1kalin/afrexai-churn-analyzer/SKILL.md
# 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. ## When to Use - Customer success reviews - Quarterly retention planning - When usage data or support ticket logs are available - Proactive outreach prioritization ## How It Works ### 1. Gather Data Ask the user for available data sources: - **Usage metrics** (logins, feature adoption, API calls) - **S
npx skillsauth add openclaw/skills 1kalin/afrexai-churn-analyzerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
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:
tools
Use when the user wants to connect to, test, or use the McDonalds service at mcp.mcd.cn, including checking authentication, probing MCP endpoints, listing tools, or calling McDonalds MCP tools through a reusable local CLI.
development
Web scraping platform — Twitter/X data, Vinted marketplace, and general web scraping API
development
SlowMist AI Agent Security Review — comprehensive security framework for skills, repositories, URLs, on-chain addresses, and products (Claude Code version)
data-ai
去除中文文本中的 AI 写作痕迹,使其读起来自然。基于维基百科 AI 写作特征指南,检测 24 种 AI 模式。触发词:humanizer-cn、去除 AI 痕迹、去除 AI 写作痕迹、中文文本人性化。