SellerSprite Product Search

This skill guides you on how to search, filter, and analyze Amazon product data via the SellerSprite product database, helping Amazon sellers make data-driven product selection decisions.

Core Concepts

SellerSprite Product Search provides access to a comprehensive Amazon product database with rich filtering dimensions. It supports real-time data (last 30 days) as well as monthly historical snapshots for year-over-year and month-over-month comparisons. Supported marketplace codes are only: US, UK, DE, FR, JP, CA, IT, ES, MX, and IN (same as the gateway schema).

BSR (Best Sellers Rank): A lower BSR value means better sales performance in its category. A BSR of 1 means the top-selling product in that category. When a user says "BSR improved", it means the numeric value decreased; "BSR dropped" means the value increased.

Data snapshot: The dataSnapshotMonth parameter controls which time period to query. Use nearly (the default) for real-time last-30-day data, or a yyyyMM string (e.g., 202412) to query a historical monthly snapshot. This is useful for seasonal analysis and year-over-year comparison.

Match types for keywords: When searching by keyword, three matching strategies are available:

• Phrase match (default): Product titles must contain the keyword phrase
• Fuzzy match: Broader matching with related terms
• Exact match: Strict exact-string matching

Parameter Guide

Search & Filtering

Price & Financials

Sales & Ranking

Reviews & Ratings

Product Attributes

Badges & Fulfillment

Seller & Brand

Listing & Pagination

Sorting

Use the order object with two fields:

Default sort: total_units descending.

Optional gateway / session fields

If the hosting environment supplies them, you may pass chatId, uid, requestId, and teamId as strings (see references/api.md). They are not required for ad-hoc script calls.

调用方式

• API 端点：POST /sellersprite/productSearch（完整参数/响应/错误码见 references/api.md）
• Python 脚本：python scripts/sellersprite_product_search.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-sellersprite-product-search-<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。

Usage Examples

1. Find high-sales products in a niche Search for products with keyword "yoga mat" in the US marketplace with monthly sales above 500 units, sorted by monthly sales descending.

{
  "keyword": "yoga mat",
  "marketplace": "US",
  "minUnits": 500,
  "order": {"field": "total_units", "desc": "true"}
}

2. Discover new product opportunities with low competition Find recently listed products (within 6 months) in the US with fewer than 50 ratings and monthly revenue above $5,000.

{
  "keyword": "desk organizer",
  "marketplace": "US",
  "listedWithinLastMonths": 6,
  "maxRatings": 50,
  "minRevenue": 5000,
  "order": {"field": "total_units", "desc": "true"}
}

3. Product improvement opportunity mining Find products with ratings between 3.8 and 4.3 (improvement sweet spot), monthly sales above 300, in a specific category.

{
  "keyword": "phone case",
  "marketplace": "US",
  "minRating": 3.8,
  "maxRating": 4.3,
  "minUnits": 300,
  "order": {"field": "total_units", "desc": "true"}
}

4. High-margin product screening Find products with gross margin above 40%, price between $15 and $50, at least 100 monthly sales.

{
  "marketplace": "US",
  "minProfit": 40,
  "minPrice": 15,
  "maxPrice": 50,
  "minUnits": 100,
  "order": {"field": "profit", "desc": "true"}
}

5. Seasonal year-over-year comparison Query last year's December snapshot data to compare with current data for seasonal product planning.

{
  "keyword": "christmas lights",
  "marketplace": "US",
  "dataSnapshotMonth": "202412",
  "minUnits": 200,
  "order": {"field": "total_units", "desc": "true"}
}

6. Chinese seller competitive landscape Find FBA-fulfilled products from Chinese sellers in a category with high monthly sales.

{
  "keyword": "bluetooth speaker",
  "marketplace": "US",
  "sellerNation": "CN",
  "fulfillment": "FBA",
  "minUnits": 200,
  "order": {"field": "total_units", "desc": "true"}
}

7. Best Seller & Amazon's Choice badge holders Find products carrying the Best Seller badge with strong sales performance.

{
  "keyword": "water bottle",
  "marketplace": "US",
  "badgeBestSeller": "Y",
  "order": {"field": "total_units", "desc": "true"}
}

8. Fast-growing products by sales growth rate Find products with monthly sales growth rate above 50%.

{
  "keyword": "standing desk",
  "marketplace": "US",
  "minUnitsGrowthRate": 50,
  "order": {"field": "total_units_growth", "desc": "true"}
}

Display Rules

1. Present data clearly: Show query results in well-structured tables. Key columns to prioritize: ASIN, title, price, monthly sales, monthly revenue, BSR rank, rating, ratings count, gross margin, fulfillment type
2. BSR clarification: When showing BSR data, remind users that lower values mean better rankings
3. Gross margin note: Gross margin values are percentages. Remind users this is an estimate based on price minus FBA fees and estimated costs
4. Pagination awareness: When the total count exceeds the returned page size, inform the user of the total result count and suggest adjusting page or size only within the first 2,000 records. If total exceeds 2,000, clearly state that records after the first 2,000 cannot be queried and suggest narrowing the filters
5. Snapshot labeling: When displaying historical snapshot data, clearly label the data period (e.g., "Data from December 2024 snapshot") to avoid confusion with real-time data
6. Error handling: When a query fails, explain the reason based on the message field and suggest adjusting query criteria
7. Weight unit reminder: When the user provides weight filters without specifying a unit, ask them to confirm the weight unit (g, kg, oz, or lb) before proceeding
8. Keyword translation: When the user provides keywords in a language different from the target marketplace, translate the keyword to the appropriate language and note the translation

Important Limitations

• Result cap: Each page returns 10-100 records, and pagination can query only the first 2,000 records in the sorted result set (page * size must not exceed 2,000). Narrow the filters to reach records outside that window
• Historical snapshots: Only past monthly snapshots are available; future dates are not supported
• Weight unit required: If any weight filter is used, the weightUnit must also be provided
• Subcategory BSR: The subcategory BSR rank filters only work when filterSubNode is set to true
• Listed time enum only: The listedWithinLastMonths parameter only accepts specific values: 1, 3, 6, 12, or 24
• Child ASIN 30-day sales filters: minAmzUnit / maxAmzUnit apply only to last-30-day style queries (typically dataSnapshotMonth: "nearly"); do not rely on them for historical yyyyMM snapshots

User Expression & Scenario Quick Reference

Applicable -- Product-level data queries on Amazon:

Not applicable -- Needs beyond product-level search data:

• ABA search term / keyword analysis (use ABA Data Explorer instead)
• Advertising / PPC campaign data
• Product review text analysis
• Listing copywriting or optimization
• Supplier sourcing or manufacturing costs
• Logistics and inventory planning

Boundary judgment: When users say "product research" or "market analysis", if it boils down to filtering Amazon products by sales, price, BSR, ratings, and other product attributes, then this skill applies. If they are asking about keyword search volume, search term rankings, or click/conversion share data, the ABA Data Explorer skill is more appropriate.

算力消耗规则

消耗 15 算力。

用户会因算力消耗而支付费用。请充分评估：当需要高频调用本技能，或用户对算力消耗量预期不足时，务必提醒用户，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.