This skill guides you on how to retrieve Amazon product details via the Keepa product request API, helping Amazon sellers and analysts obtain structured product data for one or more ASINs across multiple Amazon marketplaces.
Core Concepts
The Keepa Product Request API returns detailed product listing data from Amazon, sourced through Keepa. Given one or more ASINs and a marketplace, it returns comprehensive product information: pricing, title, main image, listing date, material, weight, dimensions, sales rank, monthly sales units (current and up to 12 months of history), FBA fees, ratings, review counts, category tree, and more.
Key points:
- You can query up to 100 ASINs in a single request by separating them with commas.
- The
domainparameter is a numeric marketplace ID (e.g.,1= Amazon.com US), not a country code. - Setting
historyto1includes historical sales data (monthly sales for up to 12 prior months, average sales rank over 30/90/180 days). Setting it to0returns only current product information. - The response does not include product descriptions or reviews content.
Parameter Guide
domain (Required)
Numeric Amazon marketplace ID. The mapping is:
| Domain ID | Marketplace |
|---|---|
| 1 | Amazon.com (US) |
| 2 | Amazon.co.uk (UK) |
| 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) |
| 12 | Amazon.com.br (Brazil) |
Default to 1 (US) when the user does not specify a marketplace.
asin (Required)
One or more Amazon Standard Identification Numbers. For multiple ASINs, separate with commas. Maximum 100 ASINs per request, with a total string length limit of 3000 characters.
history (Optional)
Whether to include historical data such as monthly sales for the past 12 months and average sales rank over 30/90/180 days. Set to 1 to include history, 0 (default) for basic info only.
Usage Examples
1. Single ASIN lookup (US marketplace, basic info)
{"asin": "B0088PUEPK", "domain": "1"}
2. Single ASIN with historical sales data
{"asin": "B0088PUEPK", "domain": "1", "history": 1}
3. Batch lookup of multiple ASINs (Germany)
{"asin": "B0088PUEPK,B00U26V4VQ,B07M68S376", "domain": "3", "history": 1}
4. Product lookup on Amazon Japan
{"asin": "B09V3KXJPB", "domain": "5", "history": 0}
5. Competitor comparison across multiple ASINs (US, with sales history)
{"asin": "B0CXYZ1234,B0CXYZ5678,B0CXYZ9012,B0CXYZABCD", "domain": "1", "history": 1}
API Usage
This tool calls the LinkFox tool gateway API. See references/api.md for calling conventions, request parameters, and response structure. You can also execute scripts/keepa_product_detail.py directly to run queries.
Display Rules
- Present data clearly: Show product details in well-structured tables. Group related fields (e.g., dimensions together, sales data together) for readability.
- Price and currency: Always display the price alongside its currency (e.g., "$29.99 USD"). The
currencyfield in the response indicates the local currency. - Sales trend: When historical data is included, present the 12-month sales trend in a table or describe the trajectory (growing, declining, stable) to help users quickly assess momentum.
- Dimensions and weight: Convert millimeter values to more intuitive units when appropriate (e.g., show both mm and inches, or mm and cm). Note that weight is in grams.
- Unavailable data: Fields with value
0or-1indicate data is unavailable. Do not display these as actual measurements; instead note "N/A" or omit them. - Image display: If
imageUrlis present, display the product image to help users visually identify the product. - Error handling: When a query fails, explain the issue based on the response and suggest corrections (e.g., invalid ASIN format, unsupported marketplace).
- Large batch results: For batch queries with many ASINs, present a summary table first and offer to show individual product details on request.
Important Limitations
- No product descriptions or reviews: The API does not return product description text or review content.
- Maximum 100 ASINs per request: Batch queries are capped at 100 ASINs.
- ASIN string length limit: The
asinparameter has a maximum length of 3000 characters. - Historical data is optional: Monthly sales history is only returned when
historyis set to1. - Data freshness: The
lastUpdatefield indicates when the product data was last refreshed.
User Expression & Scenario Quick Reference
Applicable -- Product data retrieval by ASIN:
| User Says | Scenario |
|---|---|
| "Look up this ASIN", "Get product details for B0XXXXXXXX" | Single ASIN lookup |
| "What's the price of this product on Amazon" | Price query |
| "How many units does this product sell per month" | Monthly sales check |
| "Compare these ASINs", "batch lookup these products" | Multi-ASIN comparison |
| "Show me the sales trend for this ASIN" | Historical sales analysis |
| "What category is this product in" | Category / classification lookup |
| "Product dimensions", "how much does it weigh" | Physical specs query |
| "FBA fees for this product" | Fee estimation |
| "When was this product listed", "listing date" | Listing age / launch date |
| "Is this product FBA or FBM" | Fulfillment method check |
Not applicable -- Needs beyond ASIN-level product data:
- Search term / keyword analysis (use ABA data tools instead)
- Product reviews or listing copywriting content
- Advertising / PPC campaign data
- Seller account or store-level analytics
- Product research without specific ASINs (e.g., "find trending products in kitchen category")
- Price history charts or Buy Box history over time (only current and average rank data are available)
Boundary judgment: When users say "product research" or "competitor analysis", if they have specific ASINs and want structured product data (price, sales, dimensions, category), this skill applies. If they want keyword-level analysis, market-wide trends without specific ASINs, or advertising metrics, this skill does not apply.
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.
Handling Large Responses
To avoid overflowing the agent context, persist the response to disk and extract only the fields you need:
python scripts/response_io.py run --script scripts/keepa_product_detail.py --out-dir <DIR> '<params>'
python scripts/response_io.py read <file> --fields "<paths>" # or --path "<JMESPath>"
Pick
--out-diroutside any git working tree (e.g./tmp/...on Unix,%TEMP%/...on Windows). Persisted responses may contain PII, pricing, or auth-sensitive data — do not commit them. Files are not auto-deleted; clean up when the task is done.
run writes the full response to a file and emits only a schema preview + file path. read projects specific fields, with --limit/--offset for slicing and --format json|jsonl|csv|table for output.
When to prefer this pattern — apply your judgment based on the response characteristics, e.g.:
- High field count per record, or fields you don't need
- Batch/paginated results (multiple items per call)
- Long-text fields (descriptions, reviews, HTML, time series)
- Output reused across later steps rather than consumed immediately
For small, single-use responses, calling the main script directly is fine.
⚠️ The preview is a truncated schema + sample, not the full data. Any field-level decision must read from the persisted file via read.
For more high-quality, professional cross-border e-commerce skills, set LinkFox Skills.