This skill queries the Jungle Scout Product Database via the LinkFox tool gateway, enabling multi-condition filtering of Amazon products across 10 marketplaces. Sellers can discover products by category, price range, sales volume, revenue, reviews, rating, BSR rank, Listing Quality Score (LQS), seller type, and more.
Core Concepts
The Jungle Scout product database is a multi-dimensional filtering tool at the Amazon product level, helping sellers quickly pinpoint target products from a massive number of products:
- Category product research: Filter products under a specific category by Amazon main category
- Sales/Revenue filtering: Define products with a suitable market size through monthly sales and monthly revenue ranges
- Competition assessment: Judge the intensity of competition through the number of reviews, rating, and number of sellers
- Listing quality assessment: LQS (Listing Quality Score, 1-10 points) helps discover products with large room for optimization
- Product type filtering: Distinguish FBA/FBM/AMZ seller types, standard size/oversize
- New product discovery: Filter recently listed new products by listing date
Internal paging: The API handles pagination automatically; you specify needCount to control how many results you want, and the backend fetches them across pages internally.
Data Fields
Key Output Fields
| Field | API Name | Description | Example |
|---|---|---|---|
| Product title | title | Product title | Yoga Mat Non Slip... |
| Brand | brand | Brand name | Liforme |
| Main category | category | Amazon main category | Sports & Outdoors |
| Category path | breadcrumbPath | Full category hierarchy | Sports & Outdoors > Exercise & Fitness |
| Price | price | Current selling price (USD) | 29.99 |
| Monthly sales | approximate30DayUnitsSold | Estimated sales in the last 30 days | 1200 |
| Monthly revenue | approximate30DayRevenue | Estimated revenue in the last 30 days (USD) | 35988.00 |
| BSR ranking | productRank | Best Sellers Rank | 3456 |
| Number of reviews | reviews | Cumulative number of reviews | 850 |
| Rating | rating | Average rating (1.0-5.0) | 4.5 |
| LQS | listingQualityScore | Listing quality score (1-10) | 8 |
| Number of sellers | numberOfSellers | Number of active sellers | 3 |
| Seller type | sellerType | Seller type (amz/fba/fbm) | fba |
| First listing date | dateFirstAvailable | Product first listing date | 2024-06-15 |
| Weight | weightValue / weightUnit | Product weight | 2.5 lbs |
| Size | lengthValue / widthValue / heightValue / dimensionsUnit | Product size | 24×8×8 inches |
| Parent ASIN | parentAsin | Parent ASIN | B0XXXXXXXX |
| Buy Box holder | buyBoxOwner | Current Buy Box holding seller | BrandName |
| Fee breakdown | feeBreakdown | FBA fees, referral fees, total fees, etc. | {fbaFee: 5.40, ...} |
| Subcategory ranking | subcategoryRanks | Subcategory BSR ranking list | [{subcategory: "Yoga Mats", rank: 12}] |
| Tokens consumed | costToken | Number of tokens consumed by this call | 5 |
Supported Marketplaces
us (United States), uk (United Kingdom), de (Germany), in (India), ca (Canada), fr (France), it (Italy), es (Spain), mx (Mexico), jp (Japan)
Default marketplace is us. Use us when the user doesn't specify a marketplace.
How to call
- API endpoint:
POST /tool-jungle-scout/product-database/query(For full parameters/responses/error codes, seereferences/api.md) - Python script:
python scripts/junglescout_product_database.py '<JSON 参数>' [--inline] - Cost constraints: This tool consumes computing power; by default, the same parameter combination in the same session is called only once, and the script has a 24h local cache. On failure/empty results, do not automatically try successive probes by changing keywords, paging, or changing the zip code; if further retrieval is needed, first explain to the user that additional consumption will be incurred.
Output strategy (script default behavior):
- Alwayswrite the full response to
<cwd>/linkfox/<YYYY-MM-DD>/<session>/data/linkfox-junglescout-product-database-<timestamp>.json(<cwd>The working directory when the script is executed, which in Claude Code is the current project directory;<session>Taken from the environment variableSESSION_ID, automatically aggregated according to the user task;Writing to /tmp is prohibited, if the current directory is not writable, an error is reported) - Response body ≤ 8 KB: after writing to disk, print the complete JSON to stdout
- Response body > 8 KB: after writing to disk, stdout outputs only a summary (top-level fields, common counts such as
total/costToken, the length of the largest list field + the first 3 samples) - Add
--inlineto force printing the full content to stdout (also written to disk)
Data reading recommendations: 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 bringing the entire JSON into context.
Resolve authentication and compute power issues
When the following abnormal situations occur, use references/onboarding.md to guide problem resolution:
Abnormal situations
- API Key not configured: the environment variable is not configured
LINKFOX_AGENT_API_KEY, andLINKFOXAGENT_API_KEY。 - is also not configured. Response 401 or 402 status code
- Response indicates insufficient compute power or balance: the message contains "insufficient compute power balance/insufficient billing/insufficient balance/quota exceeded/insufficient balance/package expired/recharge required/please recharge", or content with a similar meaning.
How to Build Queries
Only marketplace is required. All other parameters are optional filters — combine them to narrow results.
Principles for Building API Calls
- Site mapping: when the user says "US site" →
us, "Japan site" →jp, "Germany site" →de; when unspecified, default tous - Keywords:
includeKeywordssupports comma-separated multiple terms (title or ASIN), such asyoga mat,fitness;excludeKeywordsexclude products containing specific terms - Category matching:
categoriesmust use the English standard category name for the corresponding site, such as US siteSports & Outdoors、Home & Kitchen, etc.; multiple categories separated by commas - Numeric range: min/max are used in pairs, and only one end may be passed; for example, setting only
minSales=300means monthly sales ≥ 300 - Sorting:
sortadding-before a field name indicates descending order, such as-salessorted by sales from high to low; by default sorted bynameascending - Number of results:
needCountcontrols the total number of returned results; if not set, the default number is returned
Common Query Scenarios
1. Keyword search + filter by sales
{
"marketplace": "us",
"includeKeywords": "yoga mat",
"minSales": 300,
"maxSales": 5000,
"sort": "-sales",
"needCount": 50
}
2. Category + price range filtering
{
"marketplace": "us",
"categories": "Home & Kitchen",
"minPrice": 15,
"maxPrice": 50,
"minSales": 100,
"sort": "-revenue",
"needCount": 50
}
3. High-rating low-competition product selection (few reviews but high rating)
{
"marketplace": "us",
"categories": "Beauty & Personal Care",
"minRating": 4.0,
"maxReviews": 200,
"minSales": 100,
"sort": "-sales",
"needCount": 50
}
4. FBA-only product filtering
{
"marketplace": "us",
"includeKeywords": "phone stand",
"sellerTypes": "fba",
"productTiers": "standard",
"minSales": 200,
"sort": "-sales",
"needCount": 50
}
5. Exclude top brands + discover blue ocean opportunities
{
"marketplace": "us",
"categories": "Sports & Outdoors",
"excludeTopBrands": true,
"minSales": 300,
"maxReviews": 500,
"minRating": 4.0,
"sort": "-sales",
"needCount": 50
}
6. Discover new products by listing date
{
"marketplace": "us",
"categories": "Electronics",
"minUpdatedAt": "2026-01-01",
"minSales": 50,
"sort": "-sales",
"needCount": 50
}
Display Rules
- Table format: Present results in a structured table with key columns: title, brand, price, monthly sales, monthly revenue, BSR rank, reviews, rating, LQS
- Sorting note: Remind the user what sorting was applied and how many results were returned
- Highlight insights: Mark products with notably low reviews but high sales (potential opportunity), or high LQS scores
- Fee breakdown: When users ask about profitability, include feeBreakdown details (FBA fee, referral fee, total fees)
- Image links: Include
imageUrlwhen displaying individual product details - Error handling: When a query fails, explain the reason based on the error response and suggest adjusting parameters
Important Limitations
- marketplace is required: each query must specify a site
- Category names must match:
categoriesthe value must exactly match the standard main category name for the corresponding site - Keyword limits:
includeKeywords/excludeKeywordsat most 100 items each, each item up to 50 characters - Data timeliness: data comes from Jungle Scout periodic updates, not real-time data
- Rating range:
minRating/maxRatingvalues 1.0-5.0 - Weight unit:
minWeight/maxWeightin pounds
User Expression & Scenario Quick Reference
Applicable - Amazon product multi-condition filtering and discovery:
| User Says | Scenario |
|---|---|
| "Help me find yoga mats with monthly sales above 500" | Keyword + sales filtering |
| "What good products are there in the US site kitchen category under 30 dollars" | Category + price filtering |
| "Blue ocean products with few reviews but high ratings" | High-rating, low-competition product selection |
| "Find FBA standard-size phone stands" | Seller type + product size filtering |
| "Sports category opportunities excluding major brands" | Exclude top brands |
| "Which recently launched electronics are selling well" | New product discovery |
| "Home products with a BSR rank within 10,000" | BSR rank filtering |
| "High-sales products with an LQS below 5" | Listing optimization opportunities |
Not applicable - Beyond product database filtering:
- Keyword search volume/trend analysis (requires a keyword historical search volume tool)
- ABA search term ranking (requires an ABA tool)
- Product detail page/Listing content analysis
- Advertising/PPC campaign strategy
- Non-Amazon platform product data
Boundary judgment: When users say "product selection", "find products", or "market research", if their need is to filter products by specific criteria (price, sales, category, reviews, etc.) from Amazon's product catalog, this skill applies. If they need keyword-level search volume data, advertising insights, or non-Amazon platform data, it does not apply.
Computing power consumption rules
Billed by dynamic rules: computing power consumed = actual number of pages queried × 63.75.
Important: This skill's service is calculated dynamically by a multiplier and may consume a large amount of computing power at once. You must remind the user and let the user decide whether to continue.
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.
For more high-quality, professional cross-border e-commerce skills, visit LinkFox Skills.