wuling-overseas-dealer-expansion-skill/references/dashboard.md

Dashboard

The customer dashboard reads 客户信息汇总表 as the single customer source of truth. It does not read legacy channel sheets unless they have first been imported into the summary table with scripts/common/build_customer_summary.py.

Required Metrics

• Total unique customers.
• Contactable customers.
• Outreach status distribution.
• Customer attribute distribution.
• Customer type distribution.
• Lead grade distribution from 线索等级.
• Manual review count from 需人工确认 values other than blank or 否.
• Email sent count and bounced/failed count.
• Facebook sent count, unified reply count, reply rate, latest reply customers, and pending manual-review reply count when Facebook对话记录 exists.
• Daily target progress. Default daily outreach target is 20 customers.

Facebook Reply Metrics

Facebook reply metrics use the unified reply definition. Do not segment Facebook replies by quality, cooperation intent, or deal probability.

• Facebook sent customers: unique customers with our Facebook DM records.
• Facebook replied customers: unique customers with at least one customer-side real reply.
• Facebook reply rate: Facebook replied customers / Facebook sent customers.
• Pending reply review customers: customers with a Facebook reply that should be manually reviewed.

System messages, read receipts, our messages, automated prompts, and standalone reactions are not replies.

Source Fields

Use these summary-table fields:

公司姓名, 国家, 城市, 客户类型, 官网链接, 联系人, 职位, 个人邮箱, 联系人电话, Facebook主页链接, linkined主页链接, google map链接, 公共电话/WhatsApp, 公共邮箱, 客户属性, 线索等级, 需人工确认, 建联状态, 下次跟进, 备注

Output

Generate dashboard artifacts under runs/YYYYMMDD/<run_id>/ and optionally update dashboards/latest/. Do not copy real customer JSON back into assets/dashboard_template.html; the template must keep the {{dashboard_json}} placeholder.

Dashboard generation does not modify Excel and does not trigger Feishu sync by itself.