- Home
- Skills
- Marketing & SEO
- Churn Risk Scorecard
More screenshots
Works with the AI Agents you already use
Churn Risk Scorecard
Score every customer segment 0-100 for churn risk from behavioral signals, sort them into four action tiers with a save playbook each, and rank the work by lifetime value at stake.
$5
Churn Risk Scorecard
Example session with this skill installed
Score churn risk for my subscription app: 620 subscribers. The last 90 days show annual-plan users dropping core-feature use, a batch of monthly users logging in less with more support tickets, and a lot of new users stalling during setup. Tell me who needs saving and what to do first.
- Read your context and instructions
- Compiled the churn risk scorecard
SCORECARD — 620 subscribers, 90-day window, starter signals (first cycle, probabilities labeled uncalibrated):
| Segment | Size | Score | Tier | Top signals |
|---|---|---|---|---|
| Annual, usage down | 47 | 79 | Critical | Core-feature use -42%, 3 champion changes |
| Monthly, logins fading | 131 | 57 | High | Logins -26%, ticket volume 2x |
| New (<60d), stalled setup | 88 | 46 | Medium | Setup milestone 2 never finished |
| Steady core | 354 | 14 | Low | — |
DISTRIBUTION — 7.6% of subscribers sit in Critical but hold 29% of recurring revenue. LTV AT RISK — Critical ~$58k, High ~$41k, Medium ~$17k (avg LTV × tier-midpoint probability, uncalibrated).
PLAYBOOK CALLS — Critical: personal outreach from the founder within 48 hours, aimed at the champion changes — offer a re-onboarding call for the new admin, not a discount. Cost ~$600 of time; at a conservative 15% save rate, ~$9k revenue protected. High: two-week diagnostic sequence from support — one personal email asking what's changed, one session on the feature they stopped using; owner named per account. Medium: automated finish-your-setup nudge plus a product note — 88 people stalling on the same setup step is an onboarding defect, not a marketing problem; filed as an escalation with the LTV figure attached.
RANKED INVESTMENT — 1) Critical outreach ($600, highest return per dollar). 2) High diagnostic sequence ($1,800). 3) Setup-step fix (engineering time, removes next quarter's Medium tier at the source). Post-mortem log opened before the first save attempt goes out.
Connects securely to your tools. The creator never sees your data.
About this skill
Churn is a lagging fact; churn risk is a leading judgment, and it only helps if you read behavior early enough to act. This skill turns raw behavioral signals into a ranked rescue plan. It starts with signal selection done properly: pull your churned customers from the last 6–12 months, look backward at what changed 30, 60, and 90 days before they left, and separate leading signals from lagging ones — with a warning system for seasonal dips and product-change shocks that masquerade as risk. Scoring is a transparent weighted rubric: five signals (engagement trend, recency against each segment's own cadence, support sentiment, value realization, account health events) with anchored 0/50/100 columns you can score by hand and defend in a meeting. Scores map to four tiers — Low, Medium, High, Critical — each with its own save playbook covering action, timing window, channel, messaging tone, owner, and escalation trigger. The money layer estimates lifetime value at risk per segment and ranks interventions by retention ROI with honest, conservative save rates, so a fixed retention budget gets spent where a dollar saves the most revenue. Edge cases cover involuntary payment churn, tiny segments, businesses with no churn history yet, and the moment the real deliverable stops being a campaign and becomes a product escalation. The assessment runs on a cadence, and every cycle ends with a post-mortem log that becomes next cycle's signal list.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Marketing & SEO.
- First-cycle scores use starter signals and uncalibrated probabilities; the skill labels them as such until one cycle of outcomes calibrates the tiers.
- Accuracy depends on the behavioral data you supply — it cannot pull data from your CRM or billing system by itself.
- It recommends playbooks and messaging direction; it does not execute campaigns in your email or CRM tools.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 24 days ago
Permissions
No special permissions declared or detected