goods-images

What This Skill Does

The goods-images skill is an advanced automation agent designed for e-commerce professionals and store owners using platforms like Taobao, Tmall, or JD. It streamlines the creation of high-conversion product marketing materials. By leveraging the user's provided product photos, the skill intelligently generates a professional set of 14 images: 5 carousel images and 9 detail images. It ensures brand consistency by maintaining the visual integrity of the original product while applying sophisticated layout design, marketing copy, and scene-based backgrounds. The skill uses a dual-engine approach, preferring Python PIL for text rendering to avoid AI-generated text artifacts, and intelligently falling back to generative models for scene expansion.

Installation

To integrate this skill into your environment, run the following command in your terminal: clawhub install openclaw/skills/skills/briefness/goods-images

Use Cases

• E-commerce Launch: Quickly generate a full set of listing images from a single high-quality product shot.
• Seasonal Promotions: Update product displays with new activity tags and banners without professional graphic design software.
• Marketplace Optimization: Create consistent, professional, and high-conversion imagery for multiple platforms simultaneously.
• Brand Expansion: Generate diverse usage scenarios and lifestyle shots based on studio-captured product photos.

Example Prompts

1. "我上传了一张运动鞋的照片，帮我生成一套适合淘宝店铺的详情图和5张主图，风格要潮酷一些，活动标签写'限时8折'。"
2. "这是我的护肤品实拍图，请为我制作9张详情图，包含卖点介绍、成分标注和售后保障信息。"
3. "我想把这款杯子的图片做成轮播图，背景要简约高端，突出材质和耐用性，需要5张图，请直接帮我排版。"

Tips & Limitations

• Image Integrity: The skill is strictly instructed to preserve the product, logo, and text from the original photo. Avoid asking it to "redraw" the product; focus on the layout and context.
• Input Requirements: Provide the highest resolution images possible to ensure better detail in the final output. If the product category is niche, specify the core selling points to help the AI categorize the visual style better.
• Workflow Logic: Remember that the skill generates a large batch of 14 images. Ensure your environment has sufficient storage or memory to handle multiple generative API calls simultaneously.
• Text Rendering: Using PIL for text overlay is the preferred method for sharpness and readability; ensure your system supports the necessary font rendering libraries for the best results.