This skill guides you on how to generate comprehensive AI-powered market insight reports for Amazon keywords, helping sellers make data-driven product selection and market entry decisions.
Core Concepts
This tool generates a comprehensive business insight report by analyzing six core dimensions of an Amazon keyword:
- Market Potential - Search volume, demand trends, and growth opportunity
- Product Characteristics - Common product attributes, materials, features
- User Reviews - Customer sentiment, pain points, and satisfaction drivers
- Customer Profile - Buyer demographics, preferences, and behavior patterns
- Search Trends - Keyword popularity trajectory and seasonality
- Pricing Analysis - Price distribution, competitive pricing landscape
The report is generated by AI from real-time Amazon data and delivered as a structured Markdown document. It is a snapshot analysis for decision support, not a real-time monitoring tool.
Parameters
| Parameter | Type | Required | Description | Default |
|---|---|---|---|---|
| site | string | Yes | Amazon marketplace code (currently US only) | US |
| keyword | string | Yes | The search keyword to analyze | - |
Supported Marketplaces
Currently only US (United States) is supported. Always set site to US. If a user requests other marketplaces, inform them this tool currently only covers the US market.
How to call
- API endpoint:
POST /amazon/opportunity/reportByKeyword(for full parameters/responses/error codes, seereferences/api.md) - Python script:
python scripts/amazon_opportunity_report.py '<JSON 参数>' [--inline] - Cost constraints: This tool consumes compute; by default, the same parameter combination is called only once per session, and the script has a 24h local cache. On failure/empty results, do not automatically try different keywords, paginate, or change the zip code in repeated probing; if further retrieval is needed, first explain to the user that it will incur additional consumption.
Output strategy (default script behavior):
- Alwayswrite the full response to
<cwd>/linkfox/<YYYY-MM-DD>/<session>/data/linkfox-amazon-opportunity-report-by-keyword-<timestamp>.json(<cwd>is the working directory when the script runs, 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, and if the current directory is not writable, report an error) - Response body ≤ 8 KB: after saving to disk, print the full 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, the length of the largest list field + the 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 using jqorConvertFrom-Json to extract on demand from the saved json file, avoiding bringing the entire JSON into context.
Resolve authentication and compute issues
When the following abnormal situations occur, use references/onboarding.md to guide 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 compute or balance: The message contains "insufficient compute balance/insufficient billing/insufficient balance/quota exceeded/insufficient balance/package expired/recharge required/please recharge", or content with a similar meaning.
Usage Examples
1. Basic Market Opportunity Report
帮我搜索美国站,关键词是 hair mousse travel size 的商业洞察报告
2. Niche Product Research
帮我生成美国站关键词 magnetic shelves for whiteboard 的商业洞察报告
3. Trend-Based Product Selection
我想了解美国站 solar power ac unit 这个关键词的商业洞察,帮我生成报告
Display Rules
- No subjective advice: Apply the AI-generated analysis without adding your own business recommendations
- Clarify scope: Remind users the report is based on a point-in-time snapshot and serves as a reference for decision-making
- Error handling: When a query fails, explain the reason based on the
msgfield and suggest checking the keyword or trying again - No secondary analysis: This tool's output cannot be fed into data query tools for further processing - inform users if they attempt this
Important Limitations
- US only: Currently only supports the United States marketplace (site = US)
- Non-structured output: Returns a Markdown report, not structured JSON data. Cannot be used with data query tools for secondary aggregation or analysis
- Processing time: Report generation involves AI analysis and may take longer than simple data lookups
- Snapshot data: Reports reflect data at the time of generation and are not continuously updated
User Expression & Scenario Quick Reference
Applicable - Comprehensive keyword-level market analysis:
| User Says | Scenario |
|---|---|
| "Help me analyze this keyword's market opportunity" | Market opportunity assessment |
| "Generate a market insight report for XX" | Full insight report |
| "What's the competitive landscape for XX" | Competition & pricing analysis |
| "Consumer profile for XX product" | Customer behavior insights |
| "Is XX keyword worth entering" | Market entry evaluation |
| "product selection report", "business insights" | Chinese market research requests |
Not applicable - Needs beyond comprehensive report generation:
- Real-time keyword ranking tracking (use ABA or SIF tools)
- Individual product detail lookup (use product detail tools)
- Historical price tracking (use Keepa)
- Review-level analysis for specific ASINs (use review tools)
- Advertising / PPC strategy
Boundary judgment: When users say "market analysis" or "product research", if they want a holistic, multi-dimensional overview of a keyword's market opportunity, this skill applies. If they need specific data points (exact sales numbers, individual product details, keyword rankings over time), direct them to the appropriate specialized tool.
Compute consumption rules
Billed according to dynamic rules: compute consumed = compute consumed by input + 7.5 × compute consumed by output.
Important: The services of this skill are dynamically calculated by a multiplier and may consume a large amount of compute at once. The user must be reminded, and the user decides 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.