claude-ecom MCP — 使用场景, 安装 & 实时演示

为什么要用

核心特性

CSV in, structured review out
KPI decomposition (revenue = traffic × CVR × AOV)
Python-backed calculations for accuracy
Prioritized findings, not a wall of charts
Next-actions list tied to findings

实时演示

实际使用效果

claude-ecom-skill.replay ▶ 就绪

0/0

安装

选择你的客户端

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "claude-ecom-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/takechanman1228/claude-ecom",
        "~/.claude/skills/claude-ecom"
      ],
      "_inferred": true
    }
  }
}

打开 Claude Desktop → Settings → Developer → Edit Config。保存后重启应用。

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "claude-ecom-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/takechanman1228/claude-ecom",
        "~/.claude/skills/claude-ecom"
      ],
      "_inferred": true
    }
  }
}

Cursor 使用与 Claude Desktop 相同的 mcpServers 格式。项目级配置优先于全局。

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "claude-ecom-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/takechanman1228/claude-ecom",
        "~/.claude/skills/claude-ecom"
      ],
      "_inferred": true
    }
  }
}

点击 Cline 侧栏中的 MCP Servers 图标，然后选 "Edit Configuration"。

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "claude-ecom-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/takechanman1228/claude-ecom",
        "~/.claude/skills/claude-ecom"
      ],
      "_inferred": true
    }
  }
}

格式与 Claude Desktop 相同。重启 Windsurf 生效。

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "claude-ecom-skill",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/takechanman1228/claude-ecom",
        "~/.claude/skills/claude-ecom"
      ]
    }
  ]
}

Continue 使用服务器对象数组，而非映射。

~/.config/zed/settings.json

{
  "context_servers": {
    "claude-ecom-skill": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/takechanman1228/claude-ecom",
          "~/.claude/skills/claude-ecom"
        ]
      }
    }
  }
}

加入 context_servers。Zed 保存后热重载。

claude mcp add claude-ecom-skill -- git clone https://github.com/takechanman1228/claude-ecom ~/.claude/skills/claude-ecom

一行命令搞定。用 claude mcp list 验证，claude mcp remove 卸载。

使用场景

实战用法： claude-ecom

Weekly sales review in 10 minutes instead of 2 hours

👤 DTC founders, e-commerce managers ⏱ ~15 min beginner

何时使用： Monday morning review of last week's numbers.

前置条件

Orders CSV export from Shopify/WooCommerce/etc. — Any platform's standard order export works; column mapping is flexible
Python available locally — python3 --version; skill uses a local Python env
Skill installed — git clone https://github.com/takechanman1228/claude-ecom ~/.claude/skills/claude-ecom

步骤

Hand over the CSV

Use claude-ecom. Here's last week's orders.csv — do a KPI decomposition and tell me what moved.✓ 已复制

→ Revenue, CVR, AOV numbers with week-over-week deltas
Ask for findings

Rank the top 3 findings by impact. Be specific — named SKUs, traffic sources, time windows.✓ 已复制

→ Findings with data points, not 'revenue went up'
Extract actions

For each finding, propose one concrete action I can take this week.✓ 已复制

→ Action list I could paste in a Monday standup

结果： A weekly review I actually read.

注意事项

Garbage CSVs produce garbage reviews — Clean the export first — merge refunds, exclude test orders

搭配使用： filesystem

Understand why a specific SKU is underperforming

👤 Product managers, merchandisers ⏱ ~20 min intermediate

何时使用： A hero SKU suddenly slowed down and you need to know whether it's traffic, conversion, or pricing.

步骤

Filter to SKU

Use claude-ecom. Focus on SKU SHIRT-BLK-M for the last 60 days. Decompose revenue into traffic × CVR × AOV and compare to the prior 60.✓ 已复制

→ Decomposition with clear delta per factor
Check channel split

Is the drop concentrated in one channel or across all?✓ 已复制

→ Channel breakdown with concentration analysis

结果： A diagnosis, not a vibe.

Customer cohort retention report from order data

👤 Growth teams watching LTV ⏱ ~30 min intermediate

何时使用： Quarterly review of cohort repeat rates.

步骤

Cohort the data

Use claude-ecom. Build a monthly acquisition-cohort retention table — orders/customer by month since first order.✓ 已复制

→ Triangular retention table
Compare cohorts

Which cohort is best? Worst? What's different about them?✓ 已复制

→ Hypotheses grounded in the data

结果： A retention view you could share with an investor.

注意事项

Short data windows distort recent cohorts — Flag cohorts with <3 months of history as provisional

组合

与其他 MCP 搭配，撬动十倍杠杆

claude-ecom-skill + filesystem

Point at a folder of weekly CSVs for automated trend analysis

Run the weekly review for each CSV in data/weekly/ and build a running dashboard.✓ 已复制

claude-ecom-skill + bigquery-server

Instead of CSVs, pull from a warehouse

Query BigQuery for last week's orders and feed into claude-ecom for the review.✓ 已复制

工具

此 MCP 暴露的能力

工具	输入参数	何时调用	成本
load_csv	path, column mapping	Starting any analysis	local
kpi_decompose	date range	Weekly / monthly review	local Python
rank_findings	analysis output	After decomposition	0
cohort_table	cohort granularity	Retention analysis	local

成本与限制

运行它的成本

API 配额: None
每次调用 Token 数: Moderate — summary tables only, not raw rows
费用: Free (needs local Python)
提示: Aggregate in Python; never paste raw orders rows into prompts.

安全

权限、密钥、影响范围

凭据存储： None

数据出站： Order summaries and findings are sent to Claude API; raw rows can stay local if you keep aggregation server-side

Order data often includes customer PII. Mask or exclude email/name/address columns before analysis.

故障排查

常见错误与修复

Python deps missing

The skill uses pandas; run pip install -r ~/.claude/skills/claude-ecom/requirements.txt

验证： python -c 'import pandas'

Column mapping fails

Standard Shopify/Woo exports work out of the box. For custom exports, supply a column map in the prompt.

Wild numbers in the output

Check for duplicate order rows or non-currency values in the revenue column

替代方案

claude-ecom 对比其他方案

替代方案	何时用它替代	权衡
Looker Studio / Metabase dashboards	You want persistent dashboards, not one-shot reviews	Setup cost; no LLM-generated narrative
Shopify's own reports	Quick built-in views	Shallow; no cross-store or cohort analysis

claude-ecom

为什么要用

核心特性

实时演示

实际使用效果

安装

选择你的客户端

使用场景

实战用法： claude-ecom

Weekly sales review in 10 minutes instead of 2 hours

前置条件

步骤

注意事项

Understand why a specific SKU is underperforming

步骤

Customer cohort retention report from order data

步骤

注意事项

组合

与其他 MCP 搭配，撬动十倍杠杆

工具

此 MCP 暴露的能力

成本与限制

运行它的成本

安全

权限、密钥、影响范围

故障排查

常见错误与修复

替代方案

claude-ecom 对比其他方案

更多

资源