AI Agent Hub
Back to skills
Ecommerce Operations Diagnosis icon

Ecommerce Operations Diagnosis

Business Operations Updated 2026.08.30

Paste the following prompt into your AI chat to install this skill:

Follow https://skillhub.cn/install/skillhub.md to install @user_8d36cde0/ecommerce-operations-diagnosis.

About this skill

Problem Scope

When store revenue misses target but operational data is split across goals, products, traffic, conversion, fulfillment, and profit, Ecommerce Operations Diagnosis structures the issue into traceable components instead of producing generic advice. It is useful for ecommerce owners, operations leads, and consulting teams reviewing growth, diagnosing conversion, or checking fulfillment and margin constraints.

How It Works

The skill first checks input sources, date ranges, metric definitions, and authorization boundaries, then separates material into known facts, hypotheses, constraints, risks, and actions. Its core decomposition uses traffic × conversion × order value × repeat purchase to analyze revenue gaps, with gross margin, inventory, and fulfillment constraints layered on top, so recommendations include an owner, action, rationale, and acceptance signal. Typical output includes:
- Summary: three to five key judgments
- Main deliverable: problem tree, priorities, root-cause hypotheses, and a 30-day improvement plan
- Evidence and definitions: sources, dates, calculation method, and unverified items
- Risks and blockers: impact, release conditions, and suggested owners

Boundaries

If key facts are missing, the skill lists gaps and proposes the smallest safe path forward rather than inventing prices, sales, reviews, or platform status. Actions involving publishing, payment, deletion, permissions, accounts, or privacy require confirmed user authorization and target-system state.

Use Cases

  • When quarterly GMV misses target, an operations lead turns goals, traffic, conversion, order value, repeat purchase, and margin data into a prioritized problem tree.
  • A consulting team onboards to a new store and converts product, traffic, fulfillment, and profit materials into hypotheses, risks, and a 30-day plan.
  • An ecommerce owner investigates a conversion dip by checking date ranges and metric definitions, then asks for root-cause hypotheses with evidence and unverified items.
  • An operations lead prepares a business review by adding inventory, margin, and fulfillment constraints to recommendations with owners, actions, deadlines, and acceptance signals.

Best For

  • Ecommerce owner: needs to rank GMV, conversion, margin, and fulfillment issues and get an executable 30-day plan.
  • Operations lead: needs to organize traffic, product, inventory, and profit data into an evidence-backed problem tree and risk list.
  • Consultant: needs a deliverable diagnosis with a problem tree, root-cause hypotheses, acceptance signals, and owner suggestions.
  • Ecommerce data analyst: needs to decompose traffic, conversion, order value, and repeat purchase by metric definitions and flag unverified items.