Ecommerce Image Skills plugin
12 skills that turn one product photo into an Amazon main image, lifestyle scene, A+ module, sale banner and Xiaohongshu cover
- 176 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- Scripts send product photos to an external generation service under your key and spend paid calls
- Batch background swaps rewrite a series of files, so set a call cap and keep the originals elsewhere
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add plugins/ecommerce-image-skillsDetects 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.
- Scripts send product photos to an external generation service under your key and spend paid calls
- Batch background swaps rewrite a series of files, so set a call cap and keep the originals elsewhere
This is third-party code. Review the repository files before installing.
What it does
A set of twelve skills for Claude Code, Codex and Cursor. Each one covers a single marketplace image type: the Amazon white-background main image, A+ modules, lifestyle scenes, selling-point infographics, size charts, on-model shots, sale banners, Xiaohongshu covers and long Taobao detail pages. There is also a suite skill for a full listing image set and a multi-angle skill. In every skill the agent first locks the product shape, colour, logo and text and carries them into each prompt so the model does not redraw the product. Platform specs live inside the skills: a `#FFFFFF` background and at least 85 percent product share for the Amazon main image, a 750 px width for Taobao, a 3:4 ratio for Xiaohongshu. Python scripts handle what should not be left to a model: checking and repairing the white background, cutting an image into A+ modules, stitching grids and long pages, and swapping backgrounds across a batch with a cap on the number of calls. The agent gets images in three ways. A built-in image generator is used when the agent has one. Otherwise `scripts/generate.py` works with a `GPTIMAGE_API_KEY` and an optional `GPTIMAGE_BASE_URL` for any OpenAI-compatible gateway. With no key the skill prints a finished prompt and a link to run it online.
Who it is for. Sellers on Amazon, Taobao, Shopee and TikTok Shop, and content managers who need a full set of listing images from one phone photo.
Good fit when
- You need an Amazon white-background main image and want a script to check the background and the product share
- A Taobao store launch needs a long detail page at 750 px wide
- An A+ listing needs correctly sized modules cut from one large image
- Forty photos in a folder must be moved to a clean white background with a cap of forty calls
- Three Xiaohongshu cover variants with a Chinese headline are needed
Not a fit when
- You need a real product shoot with proper lighting: the skills work from an existing photo and do not replace a studio
- You need to edit a finished layout in a design editor with exact layers
- You want images with no API key and the agent has no built-in generator: you will only get a prompt to run by hand
Example request
Take ./photos/bottle.jpg and make an Amazon main image with the amazon-white-background skill, then run the background check scriptLimitations
Generation runs on the GPT Image 2.5 model in Flare and Sunburst modes. Without an agent built-in generator you need a `GPTIMAGE_API_KEY` and paid calls at the chosen gateway rate. The README and skill texts are in Chinese and English, and the Taobao and Xiaohongshu guidance targets the Chinese market. Sunburst is picked to keep logos and text and Flare for fast scenes, and the result should always be compared with the source photo because a model can distort small text. All scripts rely on Python and packages that are installed separately.
How to disable. Delete the skill folders from `~/.claude/skills`, `~/.codex/skills` or `.cursor/skills`. If you installed it as a plugin, run `/plugin uninstall` for this set in Claude Code and remove the marketplace.
FAQ
How do I install Ecommerce Image Skills in Claude Code?
Run `npx skills add xianyu110/ecommerce-image-skills` or `/plugin marketplace add xianyu110/ecommerce-image-skills`. You can also copy `skills/*` into `~/.claude/skills`. A single skill installs by copying its folder, the scripts are inside.
Do I need an API key for the images?
Not when the agent has built-in image generation, as Codex does. Otherwise set `GPTIMAGE_API_KEY` and optionally `GPTIMAGE_BASE_URL` for an OpenAI-compatible gateway. With no key the skill returns the final prompt and an online run link.
How is Flare different from Sunburst?
Flare is faster and suits scenes and several variants in a row. Sunburst is used when a logo and text on the product must stay intact or one area of the photo needs a fix.
Which platforms do the specs cover?
Amazon (main image and A+), Taobao and Tmall, Shopee, TikTok Shop and Xiaohongshu. Sizes and ratios are written into the skills themselves.
Can I install just one skill?
Yes. Copy the folder you need, for example `skills/amazon-white-background`, into the agent skills directory. Each skill keeps its own scripts and the skills do not depend on each other.
Discussion
No questions or reviews yet.
Related
PluginsE-Commerce Image Generator: product images for marketplaces
gpt-image2-ecommerce
A skill that builds prompts and generates listing photos from 39 scene templates and checks the main image
A skill for e-commerce visuals: builds prompts and generates product hero shots, cards and ad images from tested recipes
13 skills for short product videos: hooks, storyboards, edge-tts voice-over and a local ffmpeg render in 9:16 with no API keys
A skill that searches a library of 10,000+ image prompts, shows sample images and tailors the chosen prompt to your article or script
Five image-generation skills: Qwen-Image prompts, logos with shared geometry, diary comics, transparent PNGs and process dioramas
Generate, edit and deliver images through your API providers or the Codex ChatGPT route, with a canvas and version history.
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Repository stars | Main difference |
|---|---|---|---|
| Ecommerce Image Skills (this card) | no | 176 | |
| ecommerce-image-suite | no | 492 | one skill builds the whole listing image set, while this pack has twelve separate skills by platform and image type |
| E-Commerce Image Generator: product images for marketplaces | no | 445 | one skill with 39 scene templates and a main-image check, while this pack has separate skills and A+ and long-page slicing scripts |
README in short
The repository opens with a results gallery and a one-line install, followed by Chinese and English sections on usage, a table of the three ways to get images and a list of the twelve skills. Each skill lists the platform it serves and the scripts it uses. Example prompts and a star history close the page.