amazon-store-research

Amazon Store In-Depth Research

An end-to-end autonomous research workflow for any Amazon seller store. The user provides a store URL; the skill collects data from the storefront, runs parallel analysis, and generates a comprehensive Chinese report package.

Prerequisites

• Playwright MCP server must be available (browser_navigate, browser_evaluate, browser_snapshot, browser_close)
• Agent tool used to launch parallel analysis sub-agents
• Reports are saved to {project_root}/reports/{store-slug}/(e.g. reports/jmbricklayer/). Create a subdirectory at the start of each run.

Workflow Overview

The skill runs in three phases: data collection, parallel analysis, and report synthesis. Use TaskCreate/TaskUpdate to track progress.

Important: All file outputs (JSON data, analysis reports, synthesis reports) must go into the store-specific subfolder under reports/ . Extract a human-readable slug from the store name (e.g. "JMBricklayer" → jmbricklayer). Create the directory before saving any files.

---

Phase 1: Data Collection

Step 1.1 — Parse User Input

Extract from the user message:

• Store URL(required) — Amazon store URL, e.g. https://www.amazon.com/stores/JMBricklayer/page/3CACFA02-74C5-4F9D-81DB-0BF560B7BA47
• Store name — extracted from the URL or page title
• Report language(optional, default: Simplified Chinese)

Step 1.2 — Scrape the Store Homepage

Use mcp__playwright__browser_navigate to navigate to the store URL. Wait for the page to fully load.

First, use mcp__playwright__browser_evaluate to extract the store navigation structure:

() => {
  const storeInfo = {};
  const navItems = Array.from(document.querySelectorAll('nav a, nav button'));
  storeInfo.navigation = navItems.map(item => ({
    text: item.textContent?.trim(),
    url: item.href || '',
    type: item.tagName === 'BUTTON' ? 'dropdown' : 'link'
  })).filter(item => item.text && item.text.length > 0 && item.text !== 'Back');

  const productLinks = Array.from(document.querySelectorAll('a[href*="/dp/"]'));
  storeInfo.productLinks = productLinks.map(a => ({
    asin: a.href.match(/\/dp\/([A-Z0-9]+)/)?.[1],
    text: a.textContent?.trim()?.substring(0, 200)
  }));

  const collectionLinks = Array.from(document.querySelectorAll('a[href*="/stores/page/"]'));
  storeInfo.collections = collectionLinks.map(a => ({
    text: a.textContent?.trim(),
    url: a.href,
    id: a.href.match(/page\/([A-F0-9-]+)/)?.[1]
  })).filter(c => c.text && c.text.length > 0);

  return storeInfo;
}

This reveals:

• Store navigation items (Home, Best Sellers, New Releases, Collections, dropdown menus)
• All collection/category page URLs
• Product links visible on the homepage

Step 1.3 — Extract Products from the Homepage

Use mcp__playwright__browser_evaluate to run this product extraction script:

() => {
  const products = [];
  const seen = new Set();
  const allLinks = Array.from(document.querySelectorAll('a[href*="/dp/"]'));

  allLinks.forEach(a => {
    const href = a.href;
    const asinMatch = href.match(/\/dp\/([A-Z0-9]+)/);
    if (!asinMatch) return;
    const asin = asinMatch[1];
    if (seen.has(asin)) return;

    const title = a.textContent?.trim();
    if (title && title.length > 20 && !title.includes('Amazon Business') && !title.includes('Reload Your')) {
      seen.add(asin);
      const container = a.closest('li') || a.parentElement?.parentElement?.parentElement || document.body;
      const containerText = container?.innerText || '';
      const priceMatch = containerText.match(/\$[\d,.]+/);
      const reviewMatch = containerText.match(/\(([\d,K]+)\)/);
      const ratingMatch = containerText.match(/([\d.]+) out of 5/);

      products.push({
        asin,
        title: title.substring(0, 200),
        price: priceMatch?.[0] || null,
        reviews: reviewMatch?.[1] || null,
        rating: ratingMatch?.[1] || null,
        url: href.split('?')[0]
      });
    }
  });
  return products;
}

Step 1.4 — Scrape Key Store Pages

Use the collection URLs discovered in Step 1.2 to navigate to each key page. Standard store pages include:

1. Best Sellers — find the navigation item with the text "Best Sellers"
2. New Releases — find the navigation item with the text "New Releases"
3. About Us — find the navigation item with the text "About us"

For each page, use the same product extraction script from Step 1.3.

Step 1.5 — Scrape Collection/Category Pages

Navigate to each themed collection page discovered from the navigation. Use the same product extraction script.

Common collection patterns:

• "Shop by Theme" dropdown menu → contains theme categories
• "Shop by Difficulty" dropdown menu → contains difficulty levels
• Standalone collection links (occasions, etc.)

Important: Identify dropdown menus in the navigation. Dropdown items (by type: 'dropdown' or nested link indication) contains the actual collection subpages. Scrape each sub-collection page.

Step 1.6 — Close the browser

After all scraping is complete, run mcp__playwright__browser_close。

Step 1.7 — Save raw data

Integrate all scraped data into reports/{store-slug}/{store-slug}_store_data.json into a single JSON file, with the following structure:

{
  "storeInfo": {
    "brandName": "...",
    "storeUrl": "...",
    "storefrontId": "...",
    "scrapeDate": "...",
    "navigation": [...],
    "totalUniqueASINs": 0,
    "priceRange": "..."
  },
  "homePage": { "products": [...] },
  "bestSellers": { "products": [...] },
  "newReleases": { "products": [...] },
  "collections": {
    "Collection Name": { "productCount": 0, "products": [...] }
  }
}

Deduplicate ASINs across all pages and count unique products.

---

Phase 2: Parallel analysis

Use run_in_background: true and subagent_type: "general-purpose" to simultaneously launch 4 analysis agents. Each agent receives the complete raw data and writes its report to reports/{store-slug}/。

Agent 1 — Product portfolio analysis

File:reports/{store-slug}/{store-slug}_portfolio_analysis.md

Prompt the agent to analyze:

1. Store overview — brand positioning, category coverage, total ASIN count, price range
2. Product matrix — distribution across collections/categories, cross-category overlap
3. Product numbering system — identify any patterns in product codes/numbers
4. Pricing strategy — price bands, average price per collection, pricing tiers
5. Ratings and reviews analysis — average rating per collection, review distribution, review barriers
6. Top product profiles — Top 10 products ranked by review count and their characteristics
7. New product release cadence — product launch speed, innovation direction, recent themes
8. SKU strategy — product line expansion, series development, size/piece count gradients

Agent 2 — Competitive positioning analysis

File:reports/{store-slug}/{store-slug}_competitive_analysis.md

Prompt the agent to analyze:

1. Competitive landscape — brand positioning (e.g., LEGO alternatives, niche players, Chinese export brands)
2. SWOT analysis — strengths, weaknesses, opportunities, threats with specific evidence
3. Direct competitor comparison — vs major brands (LEGO and any well-known alternatives relevant to the category)
4. Differentiation strategy — unique features (LED lights, licensing, themes, price advantage)
5. Target customer segmentation — who buys these products (collectors, gift buyers, enthusiasts, etc.)
6. Listing strategy — title keyword patterns, common phrases, optimization observations
7. Review quality analysis — rating comparison across collections, identify weak/strong collections

Agent 3 — Revenue estimation analysis

File:reports/{store-slug}/{store-slug}_revenue_analysis.md

Prompt the agent to analyze:

1. Sales estimation methodology — review-to-sales ratio, review growth rate, daily review rate
2. Top 10 product monthly estimates — monthly unit sales and revenue (conservative/neutral/optimistic)
3. Store monthly revenue — tiered model (Top 10 + second tier + third tier long tail), three scenarios
4. Collection revenue contribution — which collections drive the most revenue
5. Price elasticity analysis — which price bands accumulate reviews fastest
6. Product lifecycle analysis — classify products into lifecycle stages by review count
7. New product performance — evaluate early-stage products (low review count)
8. Annual Revenue Forecast — Monthly × 12 with Q4 seasonal weighting considered

Agent 4 — Growth Strategy Analysis

File:reports/{store-slug}/{store-slug}_growth_strategy.md

Prompts for agent analysis:

1. Brand Development Assessment — maturity, market validation, price coverage
2. Growth Opportunities — which collections can be expanded, underserved segments, new themes
3. Product Optimization — fix low-rated products, fill price gaps, bundling opportunities
4. Operational Strategy — PPC keywords, review building, promotion calendar, inventory
5. Competitive Response — how to position against major brands and similar substitutes
6. Market Expansion — international markets, brand website, social media
7. Risk Assessment — intellectual property risk, quality issues, logistics challenges, seasonal dependence
8. Action Roadmap — 30/60/90-day plan with specific milestones

Important: pass the actual scraped data (not a summary) to each agent. Include all product ASINs, titles, prices, ratings, and review counts from the JSON file. Agents need real data to produce meaningful analysis.

---

Phase 3: Report Synthesis

Wait for all 4 agents to complete (you will receive task notifications). Then launch a final synthesis agent (subagent_type: "general-purpose", this time running in the foreground because we need the results) to generate the synthesis report.

Final Report

File:reports/{store-slug}/{store-slug}_comprehensive_report.md

The synthesis agent should:

1. From reports/ read all 4 analysis reports
2. Combine with the raw product data
3. Generate a synthesis report with the following exact structure:

# {Store Name} 亚马逊店铺深度调研报告

## 目录
1. 执行摘要
2. 店铺全景概览
3. 产品组合深度分析
4. 竞争定位与差异化策略
5. 收入与销售表现
6. 增长机会与风险评估
7. 运营优化建议
8. 关键发现与行动建议

Key sections that must be included:

• Executive Summary: 1-page overview, including a Top 5 opportunities table (segment, rating, profit, entry difficulty) and a key metrics dashboard (number of ASINs, price range, average rating, estimated monthly revenue)
• Store Overview: brand positioning, navigation structure, product numbering system, product count collection table
• Product Portfolio: price band distribution, ratings by collection, Top 10 products, new product lines, lifecycle distribution
• Competitive Positioning: SWOT matrix, major brand price comparison, differentiation, target customer segments and percentages
• Revenue and Sales: Top 10 monthly estimates (3 scenarios), collection revenue %, store monthly/annual revenue and seasonality
• Growth and Risk: 5 opportunities ranked by potential, 5 risks with mitigation measures, low-rated product diagnosis
• Operations: PPC strategy, listing optimization, review building, promotion calendar
• Key Findings: Top 5 findings, Top 5 action items, 30/60/90-day roadmap

---

Output Summary

After all phases are complete, present to the user:

1. A summary table of all generated reports and their file paths
2. The Top 5 key findings of the research
3. The Top 3 recommended action items

Error Handling

• If Playwright navigation fails, retry once, then try mcp__web_reader__webReader as a fallback
• If the extraction script returns an empty result, use browser_snapshot to inspect the page structure and adjust
• If collection discovery fails, look for alternative URL patterns in the navigation
• If the collection page has no products, skip it and note the empty result
• If any analysis agent fails, regenerate that report
• Data anomaly observation: the review count matching the product model (e.g., "40102" reviews) may be a scraping artifact — flag these in the analysis