Skip to main content
skill CX Codex

linkfox-amazon-search-by-image — Claude Code skill: how to install

Finds visually similar products across 8 Amazon regional stores from an image link, returning prices, ASINs, brands, and ratings.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add linkfox-ai/linkfox-skills --skill linkfox-amazon-search-by-image -a claude-code
Open on GitHub

What linkfox-amazon-search-by-image does

This skill queries Amazon storefronts by image URL via POST /amazon/searchByImage or python scripts/amazon_search_by_image.py. It searches across eight country domains, including the United States, Germany, the United Kingdom, France, Italy, Spain, Japan, and India. The output includes ASIN numbers, titles, storefront photos, prices, star ratings, and review totals.

Local photos require a publicly accessible web address. The helper script python scripts/upload_image.py /path/to/local/image.png hosts the file and yields a temporary address valid for 24 hours. Result ordering can follow price (price-asc-rank, price-desc-rank), rating, or feedback volume. Sales velocity and historical BSR metrics stay decoupled in Keepa requests so API hiccups do not break the visual query.

Requests consume compute quota and demand either LINKFOX_AGENT_API_KEY or LINKFOXAGENT_API_KEY in environment variables. Results are saved directly under linkfox/<YYYY-MM-DD>/<session>/data/ inside the active directory; writing to /tmp is prohibited, so the script fails immediately if current project storage is read-only.

What it helps with

  • locate similar products across eight Amazon regional stores using a photo link
  • gather competitor pricing, ASINs, and ratings from Amazon visual search
  • generate a 24-hour public URL for a local product image file
  • filter Amazon visual matches by ascending or descending price rank

Example prompts for the agent

  • Search Amazon US for products that look similar to this image: https://m.media-amazon.com/images/I/61pAlIX8SZL._AC_SY575_.jpg
  • Find similar products on amazon.de using https://example.com/product-photo.jpg sorted by price from low to high
  • Upload local file python scripts/upload_image.py /path/to/local/image.png and search amazon.co.uk for matching items

How to install linkfox-amazon-search-by-image

1Skills CLI (Vercel)

npx skills add linkfox-ai/linkfox-skills --skill linkfox-amazon-search-by-image -a claude-code

2Manually: put the files in place

~/.claude/skills/linkfox-amazon-search-by-image/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/linkfox-amazon-search-by-image/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about linkfox-amazon-search-by-image

How do I install linkfox-amazon-search-by-image in Claude Code?

Run npx skills add linkfox-ai/linkfox-skills --skill linkfox-amazon-search-by-image -a claude-code. The skill configuration saves to ~/.claude/skills/linkfox-amazon-search-by-image/SKILL.md.

What does linkfox-amazon-search-by-image do?

It searches eight Amazon marketplaces for visually identical or comparable listings using a product image URL. The output delivers ASINs, titles, ratings, review counts, and current storefront prices.

Can I run a search using a local photo file?

Yes, but you must first create a public URL by running python scripts/upload_image.py /path/to/local/image.png. That script provides a link that remains active for 24 hours.

Source text

SKILL.md · MIT
---
name: linkfox-amazon-search-by-image
description: 基于图片的亚马逊跨站点视觉商品搜索,支持8个站点的以图搜图和视觉相似商品发现。当用户提到以图搜图、图片搜索、视觉搜索、找同款、外观相似商品、图片找货、竞品图片搜索、相似商品发现、image search, Amazon visual search, find similar products, reverse image lookup, visual search, similar items, competitor image search, product image match时触发此技能。即使用户未明确提及"图片搜索",只要用户提供了图片URL并希望在亚马逊上查找匹配或相似的商品,也应触发此技能。
---

# 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

| Marketplace | Domain | Default Zip Code |
|-------------|--------|-------------------|
| United States | amazon.com | 10001 |
| United Kingdom | amazon.co.uk | EC1A 1BB |
| Germany | amazon.de | 10115 |
| France | amazon.fr | 75001 |
| Italy | amazon.it | 00100 |
| Spain | amazon.es | 28001 |
| Japan | amazon.co.jp | 100-0001 |
| India | amazon.in | 110034 |

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

## Parameter Guide

| Parameter | Required | Description |
|-----------|----------|-------------|
| imageUrl | Yes | A valid, publicly accessible image URL to search with |
| amazonDomain | Yes | Amazon marketplace domain (e.g., `amazon.com`, `amazon.de`). Defaults to `amazon.com` |
| sort | No | Sort order for results. Supported values: `default`, `price-asc-rank`, `price-desc-rank`, `rating-asc-rank`, `rating-desc-rank`, `ratings-asc-rank`, `ratings-desc-rank` |
| deliveryZip | No | Delivery address zip code within the marketplace country. Uses the marketplace default if not specified |
| countryOrAreaCode | No | Country/region code for cross-border delivery (e.g., `CN`, `JP`, `KR`). Cannot be used together with `deliveryZip`. Note: India marketplace does not support cross-border delivery |

`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

| Value | Description |
|-------|-------------|
| `default` | Default relevance sorting |
| `price-asc-rank` | Price: low to high |
| `price-desc-rank` | Price: high to low |
| `rating-asc-rank` | Rating: low to high |
| `rating-desc-rank` | Rating: high to low |
| `ratings-asc-rank` | Review count: low to high |
| `ratings-desc-rank` | Review count: high to low |

**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:
```bash
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:

| User Says | Scenario |
|-----------|----------|
| "Find similar products to this image" | Basic image search |
| "Search by image", "reverse image search on Amazon" | Visual search |
| "Find competitor lookalikes", "find same-style products" | Competitor analysis by appearance |
| "What products on Amazon look like this" | Product discovery |
| "Find cheaper alternatives that look the same" | Price-based visual comparison |
| "Search Amazon JP/DE/UK for this product image" | Cross-marketplace visual search |
| "Show me Keepa data for similar products" | Run image search first, then use the appropriate Keepa skill for user-selected ASINs |
| "Find products similar to this photo, sorted by rating" | Sorted visual search |

**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](https://skill.linkfox.com/).*

© linkfox-ai · MIT · linkfox-ai/linkfox-skills

Similar skills

All skills for Browser and scraping →

From the same set31

linkfox-mpstats-ozon-product-trend Pulls a day-by-day series for a single Ozon listing: sales, price, stock, rating. Useful when you need to tell growth apart from a seasonal spike. CX Codex +1 414installs linkfox-mpstats-ozon-seller-products This skill pulls every product a given Ozon seller has, with sales, revenue, price, rating, stock, turnover and lost profit per SKU. CX Codex +1 413installs linkfox-walmart-search The skill searches and browses Walmart listings by keyword, category and price. Useful for price comparison and competitor research. CX Codex +1 410installs linkfox-multimodal-extract-attributes Runs product main images through a multimodal model and returns color, shape, material and style as structured fields. CX Codex +1 409installs linkfox-product-title-analyze Tokenizes product titles and counts word frequencies: scene, audience, material. Useful when you rewrite listings against competitors. CX Codex +1 408installs linkfox-ebay-search Searches active listings, auctions, and completed sales across regional eBay marketplaces with filters for condition, pricing, and formats. CX Codex +1 407installs linkfox-keepa-product-search A skill that queries Keepa to filter Amazon products by price, sales, BSR, reviews and package size. Useful for niche research and competitor checks. CX Codex +1 405installs linkfox-mpstats-ozon-brand-products Pulls every product a brand sells on Ozon with sales, price, rating and lost profit. Handy for auditing a competitor's shelf or your own. CX Codex +1 404installs

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor