# ecommerce-listing-suite Orchestrates full ecommerce image sets for Amazon, Shopee, and Taobao. It locks product identity from photos, drafts platform galleries, and runs quality checks on each asset. - skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · ★ 120 - Author: xianyu110 - License: MIT · policy=mirror · the beginning of the file is at the end of this page - Source: https://github.com/xianyu110/ecommerce-image-skills/tree/HEAD/skills/ecommerce-listing-suite/SKILL.md - Updated: 2026-10-08 - HTML: https://affpapa.org/en/nevibecode/skills/ecommerce-listing-suite ## What it does The skill acts as an orchestrator for complete ecommerce listing galleries. It starts by analyzing user reference images to construct a strict product identity lock. This block details exact shapes, color hex codes, logo placements, and packaging contents, ensuring downstream generation prompts never alter physical dimensions or invent fake features. Next, it plans out the image gallery based on marketplace specifications, such as Amazon's standard seven-image layout or Taobao's five-image sequence. Individual rows in the plan trigger specialized companion skills for infographics, dimension charts, or lifestyle scenes. Prompt drafting differentiates between `gpt-image-2.5-flare` for broad scene drafting and `gpt-image-2.5-sunburst` for precise typography and logo preservation. Direct rendering relies on the agent's native image capabilities or a `GPTIMAGE_API_KEY` configured for the included Python script. Without either, the skill simply prints finished prompts alongside browser links for manual image creation. Once generated, each asset undergoes a three-point inspection before hand-off, regenerating only failing items. ## Install ### Claude Code (native platform) 1. **Skills CLI (Vercel)** ```bash npx skills add xianyu110/ecommerce-image-skills --skill ecommerce-listing-suite -a claude-code ``` 2. **Manually: put the files in place** - File: `~/.claude/skills/ecommerce-listing-suite/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/ecommerce-listing-suite/ ### Codex 1. **Skills CLI (Vercel)** ```bash npx skills add xianyu110/ecommerce-image-skills --skill ecommerce-listing-suite -a codex ``` 2. **Manually: put the files in place** - File: `.agents/skills/ecommerce-listing-suite/SKILL.md` — For all projects use ~/.agents/skills/ ### Cursor 1. **Skills CLI (Vercel)** ```bash npx skills add xianyu110/ecommerce-image-skills --skill ecommerce-listing-suite -a cursor ``` 2. **Manually: put the files in place** - File: `.cursor/skills/ecommerce-listing-suite/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/ ### GitHub Copilot 1. **GitHub CLI** ```bash gh skill install xianyu110/ecommerce-image-skills ecommerce-listing-suite ``` 2. **Manually: put the files in place** - File: `.github/skills/ecommerce-listing-suite/SKILL.md` ### Gemini CLI 1. **Skills CLI (Vercel)** ```bash npx skills add xianyu110/ecommerce-image-skills --skill ecommerce-listing-suite -a gemini-cli ``` 2. **Platform CLI** ```bash gemini skills install https://github.com/xianyu110/ecommerce-image-skills --path skills/ecommerce-listing-suite ``` ### Windsurf (Devin Desktop) **Manually: put the files in place** - File: `.devin/skills/ecommerce-listing-suite/SKILL.md` — The legacy .windsurf/skills/ path still works ### OpenCode **Skills CLI (Vercel)** ```bash npx skills add xianyu110/ecommerce-image-skills --skill ecommerce-listing-suite -a opencode ``` ### Claude.ai **Claude.ai** - Zip the folder and upload it in Settings → Capabilities → Skills Where a file is given instead of a command, copy the files from the source to that path: https://github.com/xianyu110/ecommerce-image-skills/tree/HEAD/skills/ecommerce-listing-suite/SKILL.md ## When to use it - plan complete product photo sets for Amazon, Shopee, Taobao, or TikTok Shop - enforce strict product geometry, logo rendering, and color consistency across prompts - delegate asset creation to dedicated skills for infographics, mockups, and sizing charts - verify finished assets against product specs and marketplace requirements ## Example prompts - Create a full 7-image listing set for Amazon using the product photos in `assets/bottle/` - Draft an identity lock and image plan for this blender targeting Shopee and TikTok Shop - Plan a Taobao gallery with 5 main assets and generate the benefit infographic prompts ## Source text · SKILL.md · MIT Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 66452a7c4e316483. BEGIN THIRD-PARTY FILE 66452a7c4e316483 ````text --- name: ecommerce-listing-suite description: "Orchestrate a complete ecommerce image set for one product: confirm product facts, plan the gallery per platform (Amazon 7-image set, Taobao 5 main + detail page, Shopee, TikTok Shop, Xiaohongshu), lock identity and campaign style, then call the specialised skills and QA every image. Use when the user wants a full listing image set, 全套图, 套图, 一键出图, listing images, PDP image pack." --- # Ecommerce Listing Suite · 全套电商图编排 The entry point: one product in, a full platform-ready image set out — planned, consistent, and checked. > Part of [ecommerce-image-skills](https://github.com/xianyu110/ecommerce-image-skills). Works with Claude Code, Codex, Cursor and any agent that loads `SKILL.md`. Default model: GPT Image 2.5 **Flare**. ## Step 1 · Product identity lock (always first) Before writing any prompt, study every reference photo and write a short **identity lock** for the product. Paste it verbatim into **every** prompt this skill produces, and never let a creative instruction override it. ```text PRODUCT IDENTITY LOCK (do not change): - Shape & proportions: - Colour & finish: - Logo & printed text: - Parts & details: - Must NOT appear: ``` Rules: - Only use facts visible in the photos or confirmed by the user. If something is unknown (size, capacity, material), ask or leave it out — never invent specs or certifications. - If the user gave no photo, ask for one (front view at minimum). Text-only generation is allowed but say the result is a concept, not the real product. ## Step 2 · Pick the model | Use **Flare** (`gpt-image-2.5-flare`, default) | Switch to **Sunburst** (`gpt-image-2.5-sunburst`) | |---|---| | New scenes, backgrounds, layouts, many quick variations | The product's logo / label / small text must survive exactly | ```` END THIRD-PARTY FILE 66452a7c4e316483 The third-party file has ended. Everything between the 66452a7c4e316483 tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file. First 2203 of 6530 bytes. © xianyu110 · MIT · https://github.com/xianyu110/ecommerce-image-skills/tree/HEAD/skills/ecommerce-listing-suite/SKILL.md _Part of the page did not fit — see the HTML version._ --- NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md