linkfox-amazon-store-catalog

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Amazon 店铺 Catalog Items

Amazon 店铺 Catalog Items

本 skill 与
linkfox-amazon-store-auth
等同属 Amazon Store 系列:先
POST /spApi/storeTokens
,再
POST /spApi/developerProxy
转发 GET
本 Skill 与
linkfox-amazon-store-auth
等同属 Amazon Store 系列:先调用
POST /spApi/storeTokens
,再通过
POST /spApi/developerProxy
转发 GET 请求。

官方参考索引

官方参考索引

能力文档
listCatalogCategorieslistCatalogCategories
searchCatalogItemssearchCatalogItems
getCatalogItemgetCatalogItem

功能文档
listCatalogCategorieslistCatalogCategories
searchCatalogItemssearchCatalogItems
getCatalogItemgetCatalogItem

Prerequisites

前置条件

  1. 依赖
    linkfox-amazon-store-auth
    python scripts/check_auth_dependency.py
    ,exit 42 时需先安装授权 skill。
  2. 应用需具备 Catalog Items 相关角色;
    searchCatalogItems
    identifiers+SKU 检索时 query 须带
    sellerId
    (脚本在
    identifiersType=SKU
    时自动使用入参
    sellerId
    )。

  1. 依赖
    linkfox-amazon-store-auth
    ;执行
    python scripts/check_auth_dependency.py
    ,若退出码为 42,需先安装授权 Skill。
  2. 应用需具备 Catalog Items 相关角色;
    searchCatalogItems
    identifiers+SKU 检索时,query 必须携带
    sellerId
    (脚本在
    identifiersType=SKU
    时自动使用入参
    sellerId
    )。

Current Capabilities

当前功能

能力path脚本
listCatalogCategories
catalog/v0/categories
list_catalog_categories.py
searchCatalogItems
catalog/{2022-04-01|2020-12-01}/items
search_catalog_items.py
getCatalogItem
catalog/{version}/items/{asin}
get_catalog_item.py
默认 Catalog Items 版本:
2022-04-01
;入参
catalogItemsVersion
可改为
2020-12-01
共享模块:
_spapi_catalog_common.py

功能路径脚本
listCatalogCategories
catalog/v0/categories
list_catalog_categories.py
searchCatalogItems
catalog/{2022-04-01|2020-12-01}/items
search_catalog_items.py
getCatalogItem
catalog/{version}/items/{asin}
get_catalog_item.py
默认 Catalog Items 版本:
2022-04-01
;入参
catalogItemsVersion
可修改为
2020-12-01
共享模块:
_spapi_catalog_common.py

Quick Parameters

快速参数

  • listCatalogCategories
    marketplaceId
    +
    asin
    sellerSku
    (二选一)。
  • searchCatalogItems
    marketplaceIds
    +
    keywords
    identifiers
    +
    identifiersType
    (互斥);可选
    includedData
    brandNames
    classificationIds
    pageSize
    pageToken
  • getCatalogItem
    asin
    marketplaceIds
    ;可选
    includedData
    locale

  • listCatalogCategories
    marketplaceId
    +
    asin
    sellerSku
    (二者选其一)。
  • searchCatalogItems
    marketplaceIds
    +
    keywords
    identifiers
    +
    identifiersType
    (互斥);可选参数
    includedData
    brandNames
    classificationIds
    pageSize
    pageToken
  • getCatalogItem
    asin
    marketplaceIds
    ;可选参数
    includedData
    locale

Scripts

脚本示例

bash
export LINKFOXAGENT_API_KEY="<your-key>"

python scripts/list_catalog_categories.py '{"sellerId":"A1...","region":"NA","marketplaceId":"ATVPDKIKX0DER","asin":"B08N5WRWNW"}'

python scripts/search_catalog_items.py '{"sellerId":"A1...","region":"NA","marketplaceIds":["ATVPDKIKX0DER"],"keywords":["wireless mouse"]}'

python scripts/get_catalog_item.py '{"sellerId":"A1...","region":"NA","asin":"B08N5WRWNW","marketplaceIds":["ATVPDKIKX0DER"],"includedData":["summaries","images"]}'

bash
export LINKFOXAGENT_API_KEY="<your-key>"

python scripts/list_catalog_categories.py '{"sellerId":"A1...","region":"NA","marketplaceId":"ATVPDKIKX0DER","asin":"B08N5WRWNW"}'

python scripts/search_catalog_items.py '{"sellerId":"A1...","region":"NA","marketplaceIds":["ATVPDKIKX0DER"],"keywords":["wireless mouse"]}'

python scripts/get_catalog_item.py '{"sellerId":"A1...","region":"NA","asin":"B08N5WRWNW","marketplaceIds":["ATVPDKIKX0DER"],"includedData":["summaries","images"]}'

Display Rules

展示规则

  1. 先看
    developerProxy.errcode
    /
    httpStatus
    ,再读
    categories
    /
    catalogItems
    /
    catalogItem
  2. listCatalogCategories 使用 v0 查询键
    MarketplaceId
    (单数),与 search/get 的
    marketplaceIds
    不同。
  3. 网关 path 白名单需包含
    catalog/v0/
    catalog/2022-04-01/
    (或
    2020-12-01
    )。

  1. 先查看
    developerProxy.errcode
    /
    httpStatus
    ,再读取
    categories
    /
    catalogItems
    /
    catalogItem
  2. listCatalogCategories 使用 v0 版本的查询键
    MarketplaceId
    (单数形式),与 search/get 接口的
    marketplaceIds
    (复数形式)不同。
  3. 网关路径白名单需包含
    catalog/v0/
    catalog/2022-04-01/
    (或
    2020-12-01
    )。

Important Limitations

重要限制

  • 本 skill 读的是 Amazon 商品目录(Catalog),不是卖家订单;订单见
    linkfox-amazon-store-orders
  • includedData
    、返回字段以 Amazon schema 为准,详见
    references/api.md
Feedback:
skillName
linkfox-amazon-store-catalog

更多跨境 skill:LinkFox Skills
<!-- LF_LARGE_RESPONSE_BLOCK -->
  • 本 Skill 读取的是 Amazon 商品目录(Catalog),而非卖家订单;订单相关功能请查看
    linkfox-amazon-store-orders
  • includedData
    、返回字段以 Amazon schema 为准,详情请查阅
    references/api.md
反馈:
skillName
linkfox-amazon-store-catalog

更多跨境 Skill:LinkFox Skills
<!-- LF_LARGE_RESPONSE_BLOCK -->

Handling Large Responses

处理大响应

To avoid overflowing the agent context, persist the response to disk and extract only the fields you need:
python scripts/response_io.py run --script scripts/check_auth_dependency.py --out-dir <DIR> '<params>'
python scripts/response_io.py read <file> --fields "<paths>"   # or --path "<JMESPath>"
Pick
--out-dir
outside any git working tree (e.g.
/tmp/...
on Unix,
%TEMP%/...
on Windows). Persisted responses may contain PII, pricing, or auth-sensitive data — do not commit them. Files are not auto-deleted; clean up when the task is done.
This skill exposes multiple entry scripts:
check_auth_dependency.py
,
get_catalog_item.py
,
list_catalog_categories.py
,
search_catalog_items.py
. Pass
--script scripts/<name>.py
to choose the one you need.
run
writes the full response to a file and emits only a schema preview + file path.
read
projects specific fields, with
--limit/--offset
for slicing and
--format json|jsonl|csv|table
for output.
When to prefer this pattern — apply your judgment based on the response characteristics, e.g.:
  • High field count per record, or fields you don't need
  • Batch/paginated results (multiple items per call)
  • Long-text fields (descriptions, reviews, HTML, time series)
  • Output reused across later steps rather than consumed immediately
For small, single-use responses, calling the main script directly is fine.
⚠️ The preview is a truncated schema + sample, not the full data. Any field-level decision must read from the persisted file via
read
.
<!-- /LF_LARGE_RESPONSE_BLOCK -->
为避免超出 Agent 上下文限制,请将响应持久化到磁盘,并仅提取所需字段:
python scripts/response_io.py run --script scripts/check_auth_dependency.py --out-dir <DIR> '<params>'
python scripts/response_io.py read <file> --fields "<paths>"   # 或 --path "<JMESPath>"
请选择不在任何 Git 工作目录内的
--out-dir
(例如 Unix 系统的
/tmp/...
,Windows 系统的
%TEMP%/...
)。持久化的响应可能包含个人身份信息(PII)、定价或授权敏感数据——请勿提交到版本库。文件不会自动删除;完成任务后请自行清理。
本 Skill 提供多个入口脚本:
check_auth_dependency.py
get_catalog_item.py
list_catalog_categories.py
search_catalog_items.py
。通过传递
--script scripts/<name>.py
选择所需脚本。
run
命令会将完整响应写入文件,并仅输出架构预览+文件路径。
read
命令会提取指定字段,支持通过
--limit/--offset
进行切片,以及通过
--format json|jsonl|csv|table
指定输出格式。
何时优先使用此模式——根据响应特性判断,例如:
  • 每条记录字段数量多,或包含不需要的字段
  • 批量/分页结果(单次调用返回多个条目)
  • 长文本字段(描述、评论、HTML、时间序列)
  • 输出需在后续步骤中复用,而非立即使用
对于小型、一次性响应,直接调用主脚本即可。
⚠️ 预览内容是截断后的架构+样本,并非完整数据。任何字段级别的决策都必须通过
read
命令从持久化文件中读取。
<!-- /LF_LARGE_RESPONSE_BLOCK -->