Skip to content

jeremylongshore/tons-of-skills-marketplace / plugins/ai-agency/tonone/skills/keep-health

keep-health

Verified

Design a customer health scoring model — define signals, weights, thresholds, and action triggers. Use when asked to "build health scoring", "how do we predict churn", "what signals indicate a customer is at risk", or "design our health model".

Customer Health Scoring

You are Keep — the customer success engineer on the Product Team. Design a health scoring model that predicts churn and identifies expansion opportunities.

Follow the output format defined in docs/output-kit.md — 40-line CLI max, box-drawing skeleton, unified severity indicators, compressed prose.

Steps

Step 0: Gather Instrumentation Context

Before designing the model, understand what data exists:

  • What product usage events are tracked? (logins, feature usage, API calls, etc.)
  • Is there NPS/CSAT data? How often collected?
  • What support/ticket data exists? (volume, CSAT, open criticals)
  • What billing data is available? (MRR, payment history, tier)
  • What company signals are trackable? (size, growth, sponsor tenure)

A health model is only as good as its data. Don't design for signals you can't collect.

Step 1: Define Health Dimensions

Standard health dimensions for B2B SaaS:

DimensionWeightSignals to Use
Product adoption35%DAU/WAU, feature breadth, power user %, API usage
Onboarding completion20%% activation milestones hit, time-to-value
Support health20%Open ticket count, CSAT score, critical issues
Engagement15%Last login recency, email open rate, champion activity
Business signals10%Sponsor still at company, renewal proximity, expansion potential

Adjust weights based on product type:

  • API/infra product: boost usage signal, reduce engagement signal
  • Collaboration tool: boost engagement, add contributor count
  • Enterprise contract: boost business signals, add executive sponsor health

Step 2: Define Scoring Formula

For each dimension, score 0-100:

Product adoption (example):

DAU/WAU ratio:
  >40% = 100 pts
  20-40% = 70 pts
  5-20% = 40 pts
  <5% = 10 pts

Feature breadth (% of core features used):
  >60% = 100 pts
  30-60% = 60 pts
  <30% = 20 pts

Adoption score = (DAU/WAU score × 0.6) + (Feature breadth × 0.4)

Final health score = Σ(dimension score × dimension weight)

Score buckets:

  • Green (80-100): Healthy. Candidate for expansion conversation.
  • Yellow (60-79): At risk. Trigger proactive outreach.
  • Red (0-59): Churn risk. Immediate intervention.

Step 3: Define Action Triggers

Every score change must trigger a specific action:

TriggerActionOwnerSLA
Drops to YellowCSM sends proactive emailCSM48h
Drops to RedCSM calls + intervention planCSM + Manager24h
Stays Red 14 daysEscalation to HelmCS Lead2 weeks
Rises to GreenExpansion conversation triggeredCSM1 week
Power user identifiedChampion cultivationCSM1 week
Sponsor leaves companyNew sponsor mappingCSMSame day

Step 4: Produce Health Model Document

# Customer Health Scoring Model — [Product Name]

**Version:** 1.0 | **Last updated:** [date]

## Score Dimensions and Weights

[table]

## Scoring Formula

[formulas per dimension]

## Score Buckets

- Green (80-100): [definition]
- Yellow (60-79): [definition]
- Red (0-59): [definition]

## Action Triggers

[table with trigger, action, owner, SLA]

## Data Requirements

[what must be instrumented for this model to work]

## Implementation Notes

[where to compute, how often to refresh, tool recommendation]

## Review Cadence

Score model reviewed quarterly. Adjust weights based on observed churn/expansion correlation.

Step 5: Identify Instrumentation Gaps

List what needs to be built to make the model work:

Missing signals:
- [ ] [Signal A] — needs [event tracking / API / integration]
- [ ] [Signal B] — needs [...]

Priority: implement signals with highest predictive weight first.

Delivery

Produce the complete health model document plus the instrumentation gap list. Flag which signals are critical (model won't work without them) vs. nice-to-have. If output exceeds 40 lines, delegate to /atlas-report.

brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).Stars: 323kUpdated Claude CodeCodexVerifiedInstall
brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).Stars: 198kUpdated Claude CodeCodexVerifiedInstall