/ Directory / Playground / claude-ecom
← All servers ↗ GitHub
● Community takechanman1228 ⚡ Instant

claude-ecom

by 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.

▶ Watch demo 📦 Install 💡 Use Cases

Why use it

Key features

Live Demo

What it looks like in practice

claude-ecom-skill.replay ▶ ready
0/0

Install

Author repository · Claude Skills documentation

Use Cases

Real-world ways to use claude-ecom

Weekly sales review in 10 minutes instead of 2 hours

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

When to use: Monday morning review of last week's numbers.

Flow
  1. Hand over the CSV
    Use claude-ecom. Here's last week's orders.csv — do a KPI decomposition and tell me what moved.✓ Copied
    → 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.✓ Copied
    → Findings with data points, not 'revenue went up'
  3. Extract actions
    For each finding, propose one concrete action I can take this week.✓ Copied
    → Action list I could paste in a Monday standup

Outcome: A weekly review I actually read.

Pitfalls
  • Garbage CSVs produce garbage reviews — Clean the export first — merge refunds, exclude test orders
Combine with: filesystem

Understand why a specific SKU is underperforming

👤 Product managers, merchandisers ⏱ ~20 min intermediate

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

Flow
  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.✓ Copied
    → Decomposition with clear delta per factor
  2. Check channel split
    Is the drop concentrated in one channel or across all?✓ Copied
    → Channel breakdown with concentration analysis

Outcome: A diagnosis, not a vibe.

Customer cohort retention report from order data

👤 Growth teams watching LTV ⏱ ~30 min intermediate

When to use: Quarterly review of cohort repeat rates.

Flow
  1. Cohort the data
    Use claude-ecom. Build a monthly acquisition-cohort retention table — orders/customer by month since first order.✓ Copied
    → Triangular retention table
  2. Compare cohorts
    Which cohort is best? Worst? What's different about them?✓ Copied
    → Hypotheses grounded in the data

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

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

Combinations

Pair with other MCPs for X10 leverage

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.✓ Copied
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.✓ Copied

Tools

What this MCP exposes

ToolInputsWhen to callCost
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

Cost & Limits

What this costs to run

API quota
None
Tokens per call
Moderate — summary tables only, not raw rows
Monetary
Free (needs local Python)
Tip
Aggregate in Python; never paste raw orders rows into prompts.

Security

Permissions, secrets, blast radius

Credential storage: None
Data egress: Order summaries and findings are sent to Claude API; raw rows can stay local if you keep aggregation server-side

Troubleshooting

Common errors and fixes

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

Alternatives

claude-ecom vs others

AlternativeWhen to use it insteadTradeoff
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

More

Resources

📖 Read the official README on GitHub

🐙 Browse open issues

🔍 Browse all 400+ MCP servers and Skills

Continue exploring

Related tools and workflows

Choose another guide for your workflow, or explore a collection.

Browse all topic collections → · See 29 new official additions →