churn-intervention — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited churn-intervention (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Checks.agents/product-marketing-context.mdfor user segment profiles. Checks.agents/growth-metrics-context.mdfor churn baselines. If growth-mcp connected, usespredict_churn_riskfor real predictions.
| Type | Signal | Best Intervention |
|---|---|---|
| Transaction dormancy | No tx in 14-30 days | Nudge + small voucher |
| Balance zero-out | Withdrew all funds | Reason survey + winback offer |
| Feature abandonment | Stopped using key feature | Re-onboarding flow |
| Competitor switch | Known competitor activity | Price match or exclusive benefit |
| Seasonal churn | Post-holiday drop | Streak reward, loyalty tier |
| Day | Channel | Message | Cost |
|---|---|---|---|
| D0 (dormancy detected) | Push | "You have X points expiring" | Free |
| D3 | Push | "Trending near you: [popular mechanic]" | Free |
| D7 | In-app + Email | "Here's 10% off your next [action]" | Low |
| D14 | SMS | "Special offer: [exclusive cashback]" | Medium |
| D21 | Push | "Your [feature] is waiting" | Free |
| D30 | Survey | "Help us improve" + reason dropdown | Free |
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.