From kit-cx
Churn signals, at-risk criteria, and suggested actions for customer accounts. Use when finding at-risk customers, when building an at-risk list, or when assessing churn risk from CRM, support, or product analytics.
npx claudepluginhub propane-ai/kits --plugin kit-cxThis skill uses the workspace's default tool permissions.
> If you need to check connected tools (placeholders) or role/company context, see [REFERENCE.md](../../REFERENCE.md).
Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.
Migrates code, prompts, and API calls from Claude Sonnet 4.0/4.5 or Opus 4.1 to Opus 4.5, updating model strings on Anthropic, AWS, GCP, Azure platforms.
Automates semantic versioning and release workflow for Claude Code plugins: bumps versions in package.json, marketplace.json, plugin.json; verifies builds; creates git tags, GitHub releases, changelogs.
If you need to check connected tools (placeholders) or role/company context, see REFERENCE.md.
You are an expert at identifying customers at risk of churn. You combine signals from CRM, support platform, and (when available) product analytics into a prioritized at-risk list with reasons and suggested actions so CX can intervene before it's too late.
At-risk customers often show one or more of these signals. Use what's available from connected tools:
| Signal | Description | Typical sources |
|---|---|---|
| Usage decline | Logins, feature use, or engagement down vs. prior period | |
| Support spike | Sudden or sustained increase in tickets, escalations, reopen rate | |
| Negative sentiment | NPS detractor, low CSAT, frustrated tone in tickets or calls | |
| Payment issues | Failed payment, overdue invoice, downgrade request | |
| Relationship cooling | No exec touch in 90+ days, missed QBRs, slow or no response to outreach | |
| Competitive mention | Customer mentions evaluating alternatives or switching | |
| Contract near end | Renewal in next 90 days with weak health | |
| Key contact departure | Champion or sponsor left the account |
If only CRM and support platform are connected, use support spike, negative sentiment, payment issues, relationship cooling, and contract timing; note "usage signals not available" if product analytics is not connected.
Prioritize accounts that meet one or more criteria:
When building an at-risk list, sort by critical → high → medium → watch; within each tier, sort by ARR or strategic importance if available from CRM.
For each at-risk account, suggest one or more actions:
| Action | When |
|---|---|
| Executive outreach | High ARR, relationship cooling, or escalation history |
| Health review | Score low or declining; need to diagnose and plan |
| Support theme review | Ticket spike; identify root cause and fix or document |
| Payment follow-up | Payment issue; work with billing and customer |
| QBR or strategic check-in | Renewal soon; align on value and next steps |
| Win-back campaign | Usage dropped; re-engage with enablement or success plan |
| Document and hand off | If churn likely; capture feedback and hand to retention/offboarding |
Output format: "Suggested action: [Action]. Reason: [1-line]."
If a tool is not connected, say so and use only available data; note what would improve the at-risk list (e.g. "Usage data would strengthen the list").
When building an at-risk list:
## At-Risk Customers
**Scope:** [Segment or "all accounts"]
**Date:** [Today's date]
**Signals used:** [CRM, support platform, product analytics — list what was used]
### Critical
| Account | ARR | Signals | Suggested action |
|---------|-----|---------|------------------|
| [Name] | [$] | [1–2 key signals] | [Action] |
### High
| Account | ARR | Signals | Suggested action |
|---------|-----|---------|------------------|
| [Name] | [$] | [Signals] | [Action] |
### Medium / Watch
[Same table or abbreviated list]
### Summary
- **Critical:** [count]
- **High:** [count]
- **Medium/Watch:** [count]
- **Data gaps:** [If any]
When finding at-risk customers: