@miranda0808/maya-codex 0.1.0

package/payload/.agents/skills/churn-prevention/SKILL.md

@@ -0,0 +1,424 @@
+---
+name: churn-prevention
+description: "When the user wants to reduce churn, build cancellation flows, set up save offers, recover failed payments, or implement retention strategies. Also use when the user mentions 'churn,' 'cancel flow,' 'offboarding,' 'save offer,' 'dunning,' 'failed payment recovery,' 'win-back,' 'retention,' 'exit survey,' 'pause subscription,' 'involuntary churn,' 'people keep canceling,' 'churn rate is too high,' 'how do I keep users,' or 'customers are leaving.' Use this whenever someone is losing subscribers or wants to build systems to prevent it. For post-cancel win-back email sequences, see email-sequence. For in-app upgrade paywalls, see paywall-upgrade-cro."
+metadata:
+  version: 1.1.0
+---
+
+# Churn Prevention
+
+You are an expert in SaaS retention and churn prevention. Your goal is to help reduce both voluntary churn (customers choosing to cancel) and involuntary churn (failed payments) through well-designed cancel flows, dynamic save offers, proactive retention, and dunning strategies.
+
+## Before Starting
+
+**Use approved context inputs first:**
+In Maya task workflows, start with the approved `TASK-PACKET.md` inputs and listed brand sections. If `PRODUCT.md` is explicitly provided or the work is being done in consult-style standalone usage, read `PRODUCT.md` before asking questions. If `PRODUCT.md` is missing, do not pretend the output is fully brand-calibrated.
+
+Gather this context (ask if not provided):
+
+### 1. Current Churn Situation
+- What's your monthly churn rate? (Voluntary vs. involuntary if known)
+- How many active subscribers?
+- What's the average MRR per customer?
+- Do you have a cancel flow today, or does cancel happen instantly?
+
+### 2. Billing & Platform
+- What billing provider? (Stripe, Chargebee, Paddle, Recurly, Braintree)
+- Monthly, annual, or both billing intervals?
+- Do you support plan pausing or downgrades?
+- Any existing retention tooling? (Churnkey, ProsperStack, Raaft)
+
+### 3. Product & Usage Data
+- Do you track feature usage per user?
+- Can you identify engagement drop-offs?
+- Do you have cancellation reason data from past churns?
+- What's your activation metric? (What do retained users do that churned users don't?)
+
+### 4. Constraints
+- B2B or B2C? (Affects flow design)
+- Self-serve cancellation required? (Some regulations mandate easy cancel)
+- Brand tone for offboarding? (Empathetic, direct, playful)
+
+---
+
+## How This Skill Works
+
+Churn has two types requiring different strategies:
+
+| Type | Cause | Solution |
+|------|-------|----------|
+| **Voluntary** | Customer chooses to cancel | Cancel flows, save offers, exit surveys |
+| **Involuntary** | Payment fails | Dunning emails, smart retries, card updaters |
+
+Voluntary churn is typically 50-70% of total churn. Involuntary churn is 30-50% but is often easier to fix.
+
+This skill supports three modes:
+
+1. **Build a cancel flow** — Design from scratch with survey, save offers, and confirmation
+2. **Optimize an existing flow** — Analyze cancel data and improve save rates
+3. **Set up dunning** — Failed payment recovery with retries and email sequences
+
+---
+
+## Cancel Flow Design
+
+### The Cancel Flow Structure
+
+Every cancel flow follows this sequence:
+
+```
+Trigger → Survey → Dynamic Offer → Confirmation → Post-Cancel
+```
+
+**Step 1: Trigger**
+Customer clicks "Cancel subscription" in account settings.
+
+**Step 2: Exit Survey**
+Ask why they're cancelling. This determines which save offer to show.
+
+**Step 3: Dynamic Save Offer**
+Present a targeted offer based on their reason (discount, pause, downgrade, etc.)
+
+**Step 4: Confirmation**
+If they still want to cancel, confirm clearly with end-of-billing-period messaging.
+
+**Step 5: Post-Cancel**
+Set expectations, offer easy reactivation path, trigger win-back sequence.
+
+### Exit Survey Design
+
+The exit survey is the foundation. Good reason categories:
+
+| Reason | What It Tells You |
+|--------|-------------------|
+| Too expensive | Price sensitivity, may respond to discount or downgrade |
+| Not using it enough | Low engagement, may respond to pause or onboarding help |
+| Missing a feature | Product gap, show roadmap or workaround |
+| Switching to competitor | Competitive pressure, understand what they offer |
+| Technical issues / bugs | Product quality, escalate to support |
+| Temporary / seasonal need | Usage pattern, offer pause |
+| Business closed / changed | Unavoidable, learn and let go gracefully |
+| Other | Catch-all, include free text field |
+
+**Survey best practices:**
+- 1 question, single-select with optional free text
+- 5-8 reason options max (avoid decision fatigue)
+- Put most common reasons first (review data quarterly)
+- Don't make it feel like a guilt trip
+- "Help us improve" framing works better than "Why are you leaving?"
+
+### Dynamic Save Offers
+
+The key insight: **match the offer to the reason.** A discount won't save someone who isn't using the product. A feature roadmap won't save someone who can't afford it.
+
+**Offer-to-reason mapping:**
+
+| Cancel Reason | Primary Offer | Fallback Offer |
+|---------------|---------------|----------------|
+| Too expensive | Discount (20-30% for 2-3 months) | Downgrade to lower plan |
+| Not using it enough | Pause (1-3 months) | Free onboarding session |
+| Missing feature | Roadmap preview + timeline | Workaround guide |
+| Switching to competitor | Competitive comparison + discount | Feedback session |
+| Technical issues | Escalate to support immediately | Credit + priority fix |
+| Temporary / seasonal | Pause subscription | Downgrade temporarily |
+| Business closed | Skip offer (respect the situation) | — |
+
+### Save Offer Types
+
+**Discount**
+- 20-30% off for 2-3 months is the sweet spot
+- Avoid 50%+ discounts (trains customers to cancel for deals)
+- Time-limit the offer ("This offer expires when you leave this page")
+- Show the dollar amount saved, not just the percentage
+
+**Pause subscription**
+- 1-3 month pause maximum (longer pauses rarely reactivate)
+- 60-80% of pausers eventually return to active
+- Auto-reactivation with advance notice email
+- Keep their data and settings intact
+
+**Plan downgrade**
+- Offer a lower tier instead of full cancellation
+- Show what they keep vs. what they lose
+- Position as "right-size your plan" not "downgrade"
+- Easy path back up when ready
+
+**Feature unlock / extension**
+- Unlock a premium feature they haven't tried
+- Extend trial of a higher tier
+- Works best for "not getting enough value" reasons
+
+**Personal outreach**
+- For high-value accounts (top 10-20% by MRR)
+- Route to customer success for a call
+- Personal email from founder for smaller companies
+
+### Cancel Flow UI Patterns
+
+```
+┌─────────────────────────────────────┐
+│  We're sorry to see you go          │
+│                                     │
+│  What's the main reason you're      │
+│  cancelling?                        │
+│                                     │
+│  ○ Too expensive                    │
+│  ○ Not using it enough              │
+│  ○ Missing a feature I need         │
+│  ○ Switching to another tool        │
+│  ○ Technical issues                 │
+│  ○ Temporary / don't need right now │
+│  ○ Other: [____________]            │
+│                                     │
+│  [Continue]                         │
+│  [Never mind, keep my subscription] │
+└─────────────────────────────────────┘
+         ↓ (selects "Too expensive")
+┌─────────────────────────────────────┐
+│  What if we could help?             │
+│                                     │
+│  We'd love to keep you. Here's a    │
+│  special offer:                     │
+│                                     │
+│  ┌───────────────────────────────┐  │
+│  │  25% off for the next 3 months│  │
+│  │  Save $XX/month               │  │
+│  │                               │  │
+│  │  [Accept Offer]               │  │
+│  └───────────────────────────────┘  │
+│                                     │
+│  Or switch to [Basic Plan] at       │
+│  $X/month →                         │
+│                                     │
+│  [No thanks, continue cancelling]   │
+└─────────────────────────────────────┘
+```
+
+**UI principles:**
+- Keep the "continue cancelling" option visible (no dark patterns)
+- One primary offer + one fallback, not a wall of options
+- Show specific dollar savings, not abstract percentages
+- Use the customer's name and account data when possible
+- Mobile-friendly (many cancellations happen on mobile)
+
+For detailed cancel flow patterns by industry and billing provider, see [references/cancel-flow-patterns.md](references/cancel-flow-patterns.md).
+
+---
+
+## Churn Prediction & Proactive Retention
+
+The best save happens before the customer ever clicks "Cancel."
+
+### Risk Signals
+
+Track these leading indicators of churn:
+
+| Signal | Risk Level | Timeframe |
+|--------|-----------|-----------|
+| Login frequency drops 50%+ | High | 2-4 weeks before cancel |
+| Key feature usage stops | High | 1-3 weeks before cancel |
+| Support tickets spike then stop | High | 1-2 weeks before cancel |
+| Email open rates decline | Medium | 2-6 weeks before cancel |
+| Billing page visits increase | High | Days before cancel |
+| Team seats removed | High | 1-2 weeks before cancel |
+| Data export initiated | Critical | Days before cancel |
+| NPS score drops below 6 | Medium | 1-3 months before cancel |
+
+### Health Score Model
+
+Build a simple health score (0-100) from weighted signals:
+
+```
+Health Score = (
+  Login frequency score × 0.30 +
+  Feature usage score   × 0.25 +
+  Support sentiment     × 0.15 +
+  Billing health        × 0.15 +
+  Engagement score      × 0.15
+)
+```
+
+| Score | Status | Action |
+|-------|--------|--------|
+| 80-100 | Healthy | Upsell opportunities |
+| 60-79 | Needs attention | Proactive check-in |
+| 40-59 | At risk | Intervention campaign |
+| 0-39 | Critical | Personal outreach |
+
+### Proactive Interventions
+
+**Before they think about cancelling:**
+
+| Trigger | Intervention |
+|---------|-------------|
+| Usage drop >50% for 2 weeks | "We noticed you haven't used [feature]. Need help?" email |
+| Approaching plan limit | Upgrade nudge (not a wall — paywall-upgrade-cro handles this) |
+| No login for 14 days | Re-engagement email with recent product updates |
+| NPS detractor (0-6) | Personal follow-up within 24 hours |
+| Support ticket unresolved >48h | Escalation + proactive status update |
+| Annual renewal in 30 days | Value recap email + renewal confirmation |
+
+---
+
+## Involuntary Churn: Payment Recovery
+
+Failed payments cause 30-50% of all churn but are the most recoverable.
+
+### The Dunning Stack
+
+```
+Pre-dunning → Smart retry → Dunning emails → Grace period → Hard cancel
+```
+
+### Pre-Dunning (Prevent Failures)
+
+- **Card expiry alerts**: Email 30, 15, and 7 days before card expires
+- **Backup payment method**: Prompt for a second payment method at signup
+- **Card updater services**: Visa/Mastercard auto-update programs (reduces hard declines 30-50%)
+- **Pre-billing notification**: Email 3-5 days before charge for annual plans
+
+### Smart Retry Logic
+
+Not all failures are the same. Retry strategy by decline type:
+
+| Decline Type | Examples | Retry Strategy |
+|-------------|----------|----------------|
+| Soft decline (temporary) | Insufficient funds, processor timeout | Retry 3-5 times over 7-10 days |
+| Hard decline (permanent) | Card stolen, account closed | Don't retry — ask for new card |
+| Authentication required | 3D Secure, SCA | Send customer to update payment |
+
+**Retry timing best practices:**
+- Retry 1: 24 hours after failure
+- Retry 2: 3 days after failure
+- Retry 3: 5 days after failure
+- Retry 4: 7 days after failure (with dunning email escalation)
+- After 4 retries: Hard cancel with reactivation path
+
+**Smart retry tip:** Retry on the day of the month the payment originally succeeded (if Day 1 worked before, retry on Day 1). Stripe Smart Retries handles this automatically.
+
+### Dunning Email Sequence
+
+| Email | Timing | Tone | Content |
+|-------|--------|------|---------|
+| 1 | Day 0 (failure) | Friendly alert | "Your payment didn't go through. Update your card." |
+| 2 | Day 3 | Helpful reminder | "Quick reminder — update your payment to keep access." |
+| 3 | Day 7 | Urgency | "Your account will be paused in 3 days. Update now." |
+| 4 | Day 10 | Final warning | "Last chance to keep your account active." |
+
+**Dunning email best practices:**
+- Direct link to payment update page (no login required if possible)
+- Show what they'll lose (their data, their team's access)
+- Don't blame ("your payment failed" not "you failed to pay")
+- Include support contact for help
+- Plain text performs better than designed emails for dunning
+
+### Recovery Benchmarks
+
+| Metric | Poor | Average | Good |
+|--------|------|---------|------|
+| Soft decline recovery | <40% | 50-60% | 70%+ |
+| Hard decline recovery | <10% | 20-30% | 40%+ |
+| Overall payment recovery | <30% | 40-50% | 60%+ |
+| Pre-dunning prevention | None | 10-15% | 20-30% |
+
+For the complete dunning playbook with provider-specific setup, see [references/dunning-playbook.md](references/dunning-playbook.md).
+
+---
+
+## Metrics & Measurement
+
+### Key Churn Metrics
+
+| Metric | Formula | Target |
+|--------|---------|--------|
+| Monthly churn rate | Churned customers / Start-of-month customers | <5% B2C, <2% B2B |
+| Revenue churn (net) | (Lost MRR - Expansion MRR) / Start MRR | Negative (net expansion) |
+| Cancel flow save rate | Saved / Total cancel sessions | 25-35% |
+| Offer acceptance rate | Accepted offers / Shown offers | 15-25% |
+| Pause reactivation rate | Reactivated / Total paused | 60-80% |
+| Dunning recovery rate | Recovered / Total failed payments | 50-60% |
+| Time to cancel | Days from first churn signal to cancel | Track trend |
+
+### Cohort Analysis
+
+Segment churn by:
+- **Acquisition channel** — Which channels bring stickier customers?
+- **Plan type** — Which plans churn most?
+- **Tenure** — When do most cancellations happen? (30, 60, 90 days?)
+- **Cancel reason** — Which reasons are growing?
+- **Save offer type** — Which offers work best for which segments?
+
+### Cancel Flow A/B Tests
+
+Test one variable at a time:
+
+| Test | Hypothesis | Metric |
+|------|-----------|--------|
+| Discount % (20% vs 30%) | Higher discount saves more | Save rate, LTV impact |
+| Pause duration (1 vs 3 months) | Longer pause increases return rate | Reactivation rate |
+| Survey placement (before vs after offer) | Survey-first personalizes offers | Save rate |
+| Offer presentation (modal vs full page) | Full page gets more attention | Save rate |
+| Copy tone (empathetic vs direct) | Empathetic reduces friction | Save rate |
+
+**How to run cancel flow experiments:** Use the **ab-test-setup** skill to design statistically rigorous tests. PostHog is a good fit for cancel flow experiments — its feature flags can split users into different flows server-side, and its funnel analytics track each step of the cancel flow (survey → offer → accept/decline → confirm). See the [PostHog integration guide](../../tools/integrations/posthog.md) for setup.
+
+---
+
+## Common Mistakes
+
+- **No cancel flow at all** — Instant cancel leaves money on the table. Even a simple survey + one offer saves 10-15%
+- **Making cancellation hard to find** — Hidden cancel buttons breed resentment and bad reviews. Many jurisdictions require easy cancellation (FTC Click-to-Cancel rule)
+- **Same offer for every reason** — A blanket discount doesn't address "missing feature" or "not using it"
+- **Discounts too deep** — 50%+ discounts train customers to cancel-and-return for deals
+- **Ignoring involuntary churn** — Often 30-50% of total churn and the easiest to fix
+- **No dunning emails** — Letting payment failures silently cancel accounts
+- **Guilt-trip copy** — "Are you sure you want to abandon us?" damages brand trust
+- **Not tracking save offer LTV** — A "saved" customer who churns 30 days later wasn't really saved
+- **Pausing too long** — Pauses beyond 3 months rarely reactivate. Set limits.
+- **No post-cancel path** — Make reactivation easy and trigger win-back emails, because some churned users will want to come back
+
+---
+
+## Tool Integrations
+
+For implementation, see the [tools registry](../../tools/REGISTRY.md).
+
+### Retention Platforms
+
+| Tool | Best For | Key Feature |
+|------|----------|-------------|
+| **Churnkey** | Full cancel flow + dunning | AI-powered adaptive offers, 34% avg save rate |
+| **ProsperStack** | Cancel flows with analytics | Advanced rules engine, Stripe/Chargebee integration |
+| **Raaft** | Simple cancel flow builder | Easy setup, good for early-stage |
+| **Chargebee Retention** | Chargebee customers | Native integration, was Brightback |
+
+### Billing Providers (Dunning)
+
+| Provider | Smart Retries | Dunning Emails | Card Updater |
+|----------|:------------:|:--------------:|:------------:|
+| **Stripe** | Built-in (Smart Retries) | Built-in | Automatic |
+| **Chargebee** | Built-in | Built-in | Via gateway |
+| **Paddle** | Built-in | Built-in | Managed |
+| **Recurly** | Built-in | Built-in | Built-in |
+| **Braintree** | Manual config | Manual | Via gateway |
+
+### Related CLI Tools
+
+| Tool | Use For |
+|------|---------|
+| `stripe` | Subscription management, dunning config, payment retries |
+| `customer-io` | Dunning email sequences, retention campaigns |
+| `posthog` | Cancel flow A/B tests via feature flags, funnel analytics |
+| `mixpanel` / `ga4` | Usage tracking, churn signal analysis |
+| `segment` | Event routing for health scoring |
+
+---
+
+## Related Skills
+
+- **email-sequence**: For win-back email sequences after cancellation
+- **paywall-upgrade-cro**: For in-app upgrade moments and trial expiration
+- **pricing-strategy**: For plan structure and annual discount strategy
+- **onboarding-cro**: For activation to prevent early churn
+- **analytics-tracking**: For setting up churn signal events
+- **ab-test-setup**: For testing cancel flow variations with statistical rigor

package/payload/.agents/skills/churn-prevention/evals/evals.json

@@ -0,0 +1,93 @@
+{
+  "skill_name": "churn-prevention",
+  "evals": [
+    {
+      "id": 1,
+      "prompt": "Our SaaS product has a 7% monthly churn rate and we need to bring it down. We're a $49/month project management tool with about 2,000 paying customers. Can you help us design a churn prevention strategy?",
+      "expected_output": "Should use approved TASK-PACKET.md inputs first in Maya task workflows, and read PRODUCT.md directly when it is explicitly provided or when the work is consult-style standalone. Should address both voluntary and involuntary churn. Should design a cancel flow following the framework: trigger → exit survey → dynamic save offer → confirmation → post-cancel nurture. Should include the 7 exit survey categories and recommend dynamic save offers mapped to each cancellation reason. Should address dunning for involuntary churn (pre-dunning, smart retry, email sequence, grace period). Should recommend a health score model. Should provide prioritized implementation plan.",
+      "assertions": [
+        "Uses approved TASK-PACKET.md inputs or PRODUCT.md context first",
+        "Addresses both voluntary and involuntary churn",
+        "Designs cancel flow with proper stages",
+        "Includes exit survey with multiple categories",
+        "Maps save offers to cancellation reasons",
+        "Addresses dunning stack for payment recovery",
+        "Recommends health score model",
+        "Provides prioritized implementation plan"
+      ],
+      "files": []
+    },
+    {
+      "id": 2,
+      "prompt": "We keep losing customers because their credit cards expire. About 15% of our churn is from failed payments. How do we fix this?",
+      "expected_output": "Should identify this as involuntary churn / payment recovery. Should apply the dunning stack framework: pre-dunning (card expiration reminders before failure), smart retry (retry logic based on failure reason), dunning email sequence (escalating urgency), grace period, and eventual cancellation. Should provide specific timing for each stage. Should recommend payment recovery tools and strategies (card updater services, backup payment methods). Should include recovery rate benchmarks.",
+      "assertions": [
+        "Identifies as involuntary churn / payment recovery",
+        "Applies dunning stack framework",
+        "Includes pre-dunning card expiration reminders",
+        "Includes smart retry logic",
+        "Provides dunning email sequence with escalating urgency",
+        "Recommends grace period before cancellation",
+        "Mentions card updater services or backup payment methods",
+        "Includes recovery benchmarks"
+      ],
+      "files": []
+    },
+    {
+      "id": 3,
+      "prompt": "what should we show users when they click the cancel button? right now they just go straight to cancellation with no attempt to save them",
+      "expected_output": "Should trigger on casual phrasing. Should design the cancel flow: cancel button → exit survey → dynamic save offer → confirmation → post-cancel. Should detail the exit survey categories (too expensive, missing feature, switched to competitor, not using enough, technical issues, bad support, other). Should provide dynamic save offers matched to each reason (e.g., too expensive → discount offer, missing feature → roadmap update, not using enough → onboarding help). Should include copy recommendations for each screen. Should warn against dark patterns (making it impossible to cancel).",
+      "assertions": [
+        "Triggers on casual phrasing",
+        "Designs multi-step cancel flow",
+        "Includes exit survey with 7 categories",
+        "Provides dynamic save offers mapped to reasons",
+        "Includes copy recommendations",
+        "Warns against dark patterns",
+        "Includes confirmation and post-cancel steps"
+      ],
+      "files": []
+    },
+    {
+      "id": 4,
+      "prompt": "How do we identify which customers are at risk of churning before they actually cancel? We want to be proactive.",
+      "expected_output": "Should apply the health score model framework. Should define health score components: product usage signals (login frequency, feature adoption, key action completion), engagement signals (support tickets, NPS responses, email engagement), and account signals (contract type, company growth, stakeholder changes). Should recommend scoring methodology (0-100 scale). Should define risk tiers and recommended interventions for each tier. Should suggest data sources and implementation approach.",
+      "assertions": [
+        "Applies health score model framework",
+        "Defines usage-based health signals",
+        "Defines engagement-based health signals",
+        "Defines account-based health signals",
+        "Recommends scoring methodology",
+        "Defines risk tiers with interventions",
+        "Suggests data sources and implementation"
+      ],
+      "files": []
+    },
+    {
+      "id": 5,
+      "prompt": "Our exit survey shows that 40% of cancellations say 'too expensive' as the reason. What save offers should we try?",
+      "expected_output": "Should reference the dynamic save offers mapped to the 'too expensive' reason. Should suggest multiple offer types: temporary discount, downgrade to cheaper plan, annual billing discount, pause instead of cancel, extended trial of current plan. Should recommend testing different offers to find what works best. Should also dig deeper — 'too expensive' often masks other issues (not seeing value, not using enough features). Should suggest follow-up questions in the exit survey to get more specific.",
+      "assertions": [
+        "References save offers for 'too expensive' reason",
+        "Suggests multiple offer types (discount, downgrade, pause)",
+        "Recommends testing different offers",
+        "Notes that 'too expensive' often masks other issues",
+        "Suggests deeper follow-up questions",
+        "Provides specific save offer copy or structure"
+      ],
+      "files": []
+    },
+    {
+      "id": 6,
+      "prompt": "We want to set up a win-back email sequence for customers who already cancelled. Can you help write those emails?",
+      "expected_output": "Should recognize this overlaps with email sequence work. Should defer to or cross-reference the email-sequence skill for writing the actual email sequence. May provide churn-specific context (timing post-cancel, re-engagement hooks, win-back offer strategy) but should make clear that email-sequence is the right skill for designing and writing the full email sequence.",
+      "assertions": [
+        "Recognizes overlap with email sequence work",
+        "References or defers to email-sequence skill",
+        "May provide churn-specific context for the sequence",
+        "Does not attempt to write a full email sequence"
+      ],
+      "files": []
+    }
+  ]
+}