用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/dvcrn/openclaw-skills-marketplace --skill afrexai-churn-analyzer命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
基于 SOC 职业分类
正在显示 SKILL.md
| name | afrexai-churn-analyzer |
| description | Churn Risk Analyzer |
Identify customers most likely to churn before they leave. Uses behavioral signals, usage patterns, and engagement data to score accounts and recommend retention actions.
Ask the user for available data sources:
If no structured data, work from what the user describes qualitatively.
Apply this risk framework:
| Signal | Weight | High Risk Indicator |
|---|---|---|
| Usage decline (30d) | 25% | >30% drop |
| Support ticket spike | 20% | 2x+ above baseline |
| Champion departure | 20% | Key contact left |
| Contract timing | 15% | <90 days to renewal |
| Payment behavior | 10% | Late/disputed invoices |
| Engagement drop | 10% | No response to last 3 outreach |
Score: 0-100 (higher = more likely to churn)
For each at-risk account, suggest specific retention plays:
Generate a retention report with:
