liangdabiao/amazon-sorftime-research-MCP-skill

What it solves

This project provides a comprehensive suite of AI-driven analysis tools for Amazon sellers to conduct competitor research, product selection, and listing optimization. It automates the process of gathering data from multiple e-commerce data services (Sorftime, Sif, Xiyou, and SellerSprite) and transforms raw data into actionable business decisions and high-converting product listings.

How it works

The system is built as a collection of "skills" for the Model Context Protocol (MCP), allowing an LLM (specifically via Claude Code CLI) to execute complex workflows. It integrates several third-party APIs to perform the following:

• Market & Product Research: Uses a five-dimensional scoring model (market size, growth potential, competition, barriers, and profit) to evaluate product categories.
• Competitor Analysis: Penetrates individual listings to analyze traffic sources, keyword layouts, and pricing strategies.
• VOC (Voice of Customer) Analysis: Performs deep sentiment analysis on reviews to identify pain points across six dimensions (e.g., electronic failure, design flaws).
• Listing Engineering: Implements an eight-step workflow (from keyword layering to QA design) to create listings based on semantic coverage and user intent rather than simple keyword stuffing.
• Reporting: Automatically generates reports in Markdown, HTML dashboards, and Excel files.

Who it’s for

• Amazon Sellers: Those looking to find "blue ocean" opportunities and optimize their product visibility.
• E-commerce Analysts: Professionals needing automated, data-backed competitor and market research.
• Product Managers: Individuals designing new products based on identified customer pain points.

Highlights

• Multi-Service Integration: Combines data from Sorftime, Sif, Xiyou, and SellerSprite into a single interface.
• LLM-Driven Decision Making: Uses LLMs to analyze, insight, and decide on product viability rather than just providing raw data.
• Semantic Listing Builder: Optimizes listings for modern AI-driven shopping trends (like Alexa and Rufus) using a structured evidence-based approach.
• Comprehensive Toolset: Includes specialized tools for keyword research (8-dimensional classification), review analysis (risk thresholds), and traffic gap discovery.