FlowCay logo
FlowCay
Ecommerce Image Suite Skill

Ecommerce Image Suite Skill

Product image suite Skill covering image analysis, selling-point extraction, prompt assembly and generation for domestic and cross-border platforms.

Install command

npx skills add https://github.com/wzj177/ecommerce-image-suite
SkillOpen SourceAll Platforms
Added on Popularity 19

Details

Overview

Ecommerce Image Suite (by wzj177) is an open-source agent Skill for e-commerce product-image production. It turns a raw product photo into a complete, standardized set of e-commerce images through a pipeline of image analysis → selling-point extraction → prompt assembly → image generation. It targets both domestic Chinese platforms (Taobao, JD, Pinduoduo, Douyin) and cross-border scenarios (independent stores, Amazon), with platform-specific size specs, and outputs a unified structured input that downstream copywriting, detail-page HTML and video generation can reuse.

Key Features

  • One-click image set workflow: ① upload product image (+ optional selling points) → ② AI visual analysis extracts structured product info and auto-generates selling-point copy → ③ pick platform spec + image types → ④ AI drafts detailed prompts per image (editable) → ⑤ image-generation API renders the full set → ⑥ optional platform copy → ⑦ optional detail-page HTML → ⑧ optional product showcase video.
  • Structured product analysis (analyze.py): identifies product type, colors, pattern, neckline, silhouette, hemline, fabric texture, season and more, then generates a selling-point JSON with zh/en titles, descriptions and visual keywords (used for magnifier bubbles).
  • 9 standard image types: white-background main image, core-selling-point image (2–4 points), single selling-point deep-dive, material close-up, lifestyle scene, model showcase, multi-scene collage, long detail-page image and three-angle (front/side/back) composite.
  • Prompt assembly (generate.py): builds platform-correct prompts per image type; magnifier-bubble text is auto-filled from the first two English visual keywords; garment position (top / bottom / full-body / non-apparel) is auto-detected for model shots.
  • Multi-provider support: runs against multiple image-generation backends (e.g. Alibaba Tongyi/DashScope, Doubao) with a provider check script, and works in zh or en output.
  • Scene intelligence: target-scene environments (lighting, mood, visual elements) are AI-generated per product; a fallback scene-to-env mapping is only a last resort.
  • Video generation (generate_video.py): optionally produces a product showcase video based on the generated image set.
  • Reference library: bundled prompts, platform specs, model configs and provider docs in references/, plus example images and test data.

How to Use

  1. Use a Skill-compatible agent such as Claude Code, Cursor, or Codex.
  2. Install from the terminal (Node.js required):
npx skills add https://github.com/wzj177/ecommerce-image-suite

Or paste the install prompt from this tool page into your agent and ask it to install for you. 3. Restart / reload the agent so the new Skill is loaded. 4. Invoke the Skill with its slash commands or by asking the agent to run the workflow described in Overview / Key Features. 5. Review outputs before publishing — treat model-generated copy, images, and data as drafts.

Pricing

  • Free & open source: the Skill itself (SKILL.md, Python scripts, references, examples) is free on GitHub (and Gitee mirror). ~200+ stars.
  • Cost driver — image API: you need your own API key for an image-generation provider (e.g. Alibaba DashScope/Tongyi, Doubao); those providers bill per image/token under their own pay-as-you-go plans.

Best For

E-commerce teams, freelancers and cross-border sellers who use AI agent frameworks (Claude Code, Openclaw, etc.) and need to mass-produce standardized, platform-compliant product image sets — main images, selling-point callouts, material shots, lifestyle/model scenes and detail-page material — from plain product photos, without design staff.

FAQ

What does Ecommerce Image Suite do?

It automates the full e-commerce image-set pipeline: analyze a product photo, extract selling points, assemble prompts and render standardized images for Taobao/JD/Pinduoduo/Douyin or Amazon/independent stores.

What do I need to run it?

Python 3, the repo scripts, an image-generation provider API key (e.g. Tongyi/DashScope or Doubao), and an agent framework that supports skills. Run analyze.py first, then generate.py.

What image types can it produce?

Nine types: white-background main image, core selling points, single selling point, material close-up, lifestyle scene, model showcase, multi-scene collage, long detail-page image and three-angle composite.

Which platforms does it support?

Domestic: Taobao, JD, Pinduoduo, Douyin. Cross-border: Amazon listing images and independent stores — with platform-specific size specs.

Is it free?

The Skill is open source and free; you only pay the image-generation provider for actual API usage.