Linkfox Mpstats Ozon Product Detail

MPSTATS Ozon Product Detail (Single SKU)

This skill fetches the full product card for one Ozon (Russia) SKU via MPSTATS. Returned fields include price, Ozon Card price, discount, rating, reviews, stock, monthly sales units, monthly sales revenue, lost profit, potential revenue, first listing date, image, and more.

Core Concepts

Single-SKU semantics: Pass exactly one productId in a call. productIds arrays/lists are no longer accepted by this skill; for multiple SKUs, make separate calls only after confirming the extra credit cost with the user.

Fulfillment model per SKU: Each product card carries deliveryScheme:

• FBO — Fulfillment by Ozon (stock in Ozon warehouses)
• FBS — Fulfillment by Seller (seller-shipped)

Pass includeFbs: true to allow FBS SKUs and FBS-scoped metrics into the response; false (or omitted) keeps the result FBO-centric. This switch applies to the whole request.

Previous-period comparison: The card includes previousSalesUnits / previousRevenue — sales and revenue from the equal-length period immediately before [startDate, endDate] — ready for MoM / period-over-period diffs without extra calls.

Revenue potential: revenuePotential projects what the SKU could have earned if it had been in stock every day of the window; compare with monthlySalesRevenue to quantify stock-out drag, together with lostProfit / lostProfitPercent.

Date window: startDate / endDate define the period for all period-aggregated metrics. Latest selectable date is yesterday (T-1); today and future dates are rejected.

Parameters

调用方式

• API 端点：POST /mpstats/ozon/productDetail（完整参数/响应/错误码见 references/api.md）
• Python 脚本：python scripts/mpstats_ozon_product_detail.py '<JSON 参数>' [--inline]
• 成本约束：本工具会消耗算力；同一会话同一参数组合默认只调用一次，脚本带 24h 本地缓存。失败/空结果不得自动换关键词、翻页或改邮编连续试探；需要继续检索时先向用户说明会产生额外消耗。

输出策略（脚本默认行为）：

• 始终将完整响应写入 <cwd>/linkfox/<YYYY-MM-DD>/<session>/data/linkfox-mpstats-ozon-product-detail-<timestamp>.json（<cwd> 为脚本执行时的工作目录，在 Claude Code 里即当前项目目录；<session> 取自环境变量 SESSION_ID，按用户任务自动聚合；禁止写入 /tmp，当前目录不可写则报错）
• 响应体 ≤ 8 KB：落盘后把完整 JSON 打印到 stdout
• 响应体 > 8 KB：落盘后 stdout 只输出摘要（顶层字段、常见计数如 total/costToken、最大列表字段的长度 + 前 3 条样本）
• 加 --inline 强制全量打印到 stdout（同样落盘）

读数据建议：先看摘要判断是否足够；需要具体字段时优先用 jq或ConvertFrom-Json 从保存的 json 文件按需抽取，避免整份 JSON 进入上下文。

解决认证和算力问题

发生以下异常情况时，采用 references/onboarding.md 引导解决问题：

异常情况

• 未配置API Key：环境变量未配置 LINKFOX_AGENT_API_KEY，也未配置 LINKFOXAGENT_API_KEY。
• 响应401或402状态码
• 响应提示算力或余额不足：消息含"算力余额不足/计费不足/余额不足/quota exceeded/insufficient balance/套餐到期/需充值/请充值"，或类似含义的内容。

Usage Examples

1. Single-SKU detail

{"productId": 1786874757}

2. Single-SKU lookup with period

{
  "productId": 1786874757,
  "startDate": "2025-03-01",
  "endDate": "2025-03-31",
  "includeFbs": true
}

3. FBO-only snapshot

{"productId": 1786874757, "includeFbs": false}

4. SKU discovered upstream — full card

{"productId": <productId from mpstats-ozon-product-search>}

How to Chain with Other Ozon Skills

1. Search → detail: Use mpstats-ozon-product-search to resolve a keyword / brand / seller into candidate productIds, choose one SKU, then pass that productId here for full metrics.
2. Detail vs trend: This endpoint is a period aggregate per SKU; for day-by-day time-series on a single SKU, use mpstats-ozon-product-trend.
3. Detail vs drill-downs: When the input dimension is a brand / category / seller (not a single SKU), prefer brand-products / category-products / seller-products — they already return aggregated metrics per SKU under that dimension.

Display Rules

1. Compact table — lead with productId, title, price, monthlySalesUnits, monthlySalesRevenue, rating, reviewCount, balance, deliveryScheme, firstDate. Pull revenuePotential / lostProfit / lostProfitPercent in when the user asks about stock-out impact.
2. Currency — Ozon native currency is RUB; the currency field carries the symbol. Do not silently relabel.
3. Failure handling — the response carries successCount / failedCount / failures; when failedCount > 0, list the failed productId from failures to the user rather than silently dropping it.
4. Period-over-period — when both current and previous* fields are present, render them side-by-side or as diff; don't report a single-period number as "trend".
5. With-stock vs all-days — salesPerDayWithStock / dailySalesRevenueWithStock only count days that had inventory; distinguish from the plain salesPerDay / dailySalesRevenue.
6. Delivery model — prefer the per-SKU deliveryScheme value over assuming FBO.
7. No business advice — present data; do not extrapolate "this SKU is worth selling" without a wider analysis.