linkfox-geekbi-temu-market-research

Temu Category & Keyword Demand Research

This skill researches Temu category opportunities and buyer-demand keywords from public marketplace data. Use only the endpoints needed for the user's request, and read references/api.md for the full request and response contract.

The site-list and category-list endpoints are helper capabilities. A helper-only request must not auto-select this skill unless the user explicitly invokes it or the skill is already active.

Core Concepts

• regionId selects the marketplace. Resolve it from a non-null positive sites[].regionId; never substitute siteId. The gateway default is regionId: 211 (United States).
• dsr is a supply-demand signal, not a standalone go/no-go score. Cross-check demand scale, recent growth, item/shop supply, and price.
• Search responses are paginated items[]. Defaults are page: 1 and size: 20; size is 1–200 and page * size must not exceed 10,000. order has no gateway default; when supplied, it must be asc or desc (case-insensitive).
• Range filters are limited to dsr, totalSold, avgPrice, totalSales, itemCount, and mallCount, each with Min / Max. Never make a minimum greater than its maximum; all except dsr must be non-negative.
• Use site/category helpers only when the user has not supplied a valid ID. Stop if no unambiguous ID is returned.
• Do not launch a paid search merely to answer a site-list or category-tree request.

Intent	Endpoint	Script
Compare category demand and competition	/geekbi/temu/categorySearch	geekbi_temu_category_search.py
Discover and compare buyer-demand keywords	/geekbi/temu/keywordSearch	geekbi_temu_keyword_search.py
Resolve Temu marketplaces	/geekbi/temu/siteList	geekbi_temu_site_list.py
Browse the category tree	/geekbi/temu/categoryList	geekbi_temu_category_list.py

Endpoint: /geekbi/temu/categorySearch

Request

• Category research uses keyword to compare market capacity and competition. Use the separate category-list helper with parentCatId when a trusted category tree must be traversed; categorySearch itself does not accept catLevel or parentCatId.
• Use keyword for a Chinese or English category name. catLevel and parentCatId are response/helper concepts, not categorySearch request fields.
• Filter or rank broad demand with totalSold; use dsr for candidate discovery. Treat monthSoldRate and monthSalesRate as response fields for recent-growth analysis, not as range-filter request fields.
• itemCount and mallCount can be filtered with Min/Max fields. Period *ItemCount and *MallCount values are response-only changes and can be negative.

# Compare US pet-related categories by cumulative demand
python scripts/geekbi_temu_category_search.py '{"regionId":211,"keyword":"宠物","totalSoldMin":1000,"sort":"totalSold","order":"desc","page":1,"size":20}'

Response

Path	Meaning
items[].catId / items[].parentCatItems[]	Category identity and verified hierarchy
items[].totalSold / totalSales / avgPrice	Cumulative demand, revenue, and average price
items[].itemCount / mallCount	Product and shop supply
items[].semiManagedItemCount / semiManagedMallCount	Semi-managed supply counts
items[].day* / week* / month*	Period demand, supply changes, and growth rates
errcode / errmsg	Gateway business status; verified success is 200 / ok

Endpoint: /geekbi/temu/keywordSearch

Request

• Keyword research uses keyword for a specific phrase or catIds for category-led discovery. Combine them only when the user explicitly wants a phrase within a category.
• Resolve catIds from valid categories[].catId values or a verified category-search result. Prefer level-1 or level-2 IDs for broad discovery.
• Search a supplied phrase with keyword without silently translating or replacing it.
• For category-led discovery, use catIds from the category helper. Multiple IDs match any supplied category.
• Rank hot terms with totalSold and blue-ocean candidates with dsr. Analyze recent demand from returned monthSoldRate or monthSalesRate; these period metrics are not range-filter request fields. Use firstOnSaleTimeMin/Max for market recency.
• firstOnSaleTimeMin/Max use ISO-8601 timestamps and describe the earliest associated product listing time.

# Discover dress-related demand terms within a verified category
python scripts/geekbi_temu_keyword_search.py '{"regionId":211,"keyword":"dress","catIds":[27011],"totalSoldMin":1000,"sort":"totalSold","order":"desc","page":1,"size":20}'

Response

Path	Meaning
items[].keyword / items[].cnKeyword	Search phrase and optional Chinese form
items[].catIds / items[].catItems[]	Categories associated with a keyword
items[].totalSold / totalSales / avgPrice	Cumulative demand, revenue, and average price
items[].itemCount / mallCount	Product and shop supply
items[].semiManagedItemCount / semiManagedMallCount	Semi-managed supply counts
items[].day* / week* / month*	Period demand, supply changes, and growth rates
items[].firstOnSaleTime	Earliest associated product listing time; not keyword creation time
errcode / errmsg	Gateway business status; verified success is 200 / ok

Endpoint: /geekbi/temu/siteList

Request

# Resolve a non-US marketplace; use regionId, not siteId
python scripts/geekbi_temu_site_list.py '{}'

Response

Path	Meaning
sites[].regionId	IDs accepted by the research endpoints
errcode / errmsg	Gateway business status; verified success is 200 / ok

Endpoint: /geekbi/temu/categoryList

Request

# Resolve a trusted category path when only a category name is known
python scripts/geekbi_temu_category_list.py '{}'
python scripts/geekbi_temu_category_list.py '{"parentCatId":27011}'

Response

Path	Meaning
categories[].catId	IDs accepted by the research endpoints
errcode / errmsg	Gateway business status; verified success is 200 / ok

Fields can be absent or null. Preserve runtime JSON types and raw rate values; do not replace missing values with zero.

How to call

• API endpoint：POST /geekbi/temu/categorySearch、POST /geekbi/temu/keywordSearch、POST /geekbi/temu/siteList or POST /geekbi/temu/categoryList(for full parameters/responses/error codes, see references/api.md）
• Python script：python scripts/geekbi_temu_category_search.py '<JSON 参数>' [--inline]、python scripts/geekbi_temu_keyword_search.py '<JSON 参数>' [--inline]、python scripts/geekbi_temu_site_list.py '{}' [--inline] or python scripts/geekbi_temu_category_list.py '<JSON 参数>' [--inline]
• Cost constraints: Category search and keyword search each consume 15 compute units per call; site list and category list do not consume compute units; the same endpoint with the same parameter combination uses a 24h local cache, and by default is called only once per session.--inline does not bypass the cache;--no-cache skips cache reads and writes and forces a real request; paid endpoints may deduct compute units again, while free auxiliary endpoints only force a refresh. Failures, empty results, or transient errors must not be automatically retried, nor must keywords, pages, sites, or filter conditions be automatically changed for continuous probing; if paid retrieval needs to continue, first explain to the user that additional consumption will be incurred.

Output strategy (default script behavior)：

• Alwayswrite the complete response to <cwd>/linkfox/<YYYY-MM-DD>/<session>/data/linkfox-geekbi-temu-market-research-<timestamp>.json；<cwd> is the current working directory when the script is executed,<session> is taken from the environment variable SESSION_ID, and is automatically generated when not set. If the current directory is not writable, report an error directly and do not fall back to the user directory or system temporary directory.
• Response body ≤ 8 KB: after saving to disk, print the complete JSON to stdout
• Response body > 8 KB: after saving to disk, stdout outputs only a summary (top-level status fields, common business counts, ignoring columns the length of the largest business list + the first 3 samples)
• Add --inline to force full printing to stdout (also saved to disk)

Data reading suggestions: First look at the summary to determine whether it is sufficient; when specific fields are needed, prefer using jqorConvertFrom-Json to extract on demand from the saved json file, avoiding putting the entire JSON into the context.

Resolve authentication and compute unit issues

When the following abnormal situations occur, use references/onboarding.md to guide problem resolution:

Abnormal situation

• API Key not configured: The environment variable is not configured LINKFOX_AGENT_API_KEY or the compatible key LINKFOXAGENT_API_KEY。
• Response 401 or 402 status code。
• Response indicates insufficient compute units or balance: The message contains “insufficient compute balance/insufficient billing/insufficient balance/quota exceeded/insufficient balance/package expired/recharge required/please recharge” or similar meaning.

Display Rules

1. State marketplace name, regionId, currency, filters, sort, page, and page size.
2. For categories, show the full category path, catId, level, demand/revenue, average price, item/shop supply, semi-managed supply, and relevant growth fields.
3. For keywords, show the phrase, associated category path/IDs, demand/revenue, average price, item/shop supply, semi-managed supply, earliest listing time, and relevant growth fields.
4. Label monetary values with the selected site's currency. Keep raw rate units explicit and do not silently convert them.
5. Mark incomplete pagination as a sample. Keep IDs available for downstream product, shop, or keyword research.
6. Preserve null, missing fields, and upstream extensions rather than inventing values.

Important Limitations

• This skill researches public Temu market data; it does not access or operate a seller account.
• total can be capped at 10,000. A partial page or uncompleted pagination is not the entire marketplace.
• dsr, growth, sales, or supply alone cannot prove an opportunity or predict future performance.
• firstOnSaleTime is the earliest associated product listing time, not keyword creation time.
• The category tree can require several parentCatId calls; do not guess intermediate IDs.
• Do not automatically call helpers when valid IDs are already available.
• Do not retry paid endpoints with changed filters or another page after empty results without user confirmation.

User Expression & Scenario Quick Reference

Applicable: “Check pet category opportunities on Temu US site”, “Find blue ocean categories with monthly demand growth”, “Dig out hot search terms for Temu dresses”, “Compare keyword supply-demand and price bands”, “Temu category/keyword demand research”.

Adjacent: Resolve an unknown non-US marketplace before research. For category-led keyword discovery, resolve a trusted catId from the category tree or a verified category result.

Not an automatic trigger: A request solely to enumerate Temu sites, regionId values, category-tree nodes, or catId values does not auto-trigger this skill. Route category-tree/catId-only requests to linkfox-temu-category-search. If this GeekBI skill was explicitly invoked or is already active, its site/category helpers may be called independently.

Not applicable: Temu product detail, shop-only benchmarking, review analysis, seller-center operations, listing changes, fulfillment, advertising, or research on another marketplace.

Compute unit consumption rules

Category search and keyword search each consume 15 compute units per call; site list and category list do not consume compute units.

Users will pay compute units for category search and keyword search. Before high-frequency calls, paging, or re-searching with changed conditions, the user must decide whether to continue.

Feedback:

Auto-detect and report feedback via the Feedback API when any of the following apply:

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

Call the feedback API as specified in references/api.md. Do not interrupt the user's flow.

---

For more high-quality, professional cross-border e-commerce skills, visit LinkFox Skills.