This skill helps screen and rank Amazon category markets using SellerSprite market-research data.
Core Concepts
- Category market-level analysis: not a product-level list, but a market profile aggregated by category/node.
- Market size: average monthly sales volume, average monthly sales revenue, number of products, etc.
- Competitive structure: seller/brand concentration, top concentration, self-operated share, FBA/FBM share.
- Input scale: used for filtering GoodsCrn / BrandCrn / SellerCrn / EbcProportion / FbaProportion / FbmProportion / AmazonSelfProportion(
min*/max*) must be a decimal from 0 to 1, see the parameter table below andreferences/api.md。 - New product opportunities: number of new products, new product share, average price/rating/sales of new products, etc.
How to call
- API endpoint:
POST /sellersprite/market/research(for complete parameters/response/error codes seereferences/api.md) - Python script:
python scripts/sellersprite_market_research.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 switch keywords, turn pages, or change zip codes for continuous probing; if further retrieval is needed, 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-sellersprite-market-research-<timestamp>.json(<cwd>is the working directory when the script is executed, which in Claude Code is the current project directory;<session>is taken from the environment variableSESSION_ID, automatically aggregated according to the user's task;writing to /tmp is prohibited, if the current directory is not writable, report an error) - 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 fields, common counts such as
total/costToken, length of the largest list field + first 3 samples) - Add
--inlineto 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 to use jqorConvertFrom-Json to extract on demand from the saved json file, avoiding bringing the entire JSON into context.
Resolve authentication and computing 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。 - Response 401 or 402 status code
- Response indicates insufficient computing power or balance: the message contains "insufficient computing power balance/insufficient billing/insufficient balance/quota exceeded/insufficient balance/package expired/recharge required/please recharge", or content with a similar meaning.
Key Parameters
Interface filter options are consistent with the tool
_sellersprite_market_research(70+); the table below is a commonly used subset,for complete parameters and output fields seereferences/api.md。
| Parameter | Type | Required | Description |
|---|---|---|---|
| marketplace | string | Yes | Site code, default US |
| month | string | No | nearly or yyyyMM |
| nodeIdPath | string | No | Category node path |
| departmentKeyword | string | No | Category keyword path |
| page / size | integer | No | Pagination, default 1/50,size maximum 200 |
| orderField / orderDesc | string/boolean | No | Sort field and direction;orderDesc default true(descending) |
| minAvgRevenue / maxAvgRevenue | number | No | Monthly average sales amount range |
| minAvgUnits / maxAvgUnits | integer | No | Monthly average sales volume range |
| minGoodsCount / maxGoodsCount | integer | No | Product count range |
| minGoodsCrn / maxGoodsCrn | number | No | Product concentration (decimal 0–1, e.g. 0.4 means 40%, do not use integer 40) |
| minSellerCrn / maxSellerCrn | number | No | Seller concentration (decimal 0–1) |
| minBrandCrn / maxBrandCrn | number | No | Brand concentration (decimal 0–1) |
| minAmazonSelfProportion / maxAmazonSelfProportion | number | No | Amazon self-operated share (decimal 0–1) |
| minFbaProportion / maxFbaProportion | number | No | FBA share (decimal 0–1) |
| minFbmProportion / maxFbmProportion | number | No | FBM share (decimal 0–1) |
| minEbcProportion / maxEbcProportion | number | No | A+ count share (decimal 0–1) |
| minNewProportion / maxNewProportion | number | No | New product share (the scale may differ from the above columns; refer to references/api.md / schema) |
| minAvgPrice / maxAvgPrice | number | No | Average price range |
| minAvgRating / maxAvgRating | number | No | Average rating range |
| minAvgProfit / maxAvgProfit | number | No | Average gross margin (%) |
Usage Example
{
"marketplace": "US",
"month": "nearly",
"minAvgRevenue": 10000,
"maxGoodsCrn": 0.4,
"minNewProportion": 10,
"maxSellerCrn": 0.5,
"orderField": "total_amount",
"orderDesc": true,
"page": 1,
"size": 50
}
Display Rules
- First provide the top N market candidates, then display the core metrics (market size, concentration, new product share).
- Input parameter echo:
GoodsCrn/BrandCrn/SellerCrn/EbcProportion/FbaProportion/FbmProportion/AmazonSelfProportionThe corresponding filter is 0–1 decimal; when explaining to the user, it can be converted to a percentage (e.g. passing0.4can be stated as "product concentration upper limit 40%"). If the responsedata[]still contains a "(%)" field, the scale may differ from the input parameter; the returned value shall prevail. - The units of other ratio/gross margin fields shall be based on
references/api.md. - Display the filter condition echo so the user can reproduce it.
- If there are too few or too many results, suggest the user adjust key thresholds (such as concentration and size thresholds).
Important Limitations
- Required parameters:
marketplace - Up to 200 records per page
- The historical month range is subject to third-party limitations (usually the last 24 months)
Computing power consumption rules
Consumes 15 computing power.
Users pay fees due to computing power consumption. Please fully assess: when this skill needs to be called frequently, or the user's expectation of computing power consumption is insufficient, be sure to 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.