Product photo to ad set: Multi-Step Agent Workflow for Claude Code, Codex or ChatGPT

Turns one product photo into three ad images and a short video prompt, using the site's image and video skills.

Prompt

Installs to .agents/skills/product-photo-to-ad-set-multi-step-agent-workflow-for-claude-cod/

mkdir -p .agents/skills/product-photo-to-ad-set-multi-step-agent-workflow-for-claude-cod && curl -sL "https://prompts-gpt.com/prompts/product-photo-to-ad-set-multi-step-agent-workflow-for-claude-code-codex-or-chatgpt/raw" -o .agents/skills/product-photo-to-ad-set-multi-step-agent-workflow-for-claude-cod/SKILL.md
SKILL.md
Preview
---
name: product-photo-to-ad-set-multi-step-agent-workflow-for-claude-cod
description: "Turns one product photo into three ad images and a short video prompt, using the site's image and video skills."
---

# Product photo to ad set: Multi-Step Agent Workflow for Claude Code, Codex or ChatGPT

Turns one product photo into three ad images and a short video prompt, using the site's image and video skills.

## Prompt

```
---
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.
```

## Usage Notes

Run it in Claude Code or Codex: save as .claude/skills/product-photo-to-ad-set/SKILL.md (or .agents/skills/ for Codex) and say "run the Product photo to ad set workflow"; parallel steps run as subagents. Or paste it into ChatGPT or Claude and answer its questions. It asks for: product, brand_tone. Build or run it step by step at prompts-gpt.com/workflows/product-photo-to-ad-set.

Example output

At a glanceFrom one product photo to a four-asset ad setFive workflow steps, no approval stops
  1. Product descriptionStep 1Ceramic dripper, walnut stand, glass carafe
  2. Subject promptStep 2Three-quarter view, slightly elevated
  3. Three image promptsStep 3Lifestyle 4:5, studio 1:1, flat lay 1:1
  4. Video promptStep 48-second Veo prompt, 16:9
  5. Final setStep 5Saved under images and video

Example for: product = "matte white ceramic pour-over dripper on a walnut stand with a glass carafe", brand_tone = "calm, warm, Scandinavian."

Ad Set: Ceramic Pour-Over Dripper

Step 1: Product description

A matte white ceramic cone dripper with fine vertical ribs inside and a single drain hole. It sits on an oiled walnut stand with a rounded square base. Below it is a clear borosilicate glass carafe holding about 600 ml, with a thin lip and no handle.

Step 2: subject (via prompts-gpt-image-prompt)

A matte white ceramic cone pour-over dripper with soft eggshell texture, resting on a warm-toned oiled walnut stand with visible straight grain, above a thin-walled clear glass carafe partly filled with amber coffee. Simple geometric silhouette. The best angle is three-quarter view at eye level, slightly elevated (about 15°), so the cone's taper and the walnut grain both read clearly.

Step 3: images (3 parallel subagents)

1. Lifestyle

[subject] on a pale oak kitchen counter in early morning. Soft diffused light comes through a linen-curtained window on the left. A woman's hands pour from a matte black gooseneck kettle in a slow spiral, and gentle steam rises. The palette is muted cream, walnut and sage. Shallow depth of field, 50mm, calm and unhurried Scandinavian mood. Natural skin tones, no logos, 4:5.

2. Studio

[subject] centred on a seamless warm grey (#B8B2AA) backdrop. Hard directional light from camera right casts a crisp shadow to the left and catches the ceramic's soft texture and the walnut grain. Clean, quiet, premium feel. 85mm, f/8, product fully sharp, minimal reflections on the glass, 1:1.

3. Flat lay

Top-down view of [subject] on a rumpled oatmeal linen cloth. Scattered whole coffee beans, a small stack of unbleached paper filters, and a brass scoop are arranged with generous negative space. Soft, even overhead light with gentle shadows. Warm neutral palette, calm Nordic restraint, 1:1.

Step 4: video (via prompts-gpt-video-prompt)

8-second Veo prompt: Morning kitchen with soft window light from the left and a pale oak counter. Opens on a slow push-in toward a matte white ceramic pour-over dripper on a walnut stand over a glass carafe (0–3s). Hands enter and pour hot water from a black gooseneck kettle in a gentle spiral, and steam curls upward (3–6s). Close-up of amber coffee dripping into the carafe as light catches the glass (6–8s). The camera moves smoothly on a slider. Calm, warm Scandinavian tone, muted cream and walnut palette. Audio is soft pouring, faint birdsong and a low ambient hum. No text, no music.

Step 5: Final set

#AssetFormatSaved as
1Lifestyle image prompt4:5images[0]
2Studio image prompt1:1images[1]
3Flat lay image prompt1:1images[2]
4Lifestyle animation prompt8s, 16:9video

Report: All 5 steps are complete. None of the steps needed approval, since the workflow has no STOP points. The three image prompts are saved together under images and the Veo prompt under video. Paste each one into your image or video generator to produce the final ad set.

Written by AI from this prompt. Your results will vary.

Run it in Claude Code or Codex: save as .claude/skills/product-photo-to-ad-set/SKILL.md (or .agents/skills/ for Codex) and say "run the Product photo to ad set workflow"; parallel steps run as subagents. Or paste it into ChatGPT or Claude and answer its questions. It asks for: product, brand_tone. Build or run it step by step at prompts-gpt.com/workflows/product-photo-to-ad-set.

Make it repeatable

Keep using this prompt without pasting it in every time.

Prompt details

By
Prompts-GPT editors
Published
How prompts are written and checked

Did this prompt work?

Keep exploring

More in Multi-Agent Pipelines