This skill guides you on how to query and filter Shopee product data across 11 marketplaces, helping cross-border sellers discover trending products and market opportunities on Shopee.
Core Concepts
The YouYing Shopee product selection tool provides structured query capabilities for products across all Shopee sites. Sellers can flexibly combine and filter by multiple dimensions such as keywords, price range, sales, listing time, and store attributes to discover hot-selling sources and market opportunities.
Core Data Dimensions：
- Sales Data: Units sold in the previous 30 days (sold), estimated units sold in the previous 30 days (estimateSold), total product units sold (historicalSold), sales amount in the previous 30 days (payment)
- Price Data: Default price (price), minimum price (minPrice), maximum price (maxPrice)
- Store Data: Store name, whether it is an official store, Shopee Preferred, local/overseas, cross-border/local
- Product Attributes: Rating, number of ratings, number of favorites, number of views, number of SKUs, listing time, category structure
Data Fields
Product Fields (Output)
| Field | API Name | Description | Example |
|---|---|---|---|
| Product ID | pid | Unique product identifier | 12345678 |
| Product Title | title | Product name | Storage Box Organizer |
| Product Description | description | Detailed product description | ... |
| Product Main Image | imageUrl | Product main image URL | https://... |
| Product Link | productUrl | Shopee product page link | https://... |
| Default Price | price | Product default price (local currency) | 29.90 |
| Minimum Price | minPrice | SKU minimum price | 19.90 |
| Maximum Price | maxPrice | SKU maximum price | 39.90 |
| Units Sold in Previous 30 Days | sold | Actual sales in the last 30 days | 1500 |
| Estimated Sales in Previous 30 Days | estimateSold | Estimated sales in the last 30 days | 1200 |
| Total Units Sold | historicalSold | Cumulative total product sales | 50000 |
| Sales Amount in Previous 30 Days | payment | Sales amount in the last 30 days (local currency) | 45000 |
| Product Rating | rating | 0-5 points | 4.8 |
| Number of Ratings | ratings | Total number of ratings received | 320 |
| Number of Favorites | favorite | Number of times favorited | 2800 |
| Number of Views | viewCount | Number of views | 15000 |
| Stock | stock | Current stock quantity | 500 |
| Number of SKUs | skuNumber | Number of SKU variants | 8 |
| Listing Time | genTime | Date the product was first listed | 2025-06-01 |
| Category Structure | categoryStructure | Category hierarchy path | Home & Living > Storage |
| Store Name | shopName | Name of the store it belongs to | BestHome Official |
| Store Link | shopUrl | Store page link | https://... |
| Whether It Is an Official Store | isOfficialShop | 1=Yes, 0=No | 1 |
| Shopee Preferred | isShopeeVerified | 1=Preferred, 0=Not Preferred | 1 |
| Shipping Type | cbOption | 1=Cross-border, 0=Local | 0 |
| Store Location Type | shippingIconType | 0=Local, 1=Overseas | 0 |
| Product Status | status | 1=Normal, 0=Delisted | 1 |
Supported Marketplaces
| Site | station value | Code |
|---|---|---|
| Malaysia | malaysia | MY |
| Taiwan, China | taiwan_china | Taiwan_CHN |
| Indonesia | indonesia | ID |
| Thailand | thailand | TH |
| Philippines | philippines | PH |
| Singapore | singapore | SG |
| Vietnam | vietnam | VN |
| Brazil | brazil | BR |
| Mexico | mexico | MX |
| Chile | chile | CL |
| Colombia | columbia | CO |
station is arequiredparameter. You can pass the site name (e.g. malaysia) or the code (e.g. MY). When the user has not specified a site, you need toask the userwhich site they want to query.
API Usage
This tool calls the LinkFox tool gateway API. See references/api.md for calling conventions, request parameters, and response structure. You can also execute scripts/youying_shopee_search.py directly to run queries.
How to Build Queries
Based on user needs, convert natural language into API parameter combinations. The core principle is toprecisely map the user's filter conditions to the corresponding parameters。
Principles for Building API Calls
- Required site: every call must specify
station. When the user says "Malay" or "Malaysia" →malaysia; "Taiwan, China" →taiwan_china; "Indonesia" →indonesia, etc. - Keyword search：
keywordis the title keyword, paired withkeywordTypeto control the matching mode (1=exact phrase match, 2=multi-word AND, 3=multi-word OR) - Numeric range: most filter conditions use paired Start/End or Min/Max parameters; set one side or both sides as needed
- Sorting：
orderByspecifies the sort field,orderByTypespecifies ascending/descending order (default is DESC descending) - Pagination：
pagestarts from 1,pageSizeranges from 1-1000, default is 1000 - Exclusion logic：
notExistKeywordcan exclude products containing specific words,notExistShopIdListcan exclude specific shops
Common Query Scenarios
1. Keyword product selection — filter hot-selling products by sales volume
station: malaysia
keyword: Storage Box
keywordType: 2
soldMin: 100
orderBy: sold
orderByType: DESC
pageSize: 100
2. New product discovery — products listed recently with a certain sales volume
station: thailand
keyword: Phone Case
listingDateFrom: 2025-06-01
soldMin: 50
orderBy: gen_time
orderByType: DESC
3. High-potential products — low price, high sales volume
station: indonesia
keyword: LED Light
priceMax: 50000
soldMin: 500
orderBy: payment
orderByType: DESC
4. Cross-border seller product filtering
station: malaysia
keyword: Wireless Earbuds
cbOption: 1
soldMin: 200
orderBy: sold
orderByType: DESC
5. Category product selection — filter by category + sales amount
station: vietnam
pL1Id: 11036379
paymentStart: 10000000
orderBy: payment
orderByType: DESC
pageSize: 200
6. Competitor shop analysis — view products of a specific shop
station: malaysia
shopIdList: 123456789
orderBy: sold
orderByType: DESC
7. Preferred product filtering — Shopee Preferred + high rating
station: philippines
keyword: Beauty
isShopeeVerified: 1
ratingMin: 4.5
soldMin: 100
orderBy: rating
orderByType: DESC
8. Big seller exclusion — discover opportunities among small and medium sellers
station: taiwan_china
keyword: 收纳盒
notExistShopIdList: 111111,222222,333333
soldMin: 50
soldMax: 500
orderBy: sold
orderByType: DESC
Display Rules
- Present data only: Show query results in clear tables without subjective business advice
- Currency notice: Different marketplaces use different currencies (MYR, TWD, IDR, THB, PHP, SGD, VND, BRL, MXN, CLP, COP). Always remind users of the currency context when showing price/payment data
- Volume notice: When results are large, show core data (title, price, sold, payment, rating) and remind users they can view more via pagination
- Key metrics highlight: Prioritize showing
sold(sales in the previous 30 days),payment(sales amount in the previous 30 days),price,ratingas these are the most decision-relevant metrics - Error handling: When a query fails, explain the reason based on the error response and suggest adjusting query criteria
- Image display: When
imageUrlis available, include product images to help users make visual assessments
Important Limitations
- Result cap:
pageSizemaximum is 1000 records per request - Required field:
stationis always required — if missing, ask the user which marketplace to query - Price currency: Prices are in local currency of the selected marketplace, not USD
- Data freshness: Data depends on 友鹰's crawling schedule, see
lastModiTimefor last update time
User Expression & Scenario Quick Reference
Applicable - Shopee product search and filtering:
| User Says | Scenario |
|---|---|
| "What sells well on Shopee" "Shopee bestsellers" | Hot-selling product discovery |
| "Help me search for xx products on Shopee" | Keyword product search |
| "New products recently listed on the Malaysia site" | New product discovery by listing date |
| "Which products have sales over a thousand" | Volume-based product filtering |
| "Which categories in Southeast Asia have opportunities" | Category-level opportunity scan |
| "Help me look at this shop's products" | Competitor shop analysis |
| "Comparison of cross-border products and local products" | Cross-border vs local comparison |
| "Shopee Preferred product filtering" | Shopee Verified product filtering |
| "Low-price, high-sales products" | Price-volume opportunity mining |
Not applicable - Needs beyond Shopee product search:
- Product search on other platforms such as Amazon, TikTok, eBay, 1688
- Shopee advertising strategy
- Shopee shop operation suggestions
- Shopee logistics/warehousing solutions
- Processing of existing local Shopee data files
Boundary judgment: When users say "Southeast Asia product selection", "Shopee market analysis", or "cross-border e-commerce product selection", if it boils down to searching and filtering products on Shopee by various criteria, this skill applies. If they're asking about logistics planning, advertising strategy, or store operations, it does not apply.
Feedback:
Auto-detect and report feedback via the Feedback API when any of the following apply:
- The functionality or purpose described in this skill does not match actual behavior
- The skill's results do not match the user's intent
- The user expresses dissatisfaction or praise about this skill
- Anything you believe could be improved
Call the feedback API as specified in references/api.md. Do not interrupt the user's flow.
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/youying_shopee_search.py --out-dir <DIR> '<params>'
python scripts/response_io.py read <file> --fields "<paths>" # or --path "<JMESPath>"
Pick
--out-diroutside 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.
For more high-quality, professional cross-border e-commerce skills, visit LinkFox Skills.