Create visual concepts, ready-to-generate prompts, and AI images for ecommerce and conversion-focused product visuals: hero images, lifestyle scenes, flat lays, listing galleries, product-detail pages, store visuals, and coherent image packs. Use when the image presents a product for listing, PDP, storefront, or brand account content — on-image informational copy (卖点, specs, size charts) is in scope. Do not use for paid-placement ad creatives — feed/story/display ads, 投放 banners, or promotion...
Scanned 8/20/2026
Install via CLI
openskills install DeepKolor/deepkolor-agent-skills---
name: ecommerce-image-agent
description: "Create visual concepts, ready-to-generate prompts, and AI images for ecommerce and conversion-focused product visuals: hero images, lifestyle scenes, flat lays, listing galleries, product-detail pages, store visuals, and coherent image packs. Use when the image presents a product for listing, PDP, storefront, or brand account content — on-image informational copy (卖点, specs, size charts) is in scope. Do not use for paid-placement ad creatives — feed/story/display ads, 投放 banners, or promotional ads built around a hook headline and CTA — route those to ad-creative-agent. Do not use for virtual apparel try-on, outfit replacement, or dressing a supplied person in a supplied garment. Do not use for general-purpose photo edits not tied to selling a product (object removal, background swap, retouch, style conversion)."
homepage: https://deepkolor.ai
author: DeepKolor
license: MIT
tags: [image-generation, ecommerce, product, marketplace]
version: lite
---
# Ecommerce Image Agent
> **Lite edition** — routing and core rules for agent discovery. Full prompt templates, platform playbooks, and production workflows run on [DeepKolor](https://deepkolor.ai).
Product visuals for listings, PDP, storefronts, and social — hero shots, lifestyle, flat lays, detail pages, and image packs.
## When to use
See `description` in frontmatter — the agent loads it at startup for routing.
## Workflow
- Identify platform and visual type (hero, lifestyle, UGC, detail, infographic, etc.).
- Keep product identity, claims, and platform ratio rules intact.
- Use image-to-image when a product or person reference must be preserved.
- On-image informational copy (specs, size charts) is in scope for listing content.
## Defaults
resolution=1K; ratio by platform (1:1 listing, 3:4 mobile, 9:16 short video)
## Tool: `create_image_task`
```ts
{
prompt: string,
scene: "text-to-image" | "image-to-image",
aspectRatio?: string,
imageUrls?: string[],
resolution?: "1K"
}
```
Available when your agent runtime exposes DeepKolor generation tools. Otherwise use this skill as a prompt-engineering guide and adapt tool names to your stack.
## Boundaries
- Not for paid ad creatives with hook headline + CTA — use ad-creative-agent.
- Not for virtual try-on or general photo edits unrelated to selling a product.
## Output
After generation, reply briefly: what was created, key parameters, and one useful next step. Return a full prompt only when the user explicitly asks.
## Full version
Production-grade references (SOPs, templates, platform rules) ship inside [DeepKolor](https://deepkolor.ai) — not in this public lite package.
No comments yet. Be the first to comment!