linkfox-temu-ads-us

Original：🇺🇸 English

Translated

22 scriptsChecked / no sensitive code detected

Temu 美国站电商广告 Ads API，经 LinkFox 网关转发 Partner US Ads / 广告投放相关 bg/temu 接口（广告计划、广告组、创意、报表、预算出价等，接口将按 Partner 文档逐条接入）。当用户提到 Temu US 广告、Ads、广告投放、广告计划、广告组、创意、出价、预算、广告报表、ad campaign、product-inventory 广告时触发。商品管理用 linkfox-temu-manage-product-us；促销用 linkfox-temu-promotion-us；订单用 linkfox-temu-order-us。

23installs

Sourcelinkfox-ai/linkfox-skills

Added on2026-07-04

NPX Install

npx skill4agent add linkfox-ai/linkfox-skills linkfox-temu-ads-us

SKILL.md Content

View Translation Comparison →

Temu 美国站 — 电商广告（Ads）

本 skill（

linkfox-temu-ads-us

）覆盖 Partner Platform for US Ads / 电商广告（广告计划、投放、报表等；

menu_code

与各

sub_menu_code

以 Partner 后台为准，见 partner-us-catalog.md）。

已接入 7 条 Partner Ads（

temu.searchrec.ad.*

）接口，清单见 partner-us-catalog.md。

网关（本 skill 内置）：

能力	方法	路径
广告 OpenAPI（ `us_ads_*` 、 `temu_us_proxy` ）	POST	`https://tool-gateway.linkfox.com/temu/proxy`
加签文件下载	POST	`https://tool-gateway.linkfox.com/temu/fileDownload`

场景	skill
广告 Ads（本 skill）	`linkfox-temu-ads-us`
商品列表/详情/编辑/库存/上下架	`linkfox-temu-manage-product-us`
促销/营销活动	`linkfox-temu-promotion-us`
发品	`linkfox-temu-add-product-us`
价格/供货价、定价单	`linkfox-temu-price-us`
订单列表/详情	`linkfox-temu-order-us`
退货与退款	`linkfox-temu-returns-refunds-us`
网关与 Temu token	本 skill `scripts/`

API Usage

文档	内容
api.md	网关、鉴权、错误码、接入约定
partner-us-catalog.md	接口目录 + Partner URL + 脚本（随接入更新）
apis/README.md	按接口分文件（ `apis/<type-slug>.md` ）

默认参数

字段	默认	说明
site	`us`	Partner US
managementType	`semi-managed`	半托管（具体接口以 Partner 文档为准）
tokenPurpose	`product-inventory`	卖家助手默认（若 Partner 某 Ads 接口要求其他 `tokenPurpose` ，以该接口文档为准）

鉴权

LinkFox：
```
LINKFOXAGENT_API_KEY
```
→ Header
```
Authorization
```
+
```
Token
```

Temu：

accessToken

或

storeKey

（

storeKey

时建议带

tokenPurpose=product-inventory

）

Scripts

脚本	说明
`temu_us_proxy.py`	任意 type
`temu_us_file_download.py`	加签下载
`us_ads_searchrec_ad_roas_pred.py`	`temu.searchrec.ad.roas.pred`
`us_ads_searchrec_ad_reports_mall_query.py`	`temu.searchrec.ad.reports.mall.query`
`us_ads_searchrec_ad_create.py`	`temu.searchrec.ad.create`
`us_ads_searchrec_ad_detail_query.py`	`temu.searchrec.ad.detail.query`
`us_ads_searchrec_ad_log_query.py`	`temu.searchrec.ad.log.query`
`us_ads_searchrec_ad_goods_create_query.py`	`temu.searchrec.ad.goods.create.query`
`us_ads_searchrec_ad_modify.py`	`temu.searchrec.ad.modify`

接入新接口（约定）

你每提供一条 Partner 文档（

type

+

sub_menu_code

+ URL + Request/Response 参数表），将：

新增
```
references/apis/<type-slug>.md
```
（完整入参/出参层级）

新增

scripts/us_ads_<slug>.py

（调用

_us_ads_script.run_cli

）

更新 partner-us-catalog.md、apis/README.md 与本表

示例（通用代理）

bash

export LINKFOXAGENT_API_KEY="<key>"

python scripts/temu_us_proxy.py '{
  "accessToken": "TOKEN",
  "tokenPurpose": "product-inventory",
  "type": "<TEMU_API_TYPE>",
  "params": {
    "request": {}
  }
}'

Feedback：

skillName

：

linkfox-temu-ads-us

网关与授权脚本

脚本	说明
`check_linkfox_token.py`	校验 LinkFox 用户 Token
`temu_token_guide.py`	Temu accessToken 后台授权步骤
`save_temu_access_token.py`	保存 accessToken 到本地
`list_temu_access_tokens.py`	列出已保存 token
`get_temu_access_token.py`	读取已保存 token
`temu_proxy.py`	通用网关转发（多 site）
`temu_file_download.py`	加签文件下载（多 site）

授权说明：references/access-token.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/check_linkfox_token.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_linkfox_token.py

,

get_temu_access_token.py

,

list_temu_access_tokens.py

,

save_temu_access_token.py

,

temu_file_download.py

,

temu_proxy.py

,

temu_token_guide.py

,

temu_us_file_download.py

,

temu_us_proxy.py

,

us_ads_searchrec_ad_create.py

,

us_ads_searchrec_ad_detail_query.py

,

us_ads_searchrec_ad_goods_create_query.py

,

us_ads_searchrec_ad_log_query.py

,

us_ads_searchrec_ad_modify.py

,

us_ads_searchrec_ad_reports_mall_query.py

,

us_ads_searchrec_ad_roas_pred.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

.