SellerSprite Market Research

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 market profiles aggregated by category/node.
• Market size: Monthly average sales volume, monthly average revenue, product count, etc.
• Competition structure: Seller/brand concentration, top concentration, Amazon self-operated share, FBA/FBM share.
• Input scale: Filter parameters GoodsCrn / BrandCrn / SellerCrn / EbcProportion / FbaProportion / FbmProportion / AmazonSelfProportion (min/max) must be 0~1 decimal values, see the parameter table below and references/api.md.
• New product opportunities: New product count, new product share, new product average price/rating/sales, etc.

How to Invoke

• API Endpoint: POST /sellersprite/market/research (complete params/response/error codes in references/api.md)
• Python Script: python scripts/amazonmarketresearch.py '<JSON params>' [--inline]
• Cost constraint: This tool consumes credits; the same session and parameter combination is called only once by default, with a 24h local cache in the script. On failure or empty results, do not automatically retry with different keywords, pagination, or postal codes; inform the user about additional consumption before continuing to search.

Output strategy (script default behavior):

• Always write the full response to <cwd>/nexscope/<YYYY-MM-DD>/<session>/data/nexscope-sellersprite-market-research-<timestamp>.json (<cwd> is the working directory at script execution time, i.e. the current project directory in Claude Code; <session> is taken from the SESSION_ID env var, auto-grouped by user task; do not write to /tmp, error if current directory is not writable)
• Response body <= 8 KB: print full JSON to stdout after saving
• Response body > 8 KB: print only summary to stdout after saving (top-level fields, common counts like total/costToken, length of largest list field + first 3 samples)
• Add --inline to force full output to stdout (still saves to disk)

Data reading tip: Check the summary first to decide if it's enough; when specific fields are needed, prefer using jq or ConvertFrom-Json to extract from the saved json file on demand, avoiding loading the entire JSON into context.

Key Parameters

The endpoint filter options are consistent with the sellerspritemarket_research tool (70+); below is a commonly used subset. For complete parameters and output fields, see references/api.md.

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

1. First present the top N market candidates, then show core metrics (market size, concentration, new product share).
2. Input parameter echo: GoodsCrn / BrandCrn / SellerCrn / EbcProportion / FbaProportion / FbmProportion / AmazonSelfProportion filters use 0~1 decimal values; when presenting to users, convert to percentage (e.g., passing 0.4 can be expressed as "product concentration cap of 40%"). If fields in the response data[] still carry "(%)" fields, their scale may differ from input scale, and the response values take precedence.
3. Other ratios, gross margins, and similar field units should reference references/api.md.
4. Display filter criteria echo so users can reproduce results.
5. If results are too few or too many, suggest users adjust key thresholds (e.g., concentration, scale thresholds).

Important Limitations

• Required parameter: marketplace
• Maximum 200 records per page
• Historical month range is limited by the third party (typically last 24 months)

Authentication

Set the NEXSCOPEAPIKEY environment variable. If credentials are missing or expire, visit https://www.nexscope.ai/help/skills-external-access?co-from=skillNS to top up credits.