This skill guides you on how to perform Amazon storefront search simulations, helping Amazon sellers retrieve real-time search result data including product rankings, prices, ratings, and more.
Core Concepts
This tool simulates a real user searching on Amazon's storefront. It returns live search result page (SERP) data: product listings with their positions, prices, ratings, review counts, brands, delivery info, sponsored flags, and more. This is real-time data directly from the Amazon frontend, not historical analytics.
Key distinction from ABA data: ABA data is aggregated historical search term analytics. This tool returns the actual product listings a user would see when searching a keyword on Amazon right now.
Keyword language: Keywords should be in the language of the target marketplace. For example, use English keywords for amazon.com, German keywords for amazon.de, Japanese keywords for amazon.co.jp, etc.
Parameters
| Parameter | Type | Required | Description | Default |
|---|---|---|---|---|
| keyword | string | No | Search keyword (translate to the target marketplace's language) | - |
| amazonDomain | string | No | Amazon marketplace domain | amazon.com |
| node | string | No | Amazon category node ID for category-scoped searches | - |
| language | string | No | Language locale code (e.g., en_US, de_DE, ja_JP) | - |
| sort | string | No | Sort order for results | relevanceblender |
| page | integer | No | Page number (starting from 1, ~20 results per page) | 1 |
| deliveryZip | string | No | Postal/zip code for delivery location simulation | - |
| device | string | No | Device type: desktop, mobile, or tablet | desktop |
Supported Marketplaces
| Domain | Country |
|---|---|
| amazon.com | United States |
| amazon.co.uk | United Kingdom |
| amazon.de | Germany |
| amazon.fr | France |
| amazon.it | Italy |
| amazon.es | Spain |
| amazon.co.jp | Japan |
| amazon.ca | Canada |
| amazon.com.au | Australia |
| amazon.com.br | Brazil |
| amazon.in | India |
| amazon.nl | Netherlands |
| amazon.se | Sweden |
| amazon.pl | Poland |
| amazon.sg | Singapore |
| amazon.sa | Saudi Arabia |
| amazon.ae | United Arab Emirates |
| amazon.com.mx | Mexico |
| amazon.com.tr | Turkey |
| amazon.com.be | Belgium |
| amazon.cn | China |
| amazon.eg | Egypt |
Default marketplace is amazon.com. Use amazon.com when the user doesn't specify a marketplace.
Sort Options
| Value | Description |
|---|---|
| relevanceblender | Featured / Relevance (default) |
| price-asc-rank | Price: Low to High |
| price-desc-rank | Price: High to Low |
| review-rank | Average Customer Review |
| date-desc-rank | Newest Arrivals |
| exact-aware-popularity-rank | Best Sellers |
How to Call
- API Endpoint：
POST /amazon/search(For full parameters/response/error codes, seereferences/api.md） - Python Script：
python scripts/amazon_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 consecutive probes by changing keywords, paging, or changing the zip code; if further retrieval is needed, first explain to the user that additional consumption will be incurred.
Output Strategy (Script Default Behavior)：
- Alwayswrite the full response to
<cwd>/linkfox/<YYYY-MM-DD>/<session>/data/linkfox-amazon-search-<timestamp>.json（<cwd>is the working directory when the script runs, which in Claude Code is the current project directory;<session>is taken from the environment variableSESSION_ID, automatically aggregated according to the user task;writing to /tmp is prohibited, and if the current directory is not writable, report an error) - Response body ≤ 8 KB: after saving to disk, print the full JSON to stdout
- Response body > 8 KB: after saving to disk, stdout outputs only a summary (top-level fields, common counts such as
total/costToken, length of the largest list field + first 3 samples) - Add
--inlineto force full printing to stdout (also saved to disk)
Data Reading Suggestions: First look at the summary to determine whether it is sufficient; when specific fields are needed, prioritize using jqorConvertFrom-Json to extract on demand from the saved json file, avoiding putting the entire JSON into the context.
Resolve Authentication and Compute Issues
When the following exceptional situations occur, use references/onboarding.md to guide resolution:
Exceptional Situations
- API Key not configured: The environment variable is not configured
LINKFOX_AGENT_API_KEY, and neither isLINKFOXAGENT_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 similar meanings.
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
amazonDomainvalue - Set the keyword: Translate the search term into the target marketplace's language
- Choose sort order: If the user wants results sorted by price, reviews, or newness, set the
sortparameter - Pagination: Use the
pageparameter to fetch additional result pages if needed - Category scope: If the user wants to search within a specific category, provide the
nodeparameter - Delivery simulation: Use
deliveryZipto see location-specific availability and delivery info
Usage Examples
1. Basic keyword search on US marketplace
{"keyword": "wireless earbuds", "amazonDomain": "amazon.com"}
2. Search on German marketplace with German keyword
{"keyword": "kabellose Kopfhoerer", "amazonDomain": "amazon.de", "language": "de_DE"}
3. Search sorted by price (low to high)
{"keyword": "phone case", "amazonDomain": "amazon.com", "sort": "price-asc-rank"}
4. Search for best sellers in a category
{"keyword": "yoga mat", "amazonDomain": "amazon.com", "sort": "exact-aware-popularity-rank"}
5. Search for newest arrivals on Japan marketplace
{"keyword": "USB充電器", "amazonDomain": "amazon.co.jp", "language": "ja_JP", "sort": "date-desc-rank"}
6. Multi-page search to analyze deeper results
{"keyword": "laptop stand", "amazonDomain": "amazon.com", "page": 2}
7. Mobile device search simulation
{"keyword": "running shoes", "amazonDomain": "amazon.com", "device": "mobile"}
8. Category-scoped search with delivery zip
{"keyword": "office chair", "amazonDomain": "amazon.com", "deliveryZip": "10001"}
Display Rules
- Present data clearly: Show search results in well-structured tables with key fields: position, ASIN, title, price, rating, review count, brand
- Highlight sponsored products: Clearly mark which results are sponsored ads vs organic listings
- Price formatting: Display prices with the correct currency symbol for the marketplace
- Position context: Remind users that position reflects the actual ranking on the search result page
- Pagination notice: When results span multiple pages, inform the user how many total results were found and suggest fetching additional pages if needed
- Error handling: When a query fails, explain the reason based on the error response and suggest adjusting parameters
- Image links: If image URLs are available, mention them but do not attempt to render them inline unless the user requests it
Important Limitations
- Real-time only: This tool returns live search results, not historical data. For historical search term analytics, use ABA data instead
- Rate awareness: Each call simulates a real search request; avoid excessive rapid-fire calls
- ~20 results per page: Each page returns approximately 20 product listings
- Keyword language matters: Results quality depends on using the correct language for the target marketplace
User Expression & Scenario Quick Reference
Applicable -- Real-time Amazon search result queries:
| User Says | Scenario |
|---|---|
| "Search for XX on Amazon" | Basic product search |
| "What products appear for keyword XX" | Keyword SERP analysis |
| "Where does my ASIN rank for XX keyword" | Position / ranking check |
| "Show me the top results for XX" | Competitive landscape |
| "What's the price range for XX" | Price comparison |
| "Any sponsored products for XX keyword" | Sponsored ad analysis |
| "New products for XX keyword" | New arrival monitoring |
| "Search XX on Amazon Germany/Japan/UK" | Cross-marketplace search |
| "What are the best sellers for XX" | Best seller discovery |
| "Compare search results on mobile vs desktop" | Device-specific SERP |
Not applicable -- Needs beyond real-time search results:
- Historical search term volume or ranking trends (use ABA data)
- Advertising campaign management or bid optimization
- Product review analysis or sentiment analysis
- Sales estimation or revenue analytics
- Listing optimization or copywriting suggestions
- Inventory or supply chain data
Boundary judgment: When users say "product research" or "competitor analysis", if it boils down to seeing what currently appears on Amazon search results for a keyword (product positions, prices, ratings), then this skill applies. If they want historical trends, search volume data, or aggregated analytics, ABA data is more appropriate.
Compute Consumption Rules
Consumes 15 compute.
Users will pay fees due to compute consumption. Please fully assess: when this skill needs to be called frequently, or when the user's expectation of compute consumption is insufficient, be sure to remind the user and let the user decide 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.