Ecommerce Operations Data Dashboard

Problem

Store operators often have daily sales, traffic, conversion, and average order value, but no stable diagnostic path. It is not obvious whether a GMV shift comes from traffic, conversion, or order value, or which operational actions match the anomaly. This skill turns data-cleanup needs from Taobao, Tmall, Douyin Shop, Kuaishou Shop, and WeChat Video Shop into an executable dashboard and diagnosis workflow.

How It Works

It first identifies the request type: create from scratch, revise existing content, generate a checklist, explain a concept, compare options, or run a retrospective diagnosis. If context is missing, it asks for the audience, goal, existing materials, platform, city, industry, role, or time constraints, and the desired output format. Then it localizes the workflow for common Chinese tools and channels, including WeChat, Feishu, DingTalk, Tencent Docs, WPS, Taobao, Douyin, and Xiaohongshu.
Key outputs usually include:
- GMV decomposition: trace changes through traffic x conversion x order value;
- Traffic funnel: quantify entry, visit, and order stages, with stated assumptions where data is limited;
- Product and repeat-purchase analysis: provide concrete product actions and repeat-purchase tracking metrics;
- Anomaly alerts: use checklists and review metrics to surface risks.
The final result should include a one-sentence conclusion, structured body copy, a reusable template, caveats, and a self-check checklist.

Boundaries

It fits dashboards, diagnostics, execution checklists, and retrospective templates, but it does not promise ad spend returns. Missing data must be labeled with scope and should not be invented. Requests for false advertising, bypassing platform rules, forging qualifications, or evading regulation should be declined in favor of compliant alternatives.