Xiyou Insight logo

Xiyou Insight

Community
liangdabiao
xiyou-insight

基于西柚洞察MCP的亚马逊竞品分析与广告策略工具。提供7大核心工作场景:实时监控广告投放效果、快速找到高性价比流量缺口、快速拆解对标竞对打法、提升新品推广效率、精准拆解竞品流量以及广告策略、透视竞品广告策略和预算、高效搭建关键词库。适用于亚马逊卖家进行竞品分析、广告优化和关键词研究。

Overview

Publisherliangdabiao
Repositoryamazon-sorftime-research-MCP-skill
Skill namexiyou-insight
Stars
964
Forks
138
Bundled files
13
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 13 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by liangdabiao on GitHub. Read the source before you install it.

Installation

Install the Xiyou Insight AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/liangdabiao/amazon-sorftime-research-MCP-skill/tree/main/SKILLS/skills/xiyou-insight
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/liangdabiao/amazon-sorftime-research-MCP-skill.git /tmp/amazon-sorftime-research-MCP-skill
mkdir -p .claude/skills
cp -r /tmp/amazon-sorftime-research-MCP-skill/SKILLS/skills/xiyou-insight .claude/skills/xiyou-insight
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Xiyou Insight in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Xiyou Insight on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Xiyou Insight is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

西柚洞察 (Xiyou Insight)

定位

基于 西柚洞察MCP 的亚马逊竞品分析与广告策略工具。LLM Agent 直接调用 MCP 工具获取数据,脚本仅负责数据后处理、报告生成和可视化渲染。

核心特点:

  • MCP驱动:所有数据获取通过 xydc-mcp 直接调用
  • 场景化工作流:7大核心场景,覆盖广告监控、流量分析、竞品拆解、新品推广、关键词库搭建
  • 轻量脚本:仅用于数据聚合、报告生成和 Dashboard 渲染

MCP 工具速查表

ASIN 基础信息

工具名称功能参数
get_asin_info获取ASIN基础信息(标题、价格、评分、评论数、主图)asins, country
get_asin_variations查询父子变体关系asin, country
get_asin_info_trends商品信息日趋势(价格、评分、评论数变化)asin, country, start_date, end_date

ASIN 关键词分析

工具名称功能参数
get_asin_keywordsASIN反查关键词(近7天)asin, country, page, page_size, sort_field, sort_order
get_asin_keywords_monthlyASIN反查关键词(月度历史)asin, country, start_month, end_month, page, page_size
get_asin_keyword_rank_trends关键词日排名趋势asin, keyword, country, start_date, end_date
get_asin_keyword_rank_hourly关键词小时级排名(仅US/UK/DE)asin, keyword, country, date
get_asin_keyword_traffic_trends关键词日流量趋势asin, keyword, country, start_date, end_date

ASIN 流量与销量

工具名称功能参数
get_asin_traffic近7天流量得分(自然/广告流量占比)asins, country
get_asin_traffic_trends日流量趋势(自然/广告/位置维度)asin, country, start_date, end_date
get_asin_order_trends月订单量趋势asin, country, start_month, end_month
get_asin_bsr_trendsBSR类目排名日趋势asin, country, start_date, end_date

ASIN 广告分析

工具名称功能参数
get_asin_ad_change_trends广告投放变化日趋势(新增/移除广告活动)asin, country, start_date, end_date

关键词分析

工具名称功能参数
get_keyword_info关键词基础指标(搜索量、竞争难度、建议竞价)keywords, country
get_keyword_aba_trendsABA搜索量周趋势(最长52周)keywords, country, start_week, end_week
get_keyword_asin_analysis关键词反查ASIN(近7天竞争格局)keyword, country, page, page_size, sort_field, sort_order
get_keyword_analysis_monthly关键词竞争格局月度历史keyword, country, start_month, end_month, page, page_size

7大核心工作场景

场景1:实时监控广告投放效果

目标:通过小时级排名变化和广告放映机,实时监控广告投放效果

工作流程:

Step 1: 获取ASIN基础信息
  → get_asin_info(asin)
  
Step 2: 查询小时级排名(仅US/UK/DE)
  → get_asin_keyword_rank_hourly(asin, keyword, date)
  分析广告排名位置和持续时间
  
Step 3: 查询日排名趋势
  → get_asin_keyword_rank_trends(asin, keyword, start_date, end_date)
  判断广告投放带动自然排名上升情况
  
Step 4: 查询广告投放变化
  → get_asin_ad_change_trends(asin, start_date, end_date)
  分析广告活动新增/移除情况
  
Step 5: 生成分析报告
  → 评估广告投放效率,判断是否带来自然排名提升

输出:广告投放效果分析报告


场景2:快速找到高性价比流量缺口

目标:通过多ASIN对比和关键词分析,找到竞争对手有排名但自身没有的流量缺口

工作流程:

Step 1: 获取多个ASIN基础信息
  → get_asin_info(asins)
  
Step 2: 获取各ASIN关键词列表
  → get_asin_keywords(asin1)
  → get_asin_keywords(asin2)
  → ...
  
Step 3: 对比关键词覆盖差异
  → 找出竞品有排名但自身没有的关键词
  
Step 4: 分析关键词竞争程度
  → get_keyword_info(keywords)
  判断搜索量、竞争难度、建议竞价
  
Step 5: 分析关键词下ASIN竞争格局
  → get_keyword_asin_analysis(keyword)
  判断自然位滚动率、广告位竞争难度
  
Step 6: 筛选高性价比流量缺口
  → 综合评估:搜索量中等、竞争难度低、竞品有排名但自身无排名

输出:流量缺口分析报告,包含推荐补充的关键词列表


场景3:快速拆解对标竞对打法

目标:全面分析竞品的关键词覆盖差异、流量结构和广告策略

工作流程:

Step 1: 获取竞品基础信息
  → get_asin_info(competitor_asins)
  
Step 2: 确认主推变体
  → get_asin_variations(asin)
  确定父体下流量最大的变体
  
Step 3: 分析流量结构
  → get_asin_keywords(asin)
  → get_asin_traffic(asin)
  分析头部词、腰部词、长尾词贡献的展示量
  
Step 4: 分析广告策略
  → get_asin_ad_change_trends(asin, start_date, end_date)
  → get_asin_traffic_trends(asin, start_date, end_date)
  了解广告流量构成和广告展示位置关键词
  
Step 5: 趋势分析
  → get_asin_keyword_rank_trends(asin, keyword, start_date, end_date)
  洞察竞品广告投放策略和节奏
  
Step 6: 综合对比分析
  → 关键词覆盖差异、流量份额、广告策略对比

输出:竞品打法拆解报告


场景4:提升新品推广效率

目标:分析新品流量分配阶段(稀疏期→震荡期→稳定期),把握异动关键词机会

工作流程:

Step 1: 获取ASIN基础信息
  → get_asin_info(asin)
  
Step 2: 分析流量趋势
  → get_asin_traffic_trends(asin, start_date, end_date)
  判断流量分配阶段:稀疏期/震荡期/稳定期
  
Step 3: 分析关键词排名变化
  → get_asin_keywords(asin)
  → get_asin_keyword_rank_trends(asin, keyword, start_date, end_date)
  
Step 4: 识别异动关键词
  - 新增:昨日无排名今日出现排名
  - 流失:昨日有排名今日消失
  - 流量升档:自然流量上升(稀疏→震荡→稳定)
  - 流量降档:自然流量下降
  
Step 5: 把握流量窗口机会
  → 针对新增和流量升档关键词加大投放
  → 针对流失和流量降档关键词分析原因并调整

输出:新品推广分析报告,包含流量阶段判断和异动关键词建议


场景5:精准拆解竞品流量以及广告策略

目标:深度分析竞品的关键词布局、流量来源和广告投放策略

工作流程:

Step 1: 获取竞品基础信息
  → get_asin_info(competitor_asins)
  
Step 2: 确认主推变体
  → get_asin_variations(asin)
  
Step 3: 分析关键词布局
  → get_asin_keywords(asin)
  → get_asin_keywords_monthly(asin, start_month, end_month)
  了解关键词覆盖广度和月度变化
  
Step 4: 分析流量结构
  → get_asin_traffic(asin)
  → get_asin_traffic_trends(asin, start_date, end_date)
  自然/广告流量占比、位置维度拆解
  
Step 5: 分析广告策略
  → get_asin_ad_change_trends(asin, start_date, end_date)
  → get_asin_keyword_traffic_trends(asin, keyword, start_date, end_date)
  
Step 6: 关键词竞争分析
  → get_keyword_info(keywords)
  → get_keyword_asin_analysis(keyword)
  分析竞品核心关键词的竞争格局
  
Step 7: 生成综合分析报告
  → 关键词覆盖差异、流量结构、广告策略洞察

输出:竞品流量与广告策略深度分析报告


场景6:透视竞品广告策略和预算

目标:分析竞品的广告类型分布、活动结构、预算分布和核心广告关键词

工作流程:

Step 1: 获取竞品基础信息
  → get_asin_info(asin)
  
Step 2: 确认主推变体
  → get_asin_variations(asin)
  
Step 3: 分析广告活动变化
  → get_asin_ad_change_trends(asin, start_date, end_date)
  识别新增/移除的广告活动,分析投放节奏
  
Step 4: 分析流量趋势
  → get_asin_traffic_trends(asin, start_date, end_date)
  判断SP/SB/SBV广告流量占比
  
Step 5: 分析关键词流量贡献
  → get_asin_keywords(asin)
  → get_asin_keyword_traffic_trends(asin, keyword, start_date, end_date)
  找出核心广告关键词及其流量占比
  
Step 6: 推断预算分布
  → 根据广告展示时长和关键词流量变化推断预算调整
  → 分析广告投放的周期性规律
  
Step 7: 生成广告策略分析报告
  → 广告类型分布、活动结构、核心关键词、预算推断

输出:竞品广告策略和预算分析报告


场景7:高效搭建关键词库

目标:通过反查竞品流量词和以词找词,搭建完整的关键词库

工作流程:

Step 1: 广泛收集关键词
  → 方式1:反查竞品流量词
    get_asin_keywords(competitor_asin) × 多个竞品
  → 方式2:关键词基础信息
    get_keyword_info(core_keywords)
  
Step 2: 关键词拓展
  → get_keyword_aba_trends(keywords, start_week, end_week)
  分析搜索量趋势和季节性
  
Step 3: 关键词竞争分析
  → get_keyword_asin_analysis(keyword)
  判断每个关键词下的竞争格局
  
Step 4: 按相关性筛选
  → 强/高/中相关 → 加入关键词库
  → 低/极低相关 → 加入否定词库
  
Step 5: 关键词分类
  → 数据维度:搜索量(大/中/小)、竞争难度(超难/难/中等/简单)、转化率(高/中/低)
  → 属性维度:人群受众、使用场景、产品维度、价值维度
  
Step 6: 输出关键词库
  → 结构化关键词列表,包含分类标签和优先级

输出:完整关键词库,包含关键词分类和优先级标注


Script Directory

脚本用途何时调用
report_generator.py报告生成器:将MCP数据聚合为Markdown报告每个场景完成后
dashboard_generator.pyDashboard渲染:生成可视化看板HTML报告生成后
data_aggregator.py数据聚合器:合并多个ASIN/关键词数据多ASIN对比场景

脚本职责:

  • 不做API调用:所有数据获取由LLM通过MCP直接调用
  • 仅做数据处理:聚合、清洗、格式化
  • 报告渲染:生成Markdown和HTML报告

执行流程

通用执行模式

1. 用户输入场景和参数(ASIN/关键词/站点)
2. LLM根据场景选择对应MCP工具组合
3. 调用MCP工具获取数据
4. 使用脚本进行数据后处理和报告生成
5. 输出Markdown报告和Dashboard看板

数据输出目录

xiyou-insight-reports/
└── {scenario}_{asin_or_keyword}_{site}_{YYYYMMDD}/
    ├── report.md              # Markdown完整报告
    ├── data.json              # 结构化数据
    ├── dashboard.html         # 可视化看板
    └── raw/                   # 原始MCP响应数据
        ├── asin_info.json
        ├── keywords.json
        ├── traffic.json
        └── ad_trends.json

数据字段命名规范

字段名说明示例
natural_traffic自然流量得分85.5
ad_traffic广告流量得分42.3
total_traffic总流量得分127.8
keyword_count关键词数量156
natural_rank自然排名位置5
ad_rank广告排名位置2
weekly_search_volume周搜索量125000
competitive_difficulty竞争难度(0-100)72
cost_per_click建议竞价2.35

支持的站点

US, CA, MX, BR, UK, DE, FR, ES, IT, JP, AE, AU, SA

注意:小时级排名(get_asin_keyword_rank_hourly)仅支持 US/UK/DE 站点


注意事项

  1. API限流:每批请求建议控制并发数量,避免触发限流
  2. 数据时效:近7天数据实时性较好,历史数据可能有延迟
  3. 消耗提示:查询日期范围越长,API消耗越高
  4. intent_summary:所有MCP调用必须包含脱敏的业务意图描述,禁止包含用户原始prompt、账号、手机号、邮箱或完整ASIN

与其他Skills的关系

category-selection (品类筛选)
        ↓
product-research (深度选品调研)
        ↓
xiyou-insight (竞品分析与广告策略) ← 本Skill
        ↓
review-analysis (评论深度分析)

区别:

  • category-selection:品类级别的快速筛选
  • product-research:指定品类的深度调研
  • xiyou-insight:竞品流量分析和广告策略拆解
  • review-analysis:评论的深度痛点分析

版本: v1.0 (7场景工作流) | 最后更新: 2026-07-04

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Xiyou Insight AI skill do?

基于西柚洞察MCP的亚马逊竞品分析与广告策略工具。提供7大核心工作场景:实时监控广告投放效果、快速找到高性价比流量缺口、快速拆解对标竞对打法、提升新品推广效率、精准拆解竞品流量以及广告策略、透视竞品广告策略和预算、高效搭建关键词库。适用于亚马逊卖家进行竞品分析、广告优化和关键词研究。

Why use Xiyou Insight on TypingMind?

Because you install it once and use it with any model. Xiyou Insight is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Xiyou Insight in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/liangdabiao/amazon-sorftime-research-MCP-skill/tree/main/SKILLS/skills/xiyou-insight. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Xiyou Insight?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Xiyou Insight?

As many as you like. As long as a model supports skills, you can use Xiyou Insight with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Xiyou Insight AI skill free?

It is published on GitHub by liangdabiao. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇