linkfox-ehunt-temu-product-query
Original:🇺🇸 English
Translated
2 scriptsChecked / no sensitive code detected
通过 EHunt Temu 商品查询(网关路由 `ehunt/temu/productQuery`)按多维度筛选 Temu 商品(关键词/商品 ID/店铺 ID、前后台类目、价格、评分、评论、总/周/日销量、上架时间、全托管/半托管、半托管地区、标签等)。当用户提到 EHunt Temu 商品、Temu 选品、拼多多跨境、Temu 爆款、Temu 半托管、全托管商品、Temu product query、temu items 时触发。即使用户未写 EHunt,只要在 Temu 上搜商品、看销量/评分/价格或筛品,也应触发此技能。
27installs
Added on
NPX Install
npx skill4agent add linkfox-ai/linkfox-skills linkfox-ehunt-temu-product-queryTags
Translated version includes tags in frontmatterSKILL.md Content
View Translation Comparison →EHunt Temu 商品查询(ehunt/temu/productQuery
)
ehunt/temu/productQuery在具备 LinkFox「第三方数据服务」MCP 时,对应网关路由 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 字段,是否成功以实网为准。
ehunt/temu/productQuerycode要点
- 分页:从 1 起;
page默认 20、最大 100(建议 ≤50)。pageSize - 区间入参:/
*Begin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。*End - 类目:前台类目 ID、
categoryHome后台类目 ID;可先用 Temu 品类检索拿到 id。categoryBackend - 托管模式:(0=全托管,1=半托管);半托管可用
isLocal限定地区(多个逗号分隔)。region - 上下架:(0=上架,1=下架)。
soldOut - 标签:/
tags多个用逗号分隔。customTags - 排序:为「字段-方向」字符串,如
sortBy(周销量降序,默认)、order_week-0、price-0、order_total-0。rating-0
脚本(可选)
命令行调试:(需 )。详见 references/api.md 末尾。
python scripts/ehunt_temu_product_query.py '<JSON>'LINKFOXAGENT_API_KEY参考
入参/出参表见 references/api.md。
<!-- LF_LARGE_RESPONSE_BLOCK -->
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>"Pickoutside any git working tree (e.g.--out-diron Unix,/tmp/...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.%TEMP%/...
runread--limit/--offset--format json|jsonl|csv|tableWhen 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 .
<!-- /LF_LARGE_RESPONSE_BLOCK -->read