Skill · Workflow
product-photo-to-ad-set
Turns one product photo into three ad images and a short video prompt, using the site's image and video skills. Use when asked to run the "Product photo to ad set" workflow.
The skill itself. Agents read the name and description first and load the rest only when a task matches.
product-photo-to-ad-set/SKILL.md
---
name: product-photo-to-ad-set
description: Turns one product photo into three ad images and a short video prompt, using the site's image and video skills. Use when asked to run the "Product photo to ad set" workflow.
---
# Product photo to ad set
Turns one product photo into three ad images and a short video prompt, using the site's image and video skills.
## Inputs
Ask for any of these that the user hasn't given:
- `product` (e.g. "matte white ceramic pour-over dripper on a walnut stand with a glass carafe")
- `brand_tone` (e.g. "calm, warm, Scandinavian")
## Steps
Run the steps in order. Refer to saved results by name. Don't skip a step that says STOP.
1. **Describe the product** — Start: Start with {{product}}: what it's made of, colours, shape (or describe your product photo).
2. **Image prompt skill** — Load the `prompts-gpt-image-prompt` skill, then: Turn {{product}} into a precise visual description for an image model: materials, colours, shape, best camera angle. Save the result as `subject`.
3. **Three ad images** — Launch these as parallel subagents in one message, then wait for all of them. Write one image prompt per style for {{subject}} in a {{brand_tone}} tone. Save the result as `images`.
- **Lifestyle**: Morning kitchen, soft window light, hands pouring.
- **Studio**: Seamless warm grey backdrop, hard side light.
- **Flat lay**: Top-down with beans, filter papers and a linen cloth.
4. **Video prompt skill** — Load the `prompts-gpt-video-prompt` skill, then: Write an 8-second Veo prompt that animates the lifestyle shot. Save the result as `video`.
5. **Copy the set** — Finish: Return {{images}} and {{video}} as one list.
## Done when
Every step has run, each approval was given, and you've reported what was produced and where it was saved.