mcpField
L
linkfox-ehunt-temu-product-query

linkfox-ehunt-temu-product-query

github.com/linkfox-aiMarketing & growth11389 installsUpdated 2w ago
Repository

About linkfox-ehunt-temu-product-query

A LinkFox skill for querying Temu product data through the EHunt productQuery route. It supports filtering, sorting, pagination, and saving large responses for selective reading.

Key features

  1. 01Filter products by price, sales, rating, category, and status
  2. 02Support pagination and configurable sorting
  3. 03Save large responses and read selected fields

Use cases

  1. 01Find products matching price or sales ranges
  2. 02Compare listings by rating, category, or sales
  3. 03Review selected fields from paginated results

MCP support

Uses the LinkFox third-party data service MCP to call the `ehunt/temu/productQuery` gateway route. Exact tool name depends on the metadata supplied in the current environment.

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/linkfox-ai/linkfox-skills --skill linkfox-ehunt-temu-product-query

After installing, type/linkfox-ehunt-temu-product-queryin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

references/
api.md
scripts/
ehunt_temu_product_query.py
response_io.py

Details

From the project README

EHunt Temu 商品查询（ehunt/temu/productQuery）

在具备 LinkFox「第三方数据服务」MCP 时，对应网关路由 ehunt/temu/productQuery 调用（MCP 展示名：Temu 商品查询，确切工具名以当前环境下发的工具元数据为准）。鉴权与上游路由由网关处理；若响应含根级 code 字段，是否成功以实网为准。

要点

  • 分页：page 从 1 起；pageSize 默认 20、最大 100（建议 ≤50）。
  • 区间入参：*Begin / *End 成对出现（价格、评分、评论、总/周/日销量、上架时间），组成上游区间。
  • 类目：categoryHome 前台类目 ID、categoryBackend 后台类目 ID；可先用 Temu 品类检索拿到 id。
  • 托管模式：isLocal（0=全托管，1=半托管）；半托管可用 region 限定地区（多个逗号分隔）。
  • 上下架：soldOut（0=上架，1=下架）。
  • 标签：tags / customTags 多个用逗号分隔。
  • 排序：sortBy 为「字段-方向」字符串，如 order_week-0（周销量降序，默认）、price-0、order_total-0、rating-0。

脚本（可选）

命令行调试：python scripts/ehunt_temu_product_query.py '<JSON>'（需 LINKFOXAGENT_API_KEY）。详见 references/api.md 末尾。

参考

入参/出参表见 references/api.md。

Handling Large Responses

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/ehunt_temu_product_query.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.

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.

Comments

Markdown supported