This skill searches Ozon (Russia) products in the MPSTATS analytics database by Russian keyword, SKU list, brand name, or seller name. It is the entry point for Ozon product discovery and competitor lookup — downstream drill-downs (brand/category/seller/detail/trend) typically start from the IDs returned here.
MPSTATS Ozon coverage: Ozon is Russia's largest general-category marketplace. MPSTATS indexes Ozon product listings and sales history. This endpoint returns the basic identity card only — 10 fields: productId / title / productPageUrl / imageUrl / brand / brandId / sellerName / sellerId plus sourceType / sourceTool. Per-SKU price / sales / rating / stock / turnover / ranking are not returned here — the backend OzonProductSearchItem DTO is intentionally narrow. For those metrics, chain into mpstats-ozon-product-detail (batch full card, 36 fields) or the brand/category/seller-products drill-downs (39 fields).
Language requirement: Keywords, brand names, and seller names must be in Russian (Cyrillic) — or the Latin-script form actually used on the Ozon storefront (e.g., adidas). If the user supplies an English or Chinese keyword, translate it to Russian first and note the translation.
At-least-one input rule: The input schema marks all four filters as optional, but the tool's business rule requires at least one of keyword / productIds / brandNames / sellerNames to be supplied. The four can be combined to narrow results.
| Parameter | Type | Required | Description | |
|---|---|---|---|---|
| ----------- | ------ | ---------- | ------------- | |
| keyword | string | conditional | Russian search keyword, e.g., кроссовки (sneakers) | |
| productIds | array| string> | conditional | Ozon SKU list | |
| brandNames | array | conditional | Brand display names (Russian or Latin) | |
| sellerNames | array | conditional | Seller display names (Russian) | |
| startDate | string | no | Stats window start, YYYY-MM-DD; defaults to one year ago | |
| endDate | string | no | Stats window end, YYYY-MM-DD; defaults to yesterday, cannot be today or future | |
| page | integer | no | Page number, starts at 1 | |
| pageSize | integer | no | Rows per page, 1-100, default 100 |
At least one of keyword / productIds / brandNames / sellerNames must be supplied.
This tool calls the LinkFox tool gateway API. See references/api.md for calling conventions, request parameters, response structure, and error codes. You can also execute scripts/mpstats_ozon_product_search.py directly for ad-hoc queries.
1. Keyword search — sneakers in Russian
{"keyword": "кроссовки", "pageSize": 50}
2. SKU batch reverse lookup
{"productIds": [1786874757, 151623766, 142257239]}
3. Brand-scoped discovery
{"brandNames": ["adidas", "Xiaomi"], "keyword": "наушники"}
4. Seller-scoped discovery
{"sellerNames": ["ООО Ромашка"], "pageSize": 100}
5. Dated window for period-specific search
{"keyword": "футболка", "startDate": "2025-02-01", "endDate": "2025-02-28"}
productId → call mpstats-ozon-product-detail (batch metrics) or mpstats-ozon-product-trend (single-SKU time-series).mpstats-ozon-brand-products for full sales / stock / rating metrics.sellerId from the result, then call mpstats-ozon-seller-products for the seller's full SKU map.productId, title, brand, sellerName; include productPageUrl / imageUrl as secondary columns. Do not add price / sales / rating / stock columns — they are not in the response.total exceeds the page size, tell the user the total count and suggest the next page or a narrower keyword.mpstats-ozon-product-detail (single or batch) or the *-products drill-downs. Do not fabricate or estimate from identity fields.code / errcode is non-200, explain the reason from msg / errmsg and suggest adjusting inputs (supply at least one of the four filters, use Russian, narrow date range).required is empty in inputSchema.endDate cannot be today or a future date; data is T-1.pageSize max is 100; paginate for larger sets.OzonProductSearchItem DTO declares exactly 10 identity fields. This is a hard contract, not a sparse payload — do not assume missing metric fields could be filled in by re-calling with different dates.Applicable — Ozon product discovery / identity resolution:
| User Says | Scenario |
|---|---|
| ----------- | ---------- |
| "Search Ozon for sneakers / headphones / ..." | Keyword discovery |
| "I have a list of Ozon SKUs, pull their names" | Batch SKU reverse lookup |
| "What does brand X sell on Ozon" | Brand-scoped candidate listing |
| "What does seller Y sell on Ozon" | Seller-scoped candidate listing |
| "Translate this keyword to Russian and search Ozon" | Cross-language discovery |
Not applicable — Needs beyond discovery:
mpstats-ozon-product-detail (batch card) or the *-products drill-down skills.mpstats-ozon-product-trend.mpstats-ozon-category-products with a known path.Boundary judgment: If the user wants to find or identify Ozon products, start here. If they already have an ID or a dimension (brand / category / seller) and want metrics under it, go to the corresponding drill-down skill directly.
Feedback:
Auto-detect and report feedback via the Feedback API when any of the following apply:
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.
共 2 个版本