This skill guides you on how to search and filter Amazon products using Keepa's extensive product database, helping Amazon sellers find products that match specific criteria across multiple dimensions.
Core Concepts
This tool provides advanced Amazon product search powered by Keepa data. Unlike a simple Amazon storefront search, it supports multi-criteria filtering: category, price range, monthly sales volume, BSR (Best Sellers Rank), keyword matching (positive and negative), review counts, ratings, package dimensions, weight, fulfillment type, historical sales rank, and more. It returns detailed product data including pricing, titles, images, listing dates, materials, weights, monthly sales for the past 12 months, and more.
BSR (Best Sellers Rank): A lower salesRank value means better sales performance. Rank 1 is the best-selling product in its category. When a user says "top-selling products", they want low BSR values.
Price unit: Prices are expressed in the smallest currency unit (e.g., cents for USD). So $25.99 = 2599. Always convert when building queries and when displaying results.
Category names: The categoriesIncludeNames parameter supports multi-level category paths separated by a colon : or the > character. Automatically convert user input into the correct format.
Parameters
Marketplace (Required)
| Parameter | Type | Required | Description | Default |
|---|---|---|---|---|
| domain | string | Yes | Amazon marketplace ID | - |
Domain ID mapping:
| ID | Marketplace |
|---|---|
| 1 | Amazon.com (United States) |
| 2 | Amazon.co.uk (United Kingdom) |
| 3 | Amazon.de (Germany) |
| 4 | Amazon.fr (France) |
| 5 | Amazon.co.jp (Japan) |
| 6 | Amazon.ca (Canada) |
| 8 | Amazon.it (Italy) |
| 9 | Amazon.es (Spain) |
| 10 | Amazon.in (India) |
| 11 | Amazon.com.mx (Mexico) |
Default marketplace is 1 (US). Use domain 1 when the user doesn't specify a marketplace.
Keyword Filtering
| Parameter | Type | Description |
|---|---|---|
| keyword | string | Title keyword filter (case-insensitive; space = AND; wrap phrases in double quotes; prefix with - to exclude; & is replaced by space; max 50 keywords, max 1000 chars) |
Category Filtering
| Parameter | Type | Description |
|---|---|---|
| rootCategory | array[int] | Root category IDs (max 50) |
| rootCategoryNames | array[string] | Root category names (max 50); used when rootCategory is empty; system auto-resolves IDs |
| categoriesInclude | array[int] | Sub-category IDs to include (max 50) |
| categoriesIncludeNames | array[string] | Sub-category names to include (max 50); supports full category paths with : or > separators |
| categoriesExclude | array[int] | Sub-category IDs to exclude (max 50) |
| categoriesExcludeNames | array[string] | Sub-category names to exclude (max 50); supports full category paths |
Sales & Ranking Filters
| Parameter | Type | Description |
|---|---|---|
| currentSalesGte | integer | Current BSR -- minimum (higher number = worse rank) |
| currentSalesLte | integer | Current BSR -- maximum (lower number = better rank) |
| avg90SalesGte | integer | 90-day average BSR -- minimum |
| avg90SalesLte | integer | 90-day average BSR -- maximum |
| deltaPercent90SalesGte | integer | 90-day BSR change percentage -- minimum |
| deltaPercent90SalesLte | integer | 90-day BSR change percentage -- maximum |
| monthlySoldGte | integer | Monthly sales units -- minimum |
| monthlySoldLte | integer | Monthly sales units -- maximum |
| srAvgGte | integer | Historical average BSR -- minimum (for a specific month) |
| srAvgLte | integer | Historical average BSR -- maximum (for a specific month) |
| srAvgMonth | string | Historical BSR month selection (format: YYYYMM, within last 36 months) |
Price Filters
| Parameter | Type | Description |
|---|---|---|
| currentNewGte | integer | Current new price -- minimum (smallest currency unit) |
| currentNewLte | integer | Current new price -- maximum (smallest currency unit) |
| currentBuyBoxShippingGte | integer | Current Buy Box price including shipping -- minimum (smallest currency unit) |
| currentBuyBoxShippingLte | integer | Current Buy Box price including shipping -- maximum (smallest currency unit) |
Review & Rating Filters
| Parameter | Type | Description |
|---|---|---|
| currentCountReviewsGte | integer | Review count -- minimum |
| currentCountReviewsLte | integer | Review count -- maximum |
| currentRatingGte | number | Rating -- minimum (0.0-5.0) |
| currentRatingLte | number | Rating -- maximum (0.0-5.0) |
Package & Dimensions Filters
| Parameter | Type | Description |
|---|---|---|
| packageLengthGte / packageLengthLte | integer | Package length range (mm) |
| packageWidthGte / packageWidthLte | integer | Package width range (mm) |
| packageHeightGte / packageHeightLte | integer | Package height range (mm) |
| packageWeightGte / packageWeightLte | integer | Package weight range (grams) |
Other Filters
| Parameter | Type | Description |
|---|---|---|
| brand | array[string] | Brand names (OR match) |
| color | array[string] | Colors (OR match) |
| size | array[string] | Sizes (OR match) |
| availableDateGte / availableDateLte | string | Listing date range (yyyy-MM-dd) |
| buyBoxIsAmazon | boolean | Buy Box seller is Amazon |
| buyBoxIsFBA | boolean | Buy Box is FBA fulfilled |
| isHazMat | boolean | Hazardous material flag |
| variationCountGte / variationCountLte | integer | Variation count range |
| currentCountNewGte / currentCountNewLte | integer | Number of new offers range |
| outOfStockPercentage90Gte / outOfStockPercentage90Lte | integer | 90-day out-of-stock percentage range |
| singleVariation | boolean | Return only one variation per parent ASIN |
| productType | array[int] | Product types: 0=standard, 1=downloadable, 2=ebook, 5=variation parent |
Data Options
| Parameter | Type | Description | Default |
|---|---|---|---|
| history | integer | Include historical data (price history, sales rank, monthly sales per month) | 0 (no) |
| rating | integer | Include rating info | 1 (yes) |
Pagination & Sorting
| Parameter | Type | Description | Default |
|---|---|---|---|
| page | integer | Page number (starting from 1) | 1 |
| perPage | integer | Results per page (min 50, max 100) | 50 |
| sort | array[object] | Sort rules (max 3); each object: `{"fieldName": "...", "sortDirection": "asc | desc"}` |
Sortable fields: availableDate, currentSales, monthlySold, currentRating, currentCountReviews, currentBuyBoxShipping, currentNew
How to call
- API endpoint：
POST /keepa/productSearch(for full parameters/responses/error codes, seereferences/api.md） - Python script：
python scripts/keepa_product_search.py '<JSON 参数>' [--inline] - Cost constraints: This tool consumes compute; by default, the same parameter combination is called only once per session, and the script has a 24h local cache. On failure/empty results, do not automatically try different keywords, paginate, or change the zip code in continuous probing; if further retrieval is needed, first explain to the user that additional consumption will be incurred.
Output strategy (default script behavior)：
- Alwayswrite the full response to
<cwd>/linkfox/<YYYY-MM-DD>/<session>/data/linkfox-keepa-product-search-<timestamp>.json（<cwd>is the working directory when the script is executed, which in Claude Code is the current project directory;<session>is taken from the environment variableSESSION_ID, automatically aggregated according to the user's task;writing to /tmp is prohibited, and if the current directory is not writable, report an error) - Response body ≤ 8 KB: after writing to disk, print the full JSON to stdout
- Response body > 8 KB: after writing to disk, stdout outputs only a summary (top-level fields, common counts such as
total/costToken, the length of the largest list field + the first 3 samples) - Add
--inlineto force full printing to stdout (also written to disk)
Data reading suggestions: First look at the summary to determine whether it is sufficient; when specific fields are needed, prefer to use jqorConvertFrom-Json to extract on demand from the saved json file, avoiding bringing the entire JSON into context.
Resolve authentication and compute issues
When the following abnormal situations occur, use references/onboarding.md to guide problem resolution:
Abnormal situations
- API Key not configured: the environment variable is not configured
LINKFOX_AGENT_API_KEY, andLINKFOXAGENT_API_KEY。 - Response 401 or 402 status code
- Response indicates insufficient compute or balance: the message contains "insufficient compute balance/insufficient billing/insufficient balance/quota exceeded/insufficient balance/package expired/recharge required/please recharge", or content with a similar meaning.
How to Build Queries
Construct the request parameters based on the user's intent:
- Determine the marketplace: Map the user's target country to the correct
domainID value - Set keyword filters: Use
keywordfor title-based filtering with positive and negative terms - Set category scope: Use
categoriesIncludeNamesorrootCategoryNamesto scope by category; convert user input into proper category path format - Apply numeric filters: Map sales volume, price, BSR, review, and rating requirements to the appropriate Gte/Lte parameters
- Set sort order: If the user wants results sorted by sales, price, or rating, configure the
sortarray - Enable historical data: Set
historyto1if the user needs monthly sales trends or price history
Usage Examples
1. Search for electronics with monthly sales over 1000 on US marketplace
{"domain": "1", "rootCategoryNames": ["Electronics"], "monthlySoldGte": 1000}
2. Find products in a price range with good ratings
{"domain": "1", "currentBuyBoxShippingGte": 1500, "currentBuyBoxShippingLte": 5000, "currentRatingGte": 4.0, "keyword": "wireless charger"}
3. New products listed in the last 6 months with low review counts
{"domain": "1", "availableDateGte": "2025-10-01", "currentCountReviewsLte": 50, "monthlySoldGte": 500}
4. BSR rank filtering for competitive analysis
{"domain": "1", "categoriesIncludeNames": ["Home & Kitchen"], "currentSalesLte": 5000, "sort": [{"fieldName": "monthlySold", "sortDirection": "desc"}]}
5. Find non-Amazon FBA products with good sales
{"domain": "1", "buyBoxIsAmazon": false, "buyBoxIsFBA": true, "monthlySoldGte": 300, "currentRatingGte": 4.0}
6. Lightweight small products for easy shipping
{"domain": "1", "packageWeightLte": 500, "packageLengthLte": 200, "packageWidthLte": 150, "packageHeightLte": 100, "monthlySoldGte": 200}
7. Search on Japan marketplace with historical data
{"domain": "5", "keyword": "USB charger", "history": 1, "monthlySoldGte": 100}
8. Brand-specific search excluding hazardous materials
{"domain": "1", "brand": ["Anker", "UGREEN"], "isHazMat": false, "sort": [{"fieldName": "monthlySold", "sortDirection": "desc"}]}
Display Rules
- Present data clearly: Show search results in well-structured tables with key fields: ASIN, title, price, BSR, monthly sales, rating, review count, brand
- Price conversion: Convert prices from smallest currency unit to standard format (e.g., 2599 -> $25.99)
- BSR clarification: When showing BSR data, remind users that lower values mean better sales ranking
- Monthly sales history: When historical data is included, present the 12-month sales trend clearly
- Pagination notice: Inform users of the total result count and suggest fetching additional pages if needed
- Image links: If image URLs are available, mention them but do not attempt to render them inline unless the user requests it
- Error handling: When a query fails, explain the reason and suggest adjusting filter criteria
Important Limitations
- Result cap: Maximum 100 results per page, minimum 50
- Sort limit: Maximum 3 sort rules per query
- Category limit: Maximum 50 category IDs or names per filter
- Keyword limit: Maximum 50 keywords in keyword parameter
- Historical data cost: Setting
history=1increases response size and token cost significantly - Price unit: All price values are in the smallest currency unit (cents, pence, etc.)
User Expression & Scenario Quick Reference
Applicable -- Multi-criteria Amazon product search and filtering:
| User Says | Scenario |
|---|---|
| "Find products with monthly sales over X" | Sales volume filtering |
| "Search for products in XX category" | Category-based product discovery |
| "Products with BSR under X" | Sales rank filtering |
| "New products listed in the last N months" | New product discovery |
| "Products priced between $X and $Y" | Price range filtering |
| "FBA products with good ratings" | Fulfillment + rating filter |
| "Lightweight products under X grams" | Package dimension filtering |
| "Products from brand XX" | Brand-specific search |
| "Show me historical sales data for XX" | Historical sales analysis |
| "Advanced product selection", "product screening" | Multi-criteria product research |
| "Niche product hunting", "find low-competition products" | Competitive gap analysis |
| "BSR trends", "sales rank history" | Historical rank filtering |
Not applicable -- Needs beyond product search:
- Real-time Amazon search result page simulation (use Amazon Search)
- Historical search term volume or ranking trends (use ABA data)
- Product review content or sentiment analysis
- Advertising campaign management or bid optimization
- Listing optimization or copywriting suggestions
- Inventory or supply chain data
Boundary judgment: When users say "product research" or "find products", if it involves filtering by sales metrics, BSR, price, category, and other structured criteria, this skill applies. If they want to see what appears on the actual Amazon search page for a keyword, use Amazon Search instead. If they want search term analytics, use ABA data.
Compute consumption rules
Billed according to dynamic rules: compute consumed = 0.045 × (Keepa tokens consumed in the product-finding stage + Keepa tokens consumed in the product-detail retrieval stage). First find products, then retrieve product details; if no product is found in the first stage, only the consumption of the product-finding stage is counted.
Important: The service of this skill is dynamically calculated by a multiplier and may consume a large amount of compute at once. The user must be reminded, and the user decides whether to continue.
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 references/api.md. Do not interrupt the user's flow.
For more high-quality, professional cross-border e-commerce skills, set LinkFox Skills.