• API 端点：

  POST /keepa/productSeries

  （完整参数/响应/错误码见

  references/api.md

  ）
• Python 脚本：

  python scripts/keepa_product_history.py '<JSON 参数>' [--inline]

• 成本约束：本工具会消耗积分；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。

• 始终将完整响应写入

  <cwd>/linkfox/<YYYY-MM-DD>/<session>/data/linkfox-keepa-product-series-<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）

jq

ConvertFrom-Json

• 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
• 响应提示积分或余额不足：消息含"积分余额不足/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。

• asin: The Amazon Standard Identification Number to query. Only a single ASIN per request is supported.
• domain: The Amazon marketplace domain ID (see table above). Always map the user's marketplace mention to the correct numeric ID.

• days: Number of historical days to retrieve (1-365, default 90). Use 30 for short-term, 90 for medium-term, 365 for long-term analysis.
• show* flags: Set any

  show*

  parameter to

  1

  to include that data series. By default, only the core series (Buy Box price, rating, rating count, monthly sales, sub-category BSR) are returned.

1. Price analysis: Enable

   showPrice

   ,

   showPriceList

   ,

   showPriceDeal

   ,

   showPriceCoupon

   as needed for the specific price comparison the user wants.
2. FBA vs FBM comparison: Enable both

   showPriceFba

   and

   showPriceFbm

   .
3. BSR deep-dive: Enable

   showBsrMain

   to get the root category BSR alongside the always-returned sub-category BSR.
4. Competitive landscape: Enable

   showSellerCount

   to see how many sellers are competing.
5. Full product overview: Enable all show flags for a comprehensive historical snapshot.

1. Present data clearly: Show time-series data in tables or describe trends; avoid subjective business advice unless the user explicitly asks for it.
2. BSR clarification: When showing BSR data, remind users that lower values mean better (higher) sales ranks.
3. Price formatting: Display prices with proper currency symbols matching the marketplace ($ for US, EUR for DE/FR/ES/IT, GBP for UK, JPY for JP, etc.).
4. Time formatting: Present timestamps in a human-readable date format.
5. Trend summarization: When data series are long, summarize the overall trend (e.g., "price decreased from $29.99 to $24.99 over 90 days") and highlight significant changes such as price drops, BSR spikes, or rating shifts.
6. Error handling: When a query fails, explain the reason and suggest corrections (e.g., verify the ASIN is valid, check the marketplace domain ID).
7. Single ASIN limitation: If the user asks about multiple ASINs, inform them that queries must be made one ASIN at a time, and run multiple sequential calls.

• Single ASIN per query: Only one ASIN can be queried at a time. For multi-ASIN comparisons, make separate requests.
• Maximum 365 days: Historical data is limited to at most 365 days back.
• Data granularity: Data points are at irregular intervals depending on when Keepa captured changes, not at fixed daily intervals.

• Search term / keyword analysis (use ABA data instead)
• Advertising / PPC campaign data
• Listing copywriting or content optimization
• Category-wide or market-level aggregate trends (this tool is per-ASIN only)
• Real-time inventory or stock level checks
• Product reviews text or sentiment analysis

重要：本技能的服务按倍数动态计算，可能一次性消耗大量积分，必须提醒用户，由用户决定是否继续。

1. The functionality or purpose described in this skill does not match actual behavior
2. The skill's results do not match the user's intent
3. The user expresses dissatisfaction or praise about this skill
4. Anything you believe could be improved

references/api.md