Linkfox Seerfar Ozon Product Detail Search

Seerfar Ozon Product Detail Search

This skill fetches the full detail of a single Ozon product by its SKU from the Seerfar analytics database — title, price (₽), rating, reviews, QA count, sales (total + daily average + daily trend), revenue, stock, category rank, brand, seller, fulfillment (FBO/FBS/OZON), weight and listing age. The starting point for single-product deep analysis, competitor product teardown, listing diagnostics and sales-trend tracking.

Core Concepts

Unit of data is a single product, looked up by sku: pass one Ozon SKU, get that product's full detail. This is a product-level view (one SKU), not a shop catalog, keyword or category view.

Where the SKU comes from: sku is the Ozon product SKU — the same sku returned by other Seerfar Ozon tools (shop search, keyword back search, category search, market keyword search). If the user only has a product name, URL or shop, first obtain the sku from one of those listing-level sources, then call this skill for the deep dive.

Sales window: dateRange controls the sales/metrics window — totalSales, dailySales, totalRevenue and salesTrendVOList are computed over this range. Default past_30_days. Options: past_7_days / past_30_days / past_60_days / past_90_days / past_180_days / past_365_days.

Sales & price currency: price is in Russian rubles (₽), indicated by currency. totalSales is units over the window; dailySales is the average units/day; totalRevenue is revenue over the window.

Listing age: upTime is the listing timestamp (ms); upDays / upMonths are the derived age in days / months.

Parameters

Only sku is required.

调用方式

• API 端点：POST /seerfar/ozon/productDetailSearch（完整参数/响应/错误码见 references/api.md）
• Python 脚本：python scripts/seerfar_ozon_product_detail_search.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-seerfar-ozon-product-detail-search-<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. Default 30-day detail for a product

{"sku": "175924376"}

2. Last 7 days (recent momentum)

{"sku": "175924376", "dateRange": "past_7_days"}

3. Last 90 days (quarterly trend)

{"sku": "175924376", "dateRange": "past_90_days"}

4. Full year (lifecycle view)

{"sku": "175924376", "dateRange": "past_365_days"}

How to Build Queries

1. Resolve the SKU first: if the user gives a product name, URL or shop rather than a SKU, obtain the sku from a listing-level Seerfar Ozon source (shop search / keyword back search / category search / market keyword search) before calling this skill.
2. Pick dateRange by intent: short windows (past_7_days / past_30_days) for recent momentum and current stock; long windows (past_90_days / past_180_days / past_365_days) for lifecycle, seasonality and ranking stability.
3. Read aggregates, then trend: start with top-level totalSales / dailySales / totalRevenue / stock / categoryRanks for a snapshot, then drill into salesTrendVOList for the daily series.
4. One SKU per call: this endpoint takes a single sku; to compare products, call once per SKU.

Display Rules

1. Present data only: show the product metrics in a clear layout without subjective advice.
2. Lead with identity + snapshot: title, sku, price (₽), reviewRating (reviewCount reviews, questionsAndAnswers Q&A), then the sales snapshot (totalSales, dailySales, totalRevenue, stock) and the window (startDate–endDate).
3. Category ranks: categoryRanks is a monthly rank history ({date, rank, count}) — it has no category name, so show the category path from categoryInfo (titlePath / cnTitlePath) alongside the rank history.
4. Sales trend: salesTrendVOList is a daily series ({date, sales, revenue, price, stock, reviewCount, reviewRating}) — summarize (peak day, trend direction) rather than dumping every row; offer the persisted file for the full series. Some days may have sales: 0 — treat as no-sales, not missing data.
5. Seller & brand: show sellerName (sellerId — negative means an Ozon platform seller) and brandName (brandId) so the user can trace the seller/brand.
6. Fulfillment: fulfillment is an array (e.g. ["FBO"], or ["OZON"] for platform-sold items); join multiple values with /.
7. Listing age: render upTime as a date (ms timestamp) alongside upDays / upMonths.
8. Conditional fields: weight (physical goods only) and grossMargin are schema-defined but absent for some products (e.g. digital goods / Ozon platform sellers) — show - when missing rather than failing. monthlySalesUnits / monthlySalesRevenue mirror the window's totalSales / totalRevenue and are safe to read directly.
9. Empty result: a non-existent sku returns success with total:0 and empty products — tell the user the SKU may be wrong rather than reporting a system error.
10. Error handling: when code is not "200" (or errcode is not 200), explain from msg / errmsg and suggest fixes (check SKU, retry on rate-limit).