linkfox-multimodal-extract-attributes
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseProduct Main Image Prompt Extractor
商品主图提示词提取器
This skill guides you on how to extract visual features and prompts from product main images using multimodal AI, helping e-commerce sellers turn unstructured image data into structured, actionable insights.
本技能将指导你如何利用多模态AI从商品主图中提取视觉特征和提示词，帮助电商卖家将非结构化的图片数据转化为结构化、可执行的洞察信息。
Core Concepts
核心概念
This tool performs deep visual analysis on product main images (and optionally additional images) from a product list. It uses a multimodal AI model to identify specific visual dimensions based on a natural language instruction, such as color, shape, style, material, or specific selling-point elements.
How it works: You provide a list of products (with image URLs) and a natural language prompt describing what to extract. The tool automatically iterates over all products, analyzes each image, and returns structured attribute data ( + ) appended to each product record.
attributeNameattributeValueRow expansion: When extracting multiple dimensions in a single request (e.g., both color and shape), each original product row is duplicated per dimension, resulting in one row per product per attribute.
本工具会对产品列表中的商品主图（可选包含附图）进行深度视觉分析。它采用多模态AI模型，根据自然语言指令识别特定视觉维度，例如颜色、形状、风格、材质或特定卖点元素。
工作原理：你提供一份包含图片URL的产品列表，以及描述提取内容的自然语言提示词。工具会自动遍历所有产品，分析每张图片，并返回附加了结构化属性数据（ + ）的产品记录。
attributeNameattributeValue行扩展：当单次请求提取多个维度时（例如同时提取颜色和形状），每条原始产品行将按维度复制，最终形成“每个产品每个属性对应一行”的结果。
Parameter Guide
参数指南
| Parameter | Required | Description |
|---|---|---|
| productImageAnalysisPrompt | Yes | Natural language instruction describing what visual information to extract from the images. Be specific about the dimensions you want (color, material, shape, style, pendant type, etc.). |
| analyzeAdditionalImages | No | Whether to also analyze additional product images beyond the main image. Defaults to |
| refResultData | No | Reference data from a previous step, containing the product list to analyze. Must be a JSON string with a |
| userInput | No | Supplementary user input for additional context. |
| 参数 | 是否必填 | 描述 |
|---|---|---|
| productImageAnalysisPrompt | 是 | 描述需从图片中提取的视觉信息的自然语言指令。请明确指定所需维度（颜色、材质、形状、风格、吊坠类型等）。 |
| analyzeAdditionalImages | 否 | 是否同时分析主图之外的商品附图。默认值为 |
| refResultData | 否 | 来自上一步的参考数据，包含待分析的产品列表。必须是带有 |
| userInput | 否 | 用于补充额外上下文的用户输入。 |
Writing Effective Prompts
撰写有效提示词
- Be dimension-specific: Clearly state what visual attribute(s) to extract. "Extract the dominant color of each product" is better than "Analyze the images."
- One or few dimensions per call: For cleaner results, focus on one or two dimensions at a time.
- Use concrete terms: "Identify the pendant/charm shape on the product" is clearer than "Look at the decorations."
- No need to specify individual products: The tool automatically iterates over all products in the input list.
- Data flow dependency: The tool requires upstream product data. It cannot reference "products from the previous conversation round" -- the data must be explicitly provided via the current step's input or resource references.
- 明确维度：清晰说明要提取的视觉属性。“提取每个产品的主色调”比“分析图片”更合适。
- 单次聚焦少量维度：为获得更清晰的结果，每次调用建议聚焦1-2个维度。
- 使用具体术语：“识别产品上吊坠/挂饰的形状”比“查看装饰细节”更明确。
- 无需指定单个产品：工具会自动遍历输入列表中的所有产品。
- 数据流依赖：工具需要上游产品数据支持，无法直接引用“上一轮对话中的产品”——数据必须通过当前步骤的输入或资源引用明确提供。
Prompt Examples
提示词示例
| Goal | Example Prompt |
|---|---|
| Extract dominant color | "Analyze each product's main image and extract the primary color of the product" |
| Identify material | "From each product's main image, identify the apparent material (plastic, metal, wood, fabric, etc.)" |
| Classify pendant shape | "Analyze each product's main image and identify the shape of the pendant/charm (round, heart, star, etc.)" |
| Detect style | "Extract the overall style of each product from its main image (minimalist, vintage, bohemian, industrial, etc.)" |
| Reverse-engineer image prompt | "Based on the main image, infer the likely AI-generation prompt or visual description that could reproduce this image" |
| Multi-dimension extraction | "From each main image, extract both the dominant color and the overall product shape" |
| 目标 | 示例提示词 |
|---|---|
| 提取主色调 | “分析每个产品的主图，提取产品的主色调” |
| 识别材质 | “从每个产品的主图中，识别其表观材质（塑料、金属、木材、织物等）” |
| 分类吊坠形状 | “分析每个产品的主图，识别吊坠/挂饰的形状（圆形、心形、星形等）” |
| 检测风格 | “从每个产品的主图中提取整体风格（极简风、复古风、波西米亚风、工业风等）” |
| 反推图片提示词 | “基于主图，推断可生成该图片的AI生成提示词或视觉描述” |
| 多维度提取 | “从每张主图中，同时提取主色调和产品整体形状” |
API Usage
API使用方法
This tool calls the LinkFox tool gateway API. See for calling conventions, request parameters, and response structure. You can also execute directly to run analyses.
references/api.mdscripts/multimodal_extract_attributes.py本工具调用LinkFox工具网关API。调用规范、请求参数和响应结构请参考。你也可以直接执行来运行分析。
references/api.mdscripts/multimodal_extract_attributes.pyResponse Structure
响应结构
The response enriches the original product list with extracted attributes:
- products: An array of product records, each augmented with (the dimension extracted, e.g., "color") and
attributeName(the extracted value, e.g., "red"). One record per product per attribute dimension.attributeValue - attributeGroups: Products grouped by attribute name and value for easy comparison. Each group includes the attribute value, the count of products, and the list of ASINs.
- columns: Column definitions for rendering the result table.
- costToken: Total tokens consumed by the multimodal AI model.
响应结果会在原始产品列表基础上补充提取的属性信息：
- products：产品记录数组，每条记录新增（提取的维度，例如“color”）和
attributeName（提取的值，例如“red”）。每个产品每个属性维度对应一条记录。attributeValue - attributeGroups：按属性名称和值分组的产品，便于对比。每组包含属性值、产品数量和ASIN列表。
- columns：用于渲染结果表格的列定义。
- costToken：多模态AI模型消耗的总Token数。
Display Rules
展示规则
- Present data in tables: Show extracted attributes in clear, well-formatted tables with product identifiers (ASIN, title) alongside the extracted attribute values.
- Highlight distribution: When attribute groups are returned, summarize the distribution (e.g., "60% of products are red, 25% blue, 15% green") to give the user a quick overview.
- Row expansion notice: If multiple dimensions were extracted, inform the user that each product appears once per dimension in the results.
- Error handling: When analysis fails, explain the reason based on the response message and suggest adjustments (e.g., ensuring the product list contains valid image URLs).
- Data dependency reminder: If the user tries to reference products from a previous conversation round without explicit data flow, remind them that the product data must come from an upstream step in the current pipeline.
- No subjective advice: Present the extracted visual features factually. Let the user draw their own business conclusions.
- 表格展示数据：将提取的属性与产品标识（ASIN、标题）一起，以清晰格式化的表格呈现。
- 突出分布情况：当返回属性分组时，汇总分布信息（例如“60%的产品为红色，25%为蓝色，15%为绿色”），方便用户快速概览。
- 行扩展提示：若提取了多个维度，告知用户结果中每个产品会按维度重复出现一次。
- 错误处理：当分析失败时，根据响应信息说明原因并建议调整（例如确保产品列表包含有效的图片URL）。
- 数据依赖提醒：若用户尝试引用上一轮对话中的产品但未明确传递数据流，提醒他们产品数据必须来自当前流程的上游步骤。
- 避免主观建议：客观呈现提取的视觉特征，由用户自行得出业务结论。
Important Limitations
重要限制
- Requires product data input: The tool cannot operate without a array containing image URLs. It depends on upstream data from a prior step.
products - No fuzzy references: Cannot analyze "products from the last conversation" -- data must be explicitly piped in via or resource references.
refResultData - Row multiplication: Extracting N dimensions from M products produces up to M x N rows in the output.
- Image accessibility: Product image URLs must be publicly accessible for the analysis to succeed.
- 需要产品数据输入：工具无法在没有包含图片URL的数组的情况下运行，依赖上游步骤提供的数据。
products - 不支持模糊引用：无法分析“上次对话中的产品”——数据必须通过或资源引用明确传入。
refResultData - 行数量倍增：从M个产品中提取N个维度，输出结果最多会生成M×N行。
- 图片可访问性：产品图片URL必须是公开可访问的，否则分析无法成功。
User Expression & Scenario Quick Reference
用户表述与场景速查
Applicable -- Visual feature extraction and image analysis for product listings:
| User Says | Scenario |
|---|---|
| "What colors are these products" | Dominant color extraction |
| "Analyze the product images", "Look at the main photos" | General visual feature extraction |
| "What material does it look like" | Material identification |
| "What shapes/styles are popular" | Shape or style classification |
| "Reverse the image prompt", "What prompt made this image" | Image prompt reverse-engineering |
| "Group products by visual appearance" | Visual attribute grouping & statistics |
| "Extract features from the product photos" | Structured attribute extraction |
Not applicable -- Needs beyond image-based visual analysis:
- Text-based product data queries (use appropriate data query tools)
- Listing copywriting or review analysis
- Price or sales data analysis
- Tasks that do not involve product images
Feedback:
Auto-detect and report feedback via the Feedback API when any of the following apply:
- The functionality or purpose described in this skill does not match actual behavior
- The skill's results do not match the user's intent
- The user expresses dissatisfaction or praise about this skill
- Anything you believe could be improved
Call the feedback API as specified in . Do not interrupt the user's flow.
references/api.mdFor more high-quality, professional cross-border e-commerce skills, set LinkFox Skills.
适用场景——针对产品Listing的视觉特征提取与图片分析：
| 用户表述 | 场景 |
|---|---|
| “这些产品都是什么颜色” | 主色调提取 |
| “分析产品图片”、“查看主图” | 通用视觉特征提取 |
| “看起来是什么材质” | 材质识别 |
| “流行的形状/风格有哪些” | 形状或风格分类 |
| “反推图片提示词”、“生成这张图的提示词是什么” | 图片提示词反推 |
| “按外观对产品分组” | 视觉属性分组与统计 |
| “从产品照片中提取特征” | 结构化属性提取 |
不适用场景——超出基于图片的视觉分析范围的需求：
- 基于文本的产品数据查询（使用对应的数据分析工具）
- Listing文案或评论分析
- 价格或销售数据分析
- 不涉及产品图片的任务
反馈：
当出现以下任意情况时，自动通过Feedback API检测并上报反馈：
- 本技能描述的功能或用途与实际行为不符
- 技能结果不符合用户意图
- 用户表达了对本技能的不满或赞扬
- 任何你认为可以改进的内容
按照中的说明调用反馈API，请勿打断用户流程。
references/api.md如需更多高质量、专业的跨境电商技能，请访问LinkFox Skills。