ecommerce-image-suite skill
A skill that builds a listing image set from one product photo: white background, selling points, material, scenes, model.
- 492 ★ on the repository
- Last commit
- Apache-2.0
Extended access
Why this level
- Product photos and prompts go to an image provider via an API key and the scripts run on the user's computer.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/ecommerce-image-suiteDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Product photos and prompts go to an image provider via an API key and the scripts run on the user's computer.
This is third-party code. Review the repository files before installing.
What it does
ecommerce-image-suite is a skill for generating a product image set for Taobao, JD, Pinduoduo, Douyin, Amazon and standalone stores. `scripts/analyze.py` turns a product photo into structured data, and `scripts/generate.py` uses it with chosen types (`white_bg`, `key_features`, `selling_pt`, `material`, `lifestyle`, `model`, `multi_scene`) to create images through a connected provider. Providers are Alibaba Tongyi, ByteDance Doubao, OpenAI, Google Gemini and Stability AI, and `scripts/check_providers.py` checks the setup. The skill can also draft marketplace copy, a detail-page HTML and a video from the set, but it renders the video only after user confirmation.
Who it is for. Marketplace sellers and designers preparing listing images for Chinese and cross-border platforms.
Good fit when
- A new listing needs a set: white-background main image, selling points, material and scenes.
- Clothing is shown on a model without a separate photo shoot.
- A batch of products is prepared for the image sizes of different platforms.
- Marketplace copy or a detail-page HTML is added to a finished set.
Not a fit when
- The platform accepts only studio photos: generated details may differ from the product.
- You have no key for any supported image provider.
- You need English documentation: the README and `SKILL.md` are in Chinese.
Example request
Build an image set for this T-shirt for Taobao: white background, three selling points and a scene.Limitations
Documentation and `SKILL.md` are in Chinese. You need Python 3.8 or newer, dependencies such as `openai` and `requests`, and a key for at least one image provider. Tongyi and Doubao work directly from China, while the README notes a proxy is usually needed for OpenAI, Gemini and Stability. The model may distort product details and text in images, so compare the result with the original. The README carries an ad for a third-party relay service for model APIs; the skill itself, by the author's statement, calls official endpoints.
How to disable. Remove the skill folder from the agent's skills directory and clear provider key environment variables you no longer need.
FAQ
Which image providers are supported?
Alibaba Tongyi (`DASHSCOPE_API_KEY`), ByteDance Doubao (`ARK_API_KEY`), OpenAI, Google Gemini and Stability AI. One key is enough.
How do I check the setup?
Run `python3 scripts/check_providers.py`; it reports which providers are configured.
Which image types can it make?
White background, key features, a single selling point, material, scene, model, multi-scene collage, detail page and a three-angle collage.
Where do the keys go?
Keys come from environment variables. The README states the skill calls providers' official endpoints with no third-party server in between.
Can it make video?
Yes, `scripts/generate_video.py` renders a clip from a finished set, but only after user confirmation.
Discussion
No questions or reviews yet.
Related
SkillsA library of 26 e-commerce visual skills: flat-lay to on-model shots, detail pages, main-image video and compliance checks.
E-commerce Visual Copywriting
ecommerce-visual-copywriting
A skill that turns product data into a plan for main images, the product page and A+ content, with on-image copy, generation prompts and a claims check
A Codex skill that turns a product photo and a reference into a plan of five main images and ten product-page screens.
The clipcat skill and CLI help a TikTok Shop seller find videos that sell and produce similar ones with their own product
Six Codex skills that take an Amazon seller from product photos and competitor research to finished main images and A+ content.
Seven workflows for a Shopee and Mercado Livre seller: category research, pricing, listing, images, video, ads and review analysis
README in short
The repository ships scripts for photo analysis, set generation, provider checks and video, plus references and sample results.