/ 目录 / 演练场 / claude-ecom
← 全部服务器 ↗ GitHub
● 社区 takechanman1228 ⚡ 即开即用

claude-ecom

作者 takechanman1228 · takechanman1228/claude-ecom

Drop a sales CSV in; get a KPI decomposition, ranked findings, and concrete next actions — powered by a Python analysis backend.

A Claude Code skill for e-commerce operators. Takes an orders or sales CSV and produces a structured business review: revenue decomposition, conversion and AOV trends, customer cohort signals, and a prioritized action list. Runs a Python backend so math is correct, not LLM-guessed.

▶ 观看演示 📦 安装 💡 使用场景

为什么要用

核心特性

实时演示

实际使用效果

claude-ecom-skill.replay ▶ 就绪
0/0

安装

作者仓库 · Claude Skills 官方文档

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.

步骤
  1. 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
  2. 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'
  3. 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
  1. 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
  2. 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
  1. 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
  2. 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

故障排查

常见错误与修复

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 dashboardsYou want persistent dashboards, not one-shot reviewsSetup cost; no LLM-generated narrative
Shopify's own reportsQuick built-in viewsShallow; no cross-store or cohort analysis

更多

资源

📖 阅读 GitHub 上的官方 README

🐙 查看未解决的 issue

🔍 浏览全部 400+ MCP 服务器和 Skills