claude-ecom (Claude Skill) — 설치 & 라이브 데모

왜 쓰나요

핵심 기능

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

라이브 데모

실제 사용 모습

claude-ecom-skill.replay ▶ 준비됨

0/0

설치

작성자 저장소 · Claude Skills 공식 문서

사용 사례

실전 활용법: claude-ecom

Weekly sales review in 10 minutes instead of 2 hours

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

언제 쓸까: Monday morning review of last week's numbers.

흐름

Hand over the CSV

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

→ 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.✓ 복사됨

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

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

→ Action list I could paste in a Monday standup

결과: A weekly review I actually read.

함정

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

함께 쓰기: filesystem

Understand why a specific SKU is underperforming

👤 Product managers, merchandisers ⏱ ~20 min intermediate

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

흐름

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.✓ 복사됨

→ Decomposition with clear delta per factor
Check channel split

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

→ Channel breakdown with concentration analysis

결과: A diagnosis, not a vibe.

Customer cohort retention report from order data

👤 Growth teams watching LTV ⏱ ~30 min intermediate

언제 쓸까: Quarterly review of cohort repeat rates.

흐름

Cohort the data

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

→ Triangular retention table
Compare cohorts

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

→ Hypotheses grounded in the data

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

함정

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

조합

다른 MCP와 조합해 10배 효율

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.✓ 복사됨

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.✓ 복사됨

도구

이 MCP가 노출하는 것

도구	입력	언제 호출	비용
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

비용 및 제한

운영 비용

API 쿼터: None
호출당 토큰: Moderate — summary tables only, not raw rows
금액: Free (needs local Python)
팁: Aggregate in Python; never paste raw orders rows into prompts.

보안

권한, 시크릿, 파급범위

자격 증명 저장: None

데이터 외부 송신: 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.

문제 해결

자주 발생하는 오류와 해결

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

대안

claude-ecom 다른 것과 비교

대안	언제 쓰나	단점/장점
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