/ Каталог / Песочница / Amazon-Skills
● Сообщество nexscope-ai ⚡ Сразу

Amazon-Skills

автор nexscope-ai · nexscope-ai/Amazon-Skills

Amazon seller skills — keyword research, competitor analysis, listing audit — built for Claude Code, Cursor, Windsurf, and Codex.

Amazon Skills gives sellers a focused toolkit: keyword research for Amazon SEO, competitor analysis with BSR/review-count context, listing audits that flag policy and conversion issues, and PPC strategy prompts. Cross-agent compatible via the SKILL.md format.

Зачем использовать

Ключевые функции

Живое демо

Как выглядит на практике

amazon-skill.replay ▶ готово
0/0

Установка

Выберите клиент

~/Library/Application Support/Claude/claude_desktop_config.json  · Windows: %APPDATA%\Claude\claude_desktop_config.json
{
  "mcpServers": {
    "amazon-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/nexscope-ai/Amazon-Skills",
        "~/.claude/skills/Amazon-Skills"
      ],
      "_inferred": true
    }
  }
}

Откройте Claude Desktop → Settings → Developer → Edit Config. Перезапустите после сохранения.

~/.cursor/mcp.json · .cursor/mcp.json
{
  "mcpServers": {
    "amazon-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/nexscope-ai/Amazon-Skills",
        "~/.claude/skills/Amazon-Skills"
      ],
      "_inferred": true
    }
  }
}

Cursor использует ту же схему mcpServers, что и Claude Desktop. Конфиг проекта приоритетнее глобального.

VS Code → Cline → MCP Servers → Edit
{
  "mcpServers": {
    "amazon-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/nexscope-ai/Amazon-Skills",
        "~/.claude/skills/Amazon-Skills"
      ],
      "_inferred": true
    }
  }
}

Щёлкните значок MCP Servers на боковой панели Cline, затем "Edit Configuration".

~/.codeium/windsurf/mcp_config.json
{
  "mcpServers": {
    "amazon-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/nexscope-ai/Amazon-Skills",
        "~/.claude/skills/Amazon-Skills"
      ],
      "_inferred": true
    }
  }
}

Тот же формат, что и Claude Desktop. Перезапустите Windsurf для применения.

~/.continue/config.json
{
  "mcpServers": [
    {
      "name": "amazon-skill",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/nexscope-ai/Amazon-Skills",
        "~/.claude/skills/Amazon-Skills"
      ]
    }
  ]
}

Continue использует массив объектов серверов, а не map.

~/.config/zed/settings.json
{
  "context_servers": {
    "amazon-skill": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/nexscope-ai/Amazon-Skills",
          "~/.claude/skills/Amazon-Skills"
        ]
      }
    }
  }
}

Добавьте в context_servers. Zed перезагружается автоматически.

claude mcp add amazon-skill -- git clone https://github.com/nexscope-ai/Amazon-Skills ~/.claude/skills/Amazon-Skills

Однострочная команда. Проверить: claude mcp list. Удалить: claude mcp remove.

Сценарии использования

Реальные сценарии: Amazon-Skills

How to do Amazon keyword research for a new listing

👤 Sellers launching a product and needing a keyword map ⏱ ~45 min intermediate

Когда использовать: Pre-launch or relaunch; you need root + long-tail keywords organized by intent.

Предварительные требования
  • Skill installed — git clone https://github.com/nexscope-ai/Amazon-Skills ~/.claude/skills/amazon-skills
Поток
  1. Define seed terms
    Amazon keyword research for 'reusable silicone food bags'. Give me root terms, long-tail, and attribute modifiers organized by search intent.✓ Скопировано
    → Tiered keyword map with intent tags
  2. Rank by value
    Rank by estimated search volume and competition. Flag anything that smells restricted.✓ Скопировано
    → Ranked list with restriction flags
  3. Apply to listing
    Map the top 12 keywords to title, bullets, and backend search terms (250-char limit).✓ Скопировано
    → Field-by-field placement

Итог: A keyword map mapped to listing fields, ready to upload.

Подводные камни
  • Claude guesses search volume — Require directional categories (high/med/low) rather than specific numbers; validate with Helium10/Jungle Scout if precision matters
Сочетать с: ecommerce-skill

Audit your top 5 competitors on a keyword

👤 Sellers entering an existing category ⏱ ~40 min intermediate

Когда использовать: You're about to launch and want to know what 'good' looks like.

Поток
  1. Fetch top results
    For the keyword 'silicone food storage bags', analyze the top 5 organic listings: price, BSR, review count, rating, hero image style, bullet patterns.✓ Скопировано
    → Competitor table with differentiated insights
  2. Find your angle
    What's the common weakness across all 5? Where can we differentiate without racing to the bottom on price?✓ Скопировано
    → Specific angle recommendation

Итог: A positioning angle backed by what the category is and isn't doing.

Подводные камни
  • Hallucinated review counts and BSR — Require URLs; reject numbers without the ASIN link

Audit an existing listing and produce a fix list

👤 Sellers with an existing listing underperforming ⏱ ~30 min beginner

Когда использовать: Listing is live, sessions are okay, conversion is poor.

Поток
  1. Paste listing
    Audit this listing: [paste title/bullets/description/images]. Flag policy risks, conversion blockers, keyword gaps.✓ Скопировано
    → Per-field issues with severity
  2. Prioritize
    Rank by expected impact vs effort. Top 5.✓ Скопировано
    → Ranked fix list

Итог: A sprint-sized list of listing fixes.

Draft a Sponsored Products strategy for a new launch

👤 Sellers starting PPC from zero ⏱ ~30 min intermediate

Когда использовать: Product just launched; you need a sensible first PPC structure.

Поток
  1. Campaign structure
    Design campaign structure: auto research, exact discovery, broad research, product targeting. Budgets for $30/day total.✓ Скопировано
    → Per-campaign budget + match-type split
  2. Negatives
    What should go in the negative keyword list from day one?✓ Скопировано
    → Starter negatives list

Итог: A first PPC structure that won't waste money on day one.

Подводные камни
  • Going too broad on exact-match — Start with auto for discovery, graduate converters to exact

Комбинации

Сочетайте с другими MCP — эффект x10

amazon-skill + ecommerce-skill

Ecommerce is cross-platform; Amazon skill adds Amazon-specific depth

Validate the product with ecommerce-skill, then drill into Amazon specifics with amazon-skill.✓ Скопировано

Инструменты

Что предоставляет этот MCP

ИнструментВходные данныеКогда вызыватьСтоимость
Keyword research - Pre-launch Claude tokens
Competitor analysis - Entering a category Claude tokens
Listing audit - Existing listings Claude tokens
PPC strategy - PPC launch Claude tokens

Стоимость и лимиты

Во что обходится

Квота API
None
Токенов на вызов
10-20k for full research
Деньги
Free
Совет
For precise search volume numbers, pair with Helium10/Jungle Scout; the skill handles strategy, not volume.

Безопасность

Права, секреты, радиус поражения

Хранение учётных данных: No credentials
Исходящий трафик: Prompts sent to Claude

Устранение неполадок

Частые ошибки и исправления

Keyword volumes feel invented

Ask for directional tiers, not specific numbers. Validate with external tools.

Listing audit misses Amazon policy issues

Paste the current Amazon style guide for your category as context before auditing

Альтернативы

Amazon-Skills в сравнении

АльтернативаКогда использоватьКомпромисс
ecommerce-skillYou sell on multiple platformsLess Amazon-specific depth
Helium 10 / Jungle ScoutYou need deterministic market dataPaid, not in Claude Code

Ещё

Ресурсы

📖 Читать официальный README на GitHub

🐙 Открытые задачи

🔍 Все 400+ MCP-серверов и Skills