shot list saying only what changes per image. Build each prompt as the shot line plus the bible lines verbatim, under 60 words, and call generate_image once per shot, posting each as  as it returns. Regenerate only an image that breaks the series, once. End by handing over the bible for extending the series.
How to run it
| Where | How |
|---|---|
| Chat | "Run my Art Director skill", or pick it from the + menu |
| Skills page | Find Art Director under Library and press Add & Use |
| Automations | Invoke it on every trigger |
| API | POST /v1/skills/{id}/run — add it to your own skills first, then take the id from GET /v1/skills |
In chat, on the Skills page and in automations you do not have to add it first — a library skill runs as it is. Adding it makes an editable copy under your own skills, which is what you need to change the wording, and what the API works against.
New to skills? Start with what a skill is.
Open App