This skill guides you on how to search and filter Amazon products via Sorftime across multiple dimensions, helping Amazon sellers discover products, analyze competitors, and explore market opportunities.
Core Concepts
Sorftime Product Search supports multi-dimensional product retrieval with 16 query types, single or multi-condition AND combinations, and historical monthly snapshot lookback from January 2024. Data covers pricing, BSR rankings, monthly sales, FBA fees, and profit analysis.
Key differentiator: This tool is for searching and filtering across products. If you need detailed trend data (sales/price/BSR history) for a specific ASIN, use the Sorftime Product Detail skill instead.
Data Fields
Response data covers the following categories (see references/api.md for complete field reference):
- Basic info: ASIN, title, brand, listing URL, images (main + list), parent ASIN, variation count, weight, size
- Pricing & profit: current price, sale price (after coupon), strikethrough price, coupon, FBA fees (with detail breakdown), platform fee, profit amount & rate
- Sales: monthly sales units, monthly revenue, daily sales, daily revenue (values of -1 = cannot estimate)
- Rankings: BSR rank, category, sub-category rankings
- Ratings: rating score, rating count
- Listing info: listing date, days online
- Seller: Buybox seller name/ID/country, FBA status, seller count
- Listing features: A+ content, video, brand store
Supported Marketplaces
US (United States), GB (United Kingdom), DE (Germany), FR (France), IN (India), CA (Canada), JP (Japan), ES (Spain), IT (Italy), MX (Mexico), AE (United Arab Emirates), AU (Australia), BR (Brazil), SA (Saudi Arabia)
Default marketplace is US. Use us when the user doesn't specify a marketplace.
Note: Sorftime uses lowercase codes (e.g., us, gb, de), and UK is coded as gb (not uk).
How to call
- API endpoint：
POST /sorftime/amazon/productQuery(For complete parameters/responses/error codes, seereferences/api.md） - Python script：
python scripts/sorftime_product_search.py '<JSON 参数>' [--inline] - Cost constraints: This tool consumes compute; by default, the same parameter combination in the same session is called only once, and the script has a 24h local cache. On failure/empty results, do not automatically switch keywords, paginate, or change zip codes to probe continuously; if continued retrieval is needed, first explain to the user that it will incur additional consumption.
Output strategy (script default behavior)：
- Alwayswrite the complete response to
<cwd>/linkfox/<YYYY-MM-DD>/<session>/data/linkfox-sorftime-amazon-product-query-<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, if the current directory is not writable, report an error) - Response body ≤ 8 KB: after writing to disk, print the complete 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 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
The key parameters are marketplace (required), queryMode, queryType, and queryValue. The query system has two modes and 16 filter types that can be combined flexibly.
Principles for Building Queries
- Always specify the marketplace: Use lowercase site codes, e.g.,
us,de,jp - Choose the right query mode: Use
queryMode=1for a single filter; usequeryMode=2to combine multiple filters with AND logic - Match queryType with queryValue format: Each queryType expects a specific format - see the table below. Mismatched formats will cause errors
- Mind price units: Price filters (queryType=8) use smcurrency unit (cents for USD), so $19.99 =
1999 - Use open ranges when appropriate: Omit one end for open range -
,1000means "up to 1000";100,means "100 or more" - Use queryMonth for historical comparison: Format
yyyy-MM; compare with a second call without queryMonth to see changes over time
Query Types (queryType, for queryMode=1)
| queryType | Name | queryValue Format | Example |
|---|---|---|---|
| 1 | ASIN Similar | ASIN | B0CVM8TXHP |
| 2 | Category | NodeId | 3743561 |
| 3 | Brand | Brand name | Anker |
| 4 | Seller Name | Store name | AnkerDirect |
| 5 | Seller ID | SellerId | A294P4X9EWVXLJ |
| 6 | ABA Keyword | Keyword | Power Bank |
| 7 | Title/Attribute Match | Keywords | 10,000mAh 30W |
| 8 | Price Range | min,max (in cents) |
1,1000 (=$0.01~$10) |
| 9 | Monthly Sales Range | min,max |
100,1000 |
| 10 | Seasonal Products | Month list | 1,2,3 (peak in Jan-Mar) |
| 11 | Listing Date Range | start,end (yyyy-MM-dd) |
2024-06-01,2024-12-01 |
| 12 | Rating Range | min,max |
3,5 |
| 13 | Review Count Range | min,max |
10,500 |
| 14 | Rank Range | bsr_min,bsr_max;sub_min,sub_max |
500,5000;1,100 |
| 15 | Fulfillment | FBA / FBM |
FBA,FBM |
| 16 | Variation Count | min,max |
1,50 |
Important: queryType=1 (ASIN Similar) finds products similar to the given ASIN, not the ASIN itself. To query a single product's detail, use the Sorftime Product Detail skill.
Historical Snapshots (queryMonth)
Set queryMonth (format yyyy-MM) to query a past month's product data snapshot. This lets users compare historical prices, rankings, and sales with current data.
- Supported range: January 2024 to present (~2 years)
- US, GB, DE support full "unlimited" lookback mode
- Other sites support Top 100 products only in lookback
- AU, BR, IN do not support lookback
Query Examples for Common Scenarios
1. Fititors of a given ASIN
queryMode: 1, queryType: 1, queryValue: B0CVM8TXHP, marketplace: us
2. Browse a category's top products
queryMode: 1, queryType: 2, queryValue: 3743561, marketplace: us
3. Analyze a brand's product portfolio
queryMode: 1, queryType: 3, queryValue: Anker, marketplace: us
4. Search by ABA keyword
queryMode: 1, queryType: 6, queryValue: Power Bank, marketplace: us
5. Discover seasonal products (Q4 peak)
queryMode: 1, queryType: 10, queryValue: 10,11,12, marketplace: us
6. Compare historical vs current data
queryMonth: 2024-11, queryMode: 1, queryType: 2, queryValue: 3743561, marketplace: us
-> Compare with current data (no queryMonth) to see price/sales changes
7. Multi-condition: new FBA products with good sales
queryMode: 2
queryValue: [{"QueryType":11,"Content":"2024-06-01,"},{"QueryType":9,"Content":"300,"},{"QueryType":15,"Content":"FBA"}]
marketplace: us
8. Find low-price high-sales products
queryMode: 2
queryValue: [{"QueryType":8,"Content":",2000"},{"QueryType":9,"Content":"500,"}]
marketplace: us
9. Check a seller's product portfolio
queryMode: 1, queryType: 4, queryValue: AnkerDirect, marketplace: us
Display Rules
- Present data only: Show query results in clear tables without subjective business advice
- Ranking clarification: When showing ranking data, remind users that lower values mean better rankings
- Pagination notice: Search results return max 100 products per page, up to 200 pages. If results are large, show highlights and remind users to paginate
- Sales estimation caveat: Values of
-1in sales/revenue fields mean "cannot estimate" - explain this to the user rather than showing -1 directly - Error handling: When a query fails, explain the reason based on the
msgfield and suggest adjusting query criteria
Important Limitations
- Pagination: Max 100 products per page, max 200 pages
- **Historisupported
- Non-structured data: Results do not support secondary analysis via
_dataQuery_executeDynamicQuery - Sales estimation: Products in non-standard categories may return -1 for sales fields
- ABA keyword search (queryType=6): Currently only supports ABA keywords, not arbitrary search terms
User Expression & Scenario Quick Reference
Applicable - Product search and filtering on Amazon:
| User Says | Scenario |
|---|---|
| "Find products that sell well in this category" | Category exploration |
| "What best-selling products does the Anker brand have" | Brand analysis |
| "What are the competitors of this ASIN" | Competitor discovery |
| "Help me find some seasonal products" | Seasonal product discovery |
| "Which new products have monthly sales over 500" | Filtered product discovery |
| "The price snapshot of this category during last year's Double 11" | Historical snapshot comparison |
| "What other products has this seller sold" | Seller portfolio |
| "Help me filter FBA products with a profit margin higher than 30%" | Profit-focused filtering |
| "Products with monthly sales above 1000 and a rating above 4 stars" | Multi-condition filtering |
| "Products whose title contains wireless charger" | Title keyword search |
Not applicable - Needs beyond product search:
- Detailed trend/history data for a specific ASIN (use Sorftime Product Detail)
- ABA search term ranking data (use ABA Data Explorer)
- Advertising / PPC strategy
- Product reviews content analysis
- Patent or trademark checks
Boundary judgment: When users say "competitor analysis" or "market research", if they need to discover and compare products across dimensions (category, brand, price range, etc.), this skill applies. If they need historical trend curves for a specific ASIN, use the Prt Detail skill. If they need keyword search volume data, use ABA Data Explorer.
Compute consumption rules
Billed according to dynamic rules: compute consumed = number of Sorftime internal queries × 6. Number of Sorftime internal queries: different query conditions may require different numbers of queries, and this number is determined by Sorftime.
Important: The service for this skill is dynamically calculated by multiples and may consume a large amount of computing power 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, visit LinkFox Skills.