Linkfox Mpstats Ozon Product Trend

MPSTATS Ozon Product Trend (Daily Time-Series)

This skill returns a daily time-series of a single Ozon (Russia) SKU — sales units, price, stock, rating, and optionally search-position / visibility metrics. It is the go-to for validating growth, seasonality, or anomalies for a specific product.

Core Concepts

Single-SKU scope: Each call analyzes exactly one productId. For batch per-SKU snapshots (period aggregates), use mpstats-ozon-product-detail instead.

Daily granularity: The response is an array of daily points (top-level field data) across the [startDate, endDate] window. Each point carries a hasData boolean — if hasData=false, the day has no observation (distinct from sales=0 with hasData=true).

T-1 delay: MPSTATS trend data is delayed by one day; the latest selectable end date is yesterday. Today or future dates are rejected.

Search-visibility add-on: Set includeSearchStats: true to append search-position / visibility signals. Some niches (especially small categories) may not have search-stats coverage — expect partial or empty fields in those cases.

Parameters

调用方式

• API 端点：POST /mpstats/ozon/productTrend（完整参数/响应/错误码见 references/api.md）
• Python 脚本：python scripts/mpstats_ozon_product_trend.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-trend-<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. Monthly trend for a SKU

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

2. Trend with search visibility

{
  "productId": 1786874757,
  "startDate": "2025-02-01",
  "endDate": "2025-02-28",
  "includeSearchStats": true
}

3. Combined FBO+FBS trend

{
  "productId": 151623766,
  "startDate": "2025-01-01",
  "endDate": "2025-01-31",
  "includeFbs": true
}

How to Chain with Other Ozon Skills

1. Discovery → trend: Use mpstats-ozon-product-search to find a SKU, then check growth / volatility here before committing.
2. Aggregate vs time-series: mpstats-ozon-product-detail gives a one-number-per-metric period view; this skill shows the day-by-day shape behind those numbers.
3. Drill-down → trend: After brand-products / category-products / seller-products surfaces a hot SKU, use this skill to validate whether the hotness is recent, seasonal, or sustained.

Display Rules

1. Prefer a simple table or sparkline-friendly output — one row per date with date, price, sales, balance, rating, comments; do not overfit a 90-point series into a single paragraph.
2. Use hasData to distinguish gaps from zero sales — hasData=false means the day has no observation; don't report it as a zero-sale day.
3. Call out anomalies — large single-day spikes or stockouts (balance=0 runs where hasData=true) should be flagged factually, not as buying advice.
4. Currency is RUB unless upstream layer is already converting (the currency field per point carries the symbol, e.g. ₽); state the currency when showing price movement.
5. Revenue is not returned per day — if the user asks for daily revenue, estimate via sales * price and note it's an estimate.
6. includeSearchStats gaps — when no search-visibility fields come back, note "搜索位次数据在该赛道暂不可用" rather than silently omitting.
7. No business advice — present the shape; leave "should we buy this listing?" to the user.