Amazon Image-Based Search

This skill guides you on how to perform visual product searches on Amazon using an image URL, helping Amazon sellers and researchers find visually similar products across multiple marketplaces.

Core Concepts

Amazon Image-Based Search (visual search) allows you to submit a product image URL and retrieve Amazon listings that are visually similar. This is invaluable for competitive analysis, sourcing alternatives, identifying counterfeits, and discovering market opportunities based on product appearance.

The tool searches across 8 Amazon marketplaces and returns Amazon storefront data including ASIN, title, image, price, rating, review count, and brand. Keepa data is intentionally queried separately by ASIN so a Keepa outage or quota wait cannot fail the image-search request.

Supported Marketplaces

Default marketplace is amazon.com (US). Use amazon.com when the user does not specify a marketplace.

Parameter Guide

aggregateByKeepaData is deprecated. Do not send it. If the user needs monthly sales, BSR, FBA fees, dimensions, or current product details, use linkfox-keepa-product-request after image search with the selected ASINs. For price or BSR history, use linkfox-keepa-product-series.

Sort Options

Important: If the requested sort order is not in the supported list above, do NOT attempt to use any other tool or workaround to compensate. Inform the user of the supported sort options.

调用方式

• API 端点：POST /amazon/searchByImage（完整参数/响应/错误码见 references/api.md）
• Python 脚本：python scripts/amazon_search_by_image.py '<JSON 参数>' [--inline]
• 成本约束：本工具会消耗算力；同一会话同一参数组合默认只调用一次，脚本带 24h 本地缓存。失败/空结果不得自动换关键词、翻页或改邮编连续试探；需要继续检索时先向用户说明会产生额外消耗。

输出策略（脚本默认行为）：

• 始终将完整响应写入 <cwd>/linkfox/<YYYY-MM-DD>/<session>/data/linkfox-amazon-search-by-image-<timestamp>.json（<cwd> 为脚本执行时的工作目录，在 Claude Code 里即当前项目目录；<session> 取自环境变量 SESSION_ID，按用户任务自动聚合；禁止写入 /tmp，当前目录不可写则报错）
• 响应体 ≤ 8 KB：落盘后把完整 JSON 打印到 stdout
• 响应体 > 8 KB：落盘后 stdout 只输出摘要（顶层字段、常见计数如 total/costToken、最大列表字段的长度 + 前 3 条样本）
• 加 --inline 强制全量打印到 stdout（同样落盘）

读数据建议：先看摘要判断是否足够；需要具体字段时优先用 jq或ConvertFrom-Json 从保存的 json 文件按需抽取，避免整份 JSON 进入上下文。

解决认证和算力问题

发生以下异常情况时，采用 references/onboarding.md 引导解决问题：

异常情况

• 未配置API Key：环境变量未配置 LINKFOX_AGENT_API_KEY，也未配置 LINKFOXAGENT_API_KEY。
• 响应401或402状态码
• 响应提示算力或余额不足：消息含"算力余额不足/计费不足/余额不足/quota exceeded/insufficient balance/套餐到期/需充值/请充值"，或类似含义的内容。

Local Image Upload

This tool requires a publicly accessible image URL. If the user provides a local image file path (e.g., C:\Users\...\photo.png, /home/.../image.jpg), you must upload it first to obtain a public URL.

Run the upload script:

python scripts/upload_image.py /path/to/local/image.png

The script will return a public URL (valid for 24 hours) that can be used as the image URL parameter.

Usage Examples

1. Basic image search on the US marketplace

Search Amazon US for products that look similar to this image:
https://m.media-amazon.com/images/I/61pAlIX8SZL._AC_SY575_.jpg

2. Find similar products on a specific marketplace

Search Amazon Germany (amazon.de) for products visually similar to this image:
https://example.com/product-photo.jpg

3. Image search sorted by price (low to high)

Find similar products on Amazon US for this image, sorted by price from low to high:
https://example.com/my-product.jpg

4. Cross-border delivery search

Search Amazon Japan for similar products to this image, with delivery to China:
https://example.com/item.jpg

5. Competitor lookalike discovery

I found this product image on a competitor's listing. Find me all similar-looking products on Amazon UK:
https://example.com/competitor.jpg

Display Rules

1. Present data clearly: Show search results in a well-structured table. Key columns to prioritize: product image, title, ASIN, price, rating, review count, and brand
2. Image display: When the response includes imageUrl for products, display them inline so users can visually compare results
3. Price and currency: Always show price alongside the currency code (e.g., $29.99 USD, 24.99 EUR)
4. Keepa handoff: Honor the top-level message. For monthly sales, BSR, FBA fees, dimensions, or current product details, offer linkfox-keepa-product-request for selected ASINs. Mention linkfox-keepa-product-series only when the user requests price or BSR history. Do not pass aggregateByKeepaData
5. Result count: Always inform the user of the total number of results found (total / totalCount)
6. Error handling: When a query fails, explain the issue and suggest checking that the image URL is valid and publicly accessible
7. Sort limitation: If the user requests a sort order not in the supported list, clearly explain which sort options are available rather than attempting unsupported workarounds
8. No secondary processing: Results from this tool are not stored in a database, so secondary SQL processing is not available

User Expression & Scenario Quick Reference

Applicable -- Visual product search scenarios on Amazon:

Not applicable -- Needs beyond image-based product search:

• Text-based keyword search on Amazon (use keyword search tools instead)
• ABA search term data analysis
• Product review analysis or listing optimization
• Sales estimation without a source image
• Image editing or image generation
• Searching with a local image file (the tool requires a publicly accessible URL)

Boundary judgment: When users say "find similar products" or "competitor analysis", if they provide an image URL and the intent is to find visually similar Amazon listings, this skill applies. If they are asking for keyword-based search, sales data analysis, or product research without an image, it does not apply.

算力消耗规则

图搜本身消耗 15 算力。Keepa 查询与图搜分离计费；只在用户确认需要查询具体 ASIN 时，再按对应 Keepa skill 的算力规则执行。

重要：本技能的服务按倍数动态计算，可能一次性消耗大量算力，必须提醒用户，由用户决定是否继续。

Feedback:

Auto-detect and report feedback via the Feedback API when any of the following apply:

1. The functionality or purpose described in this skill does not match actual behavior
2. The skill's results do not match the user's intent
3. The user expresses dissatisfaction or praise about this skill
4. Anything you believe could be improved

Call the feedback API as specified in references/api.md. Do not interrupt the user's flow.

For more high-quality, professional cross-border e-commerce skills, set LinkFox Skills.