Product Research
Command
/product-research "{PRODUCT_KEYWORD}" {SITE}
Goal
Evaluate a product opportunity and produce a decision-ready research report.
Credential Preflight
Before any data call, read references/runtime-credential-preflight.md when it is available.
- If SellerSprite MCP is not configured, unavailable, or returns an authentication error, ask the user for the SellerSprite MCP API key before product research.
- If Gemini/GLM validation is part of the requested output and model keys are missing, ask for the missing keys before validation.
- Do not continue with mock MCP data or fabricated opportunity conclusions.
- Do not write provided keys into reports, raw files, dashboards, examples, or the open-source repository.
Required Reference
Read references/sellersprite-mcp-api.md before execution when it is available.
Normalize GB to SellerSprite MCP UK before tool calls.
Data Calls
product_node: map the product direction to relevant Amazon category nodes.product_research: collect candidate products and opportunity-filtered samples.competitor_lookup: compare representative products by keyword, ASIN, brand, seller, node, month, and variation setting.market_research and market_research_statistics: quantify category market size and competition.market_price_distribution, market_rating_distribution, market_product_demand_trend: check pricing, maturity, and demand trend.market_product_concentration, market_brand_concentration, market_seller_concentration: quantify head concentration.keyword_miner, keyword_research, keyword_research_trends: validate keyword demand, CPC/PPC, purchase rate, supply-demand ratio, and trend.traffic_listing, traffic_source, traffic_extend: inspect traffic patterns for representative competitors when available.review: collect VOC from representative ASINs.google_trend: optional external demand validation.trademark_country_list, trademark_list, trademark_stats, trademark_detail: use only for naming/IP/trademark risk checks.
If MCP cannot answer a required question, mark the gap and then use a crawl/browser fallback only for that missing evidence.
Workflow
- Clarify product keyword and site.
- Normalize site code for SellerSprite MCP.
- Collect representative products using
product_research and competitor_lookup.
- Collect keyword, category, market distribution, and traffic context from MCP.
- Save raw or compact MCP responses before reasoning.
- Label product attributes: price, rating, reviews, feature, material, scenario.
- Compare opportunity patterns with evidence references.
- Analyze VOC and barriers using review/category/trademark evidence or labeled assumptions.
- Output decision: enter, observe, or reject.
Research Dimensions
| Dimension |
Questions |
| Demand |
Is there enough search and sales demand? |
| Competition |
Are review moats and brands too strong? |
| Differentiation |
Can the product be meaningfully improved? |
| Profit |
Is price/CPC/return risk acceptable? |
| Supply chain |
Is production feasible? |
| Launch path |
What keywords and segments should be tested first? |
Do not invent supply-chain, patent, compatibility, seasonality, inventory, or certification risks. Use MCP data first, then existing user files, then explicitly labeled assumptions or crawl evidence.
Output
Save under:
product-research-reports/{PRODUCT_KEYWORD}_{SITE}_{YYYYMMDD}/report.md
Do not publish raw product exports or private cost assumptions.
1---2name: product-research3description: Amazon product opportunity research using SellerSprite MCP and LLM reasoning. Use when the user runs `/product-research "{PRODUCT_KEYWORD}" {SITE}` to research a product direction, evaluate market opportunity, competitors, VOC, barriers, and launch decision.4---56# Product Research78## Command910```text11/product-research "{PRODUCT_KEYWORD}" {SITE}12```1314## Goal1516Evaluate a product opportunity and produce a decision-ready research report.1718## Credential Preflight1920Before any data call, read `references/runtime-credential-preflight.md` when it is available.2122- If SellerSprite MCP is not configured, unavailable, or returns an authentication error, ask the user for the SellerSprite MCP API key before product research.23- If Gemini/GLM validation is part of the requested output and model keys are missing, ask for the missing keys before validation.24- Do not continue with mock MCP data or fabricated opportunity conclusions.25- Do not write provided keys into reports, raw files, dashboards, examples, or the open-source repository.2627## Required Reference2829Read `references/sellersprite-mcp-api.md` before execution when it is available.30Normalize `GB` to SellerSprite MCP `UK` before tool calls.3132## Data Calls3334- `product_node`: map the product direction to relevant Amazon category nodes.35- `product_research`: collect candidate products and opportunity-filtered samples.36- `competitor_lookup`: compare representative products by keyword, ASIN, brand, seller, node, month, and variation setting.37- `market_research` and `market_research_statistics`: quantify category market size and competition.38- `market_price_distribution`, `market_rating_distribution`, `market_product_demand_trend`: check pricing, maturity, and demand trend.39- `market_product_concentration`, `market_brand_concentration`, `market_seller_concentration`: quantify head concentration.40- `keyword_miner`, `keyword_research`, `keyword_research_trends`: validate keyword demand, CPC/PPC, purchase rate, supply-demand ratio, and trend.41- `traffic_listing`, `traffic_source`, `traffic_extend`: inspect traffic patterns for representative competitors when available.42- `review`: collect VOC from representative ASINs.43- `google_trend`: optional external demand validation.44- `trademark_country_list`, `trademark_list`, `trademark_stats`, `trademark_detail`: use only for naming/IP/trademark risk checks.4546If MCP cannot answer a required question, mark the gap and then use a crawl/browser fallback only for that missing evidence.4748## Workflow49501. Clarify product keyword and site.512. Normalize site code for SellerSprite MCP.523. Collect representative products using `product_research` and `competitor_lookup`.534. Collect keyword, category, market distribution, and traffic context from MCP.545. Save raw or compact MCP responses before reasoning.556. Label product attributes: price, rating, reviews, feature, material, scenario.567. Compare opportunity patterns with evidence references.578. Analyze VOC and barriers using review/category/trademark evidence or labeled assumptions.589. Output decision: enter, observe, or reject.5960## Research Dimensions6162| Dimension | Questions |63|---|---|64| Demand | Is there enough search and sales demand? |65| Competition | Are review moats and brands too strong? |66| Differentiation | Can the product be meaningfully improved? |67| Profit | Is price/CPC/return risk acceptable? |68| Supply chain | Is production feasible? |69| Launch path | What keywords and segments should be tested first? |7071Do not invent supply-chain, patent, compatibility, seasonality, inventory, or certification risks. Use MCP data first, then existing user files, then explicitly labeled assumptions or crawl evidence.7273## Output7475Save under:7677```text78product-research-reports/{PRODUCT_KEYWORD}_{SITE}_{YYYYMMDD}/report.md79```8081Do not publish raw product exports or private cost assumptions.
Ethan-paseya