sales-customer-success
Customer success strategy across platforms — health scores, churn prevention, onboarding playbooks, expansion revenue, QBRs, CS metrics, platform comparison. Use when health scores aren't predicting churn, customers are churning and you don't know why, onboarding takes too long, expansion revenue is flat, need to design CS playbooks, choosing between Vitally vs Gainsight vs ChurnZero vs Totango, NRR is declining, or building a CS team from scratch. Do NOT use for NPS/CSAT survey methodology (use /sales-customer-feedback) or ecommerce visitor identity resolution (use /sales-retention).
What this skill does
# Customer Success Strategy
Help the user design, optimize, and scale customer success programs — from building health scores and churn playbooks through onboarding optimization, expansion strategy, and CS platform selection.
## Step 1 — Gather context
If `references/learnings.md` exists, read it first for accumulated knowledge.
Ask the user:
1. **What do you need help with?**
- A) Building or fixing a health score model
- B) Reducing churn — understanding why customers leave
- C) Onboarding — accelerating time-to-value for new customers
- D) Expansion — upsell, cross-sell, identifying growth opportunities
- E) CS playbooks — designing automated workflows for key moments
- F) Choosing a CS platform (Vitally, Gainsight, ChurnZero, etc.)
- G) CS metrics — NRR, GRR, logo retention, time-to-value
- H) QBRs / business reviews — structure, cadence, content
- I) Building/scaling a CS team — hiring, book-of-business, ratios
- J) Something else — describe it
2. **What type of business?**
- A) B2B SaaS (self-serve / PLG)
- B) B2B SaaS (sales-led, mid-market)
- C) B2B SaaS (enterprise, high-touch)
- D) B2B services / consulting
- E) Other
3. **Current CS tooling?** (Vitally, Gainsight, ChurnZero, Totango, spreadsheets, CRM-only, none)
4. **Customer count and ACV?** (Rough ranges: <50 customers, 50-500, 500-5000, 5000+; ACV: <$5K, $5-50K, $50-500K, $500K+)
**If the user's request already provides enough context, skip to the relevant step.** Lead with your best-effort answer, then ask 1-2 clarifying questions at the end.
## Step 2 — Route or answer directly
If the request maps to a platform-specific skill, route:
- Gainsight platform questions → `/sales-gainsight {your question}`
- Vitally platform questions → `/sales-vitally {your question}`
- Planhat platform questions → `/sales-planhat {your question}`
- ChurnZero platform questions → `/sales-churnzero {your question}`
- Totango platform questions → `/sales-totango {your question}`
- NPS/CSAT/CES survey methodology → `/sales-customer-feedback {your question}`
- Ecommerce visitor identity/retention → `/sales-retention {your question}`
- In-app messaging for onboarding → `/sales-in-app-messaging {your question}`
- Enterprise digital adoption (Whatfix) → `/sales-whatfix {your question}`
- CRM data quality for CS → `/sales-data-hygiene {your question}`
Otherwise, answer directly using the strategy guidance below.
## Step 3 — Customer success strategy
### Health score design
**The 4-metric framework** (start here, expand later):
| Category | What to measure | Signal type | Example indicators |
|---|---|---|---|
| **Product usage** | Are they using the product? | Leading | DAU/MAU ratio, key feature adoption, login frequency |
| **Engagement** | Are they talking to you? | Leading | Email opens, meeting attendance, support interactions |
| **Outcomes** | Are they getting value? | Lagging | Goal completion, ROI metrics, time-to-value |
| **Sentiment** | How do they feel? | Lagging | NPS score, CSAT trend, champion engagement |
**Weighting guidelines:**
- Weight product usage highest (40-50%) — it's the strongest churn predictor
- Don't weight NPS above 15-20% — it's a lagging indicator
- Adjust weights by segment — enterprise health depends more on champion engagement, PLG depends more on usage
- Don't change weights for 6-10 months after initial setup — you need stable data to validate
**Scoring model:**
- Use a 0-100 or 0-10 composite score
- Define thresholds: Green (healthy), Yellow (at-risk), Red (critical)
- Set thresholds based on actual churn data, not gut feel — run a retroactive analysis
### Churn prevention
**Early warning signals (by priority):**
1. **Champion leaves** — the single strongest churn predictor. Track job changes via LinkedIn/enrichment tools.
2. **Usage decline** — 20%+ drop in key feature usage over 2-4 weeks
3. **Support escalations** — increasing ticket volume or severity
4. **Engagement drop** — missing QBRs, not responding to emails, skipping training
5. **Contract/billing signals** — late payments, downgrade requests, procurement inquiries
**Response playbook by signal:**
| Signal | Response | Timeline |
|---|---|---|
| Champion left | Executive outreach + new champion identification | Within 48 hours |
| Usage declined 20%+ | CSM call + usage review + retraining offer | Within 1 week |
| Health score dropped to Yellow | Check-in email + value reaffirmation | Within 3 days |
| Health score dropped to Red | Executive sponsor escalation + save plan | Within 24 hours |
| Renewal < 90 days + Red health | Save team assembled (CS + Sales + Exec) | Immediately |
### Customer onboarding
**Time-to-value framework:**
1. **Define "first value"** — what's the moment the customer says "this is working"? Map it.
2. **Milestone-based progression** — don't use time-based milestones ("Week 2: do X"). Use outcome-based: "Complete when customer has sent their first campaign."
3. **Track onboarding health separately** — a new customer's health score is meaningless until they've activated. Use project completion % instead.
**Common onboarding stalls and fixes:**
- **Data migration stuck**: Offer white-glove migration for high-ACV accounts; self-serve import tools for low-ACV
- **Champion too busy**: Identify 2-3 stakeholders during kickoff, not just the champion
- **Technical blockers**: Engineering liaison on standby for first 30 days
- **No executive sponsor**: Get exec buy-in during handoff from sales
### Expansion revenue
**Expansion triggers:**
- Usage approaching plan limits (seats, API calls, storage)
- New department or team adopting the product
- Customer asking about features on higher tier
- Champion promoted (now has budget authority)
- Company raised funding or had strong earnings
**Expansion playbook:**
1. Identify the trigger signal (automated via CS platform or manual)
2. CSM validates the opportunity is real (not just a data blip)
3. Warm handoff to AE/AM with context package (usage data, stakeholder map, recommended package)
4. Joint call: CSM provides continuity, AE handles commercial
### CS platform comparison
| Platform | Best for | Pricing | Key strength |
|---|---|---|---|
| **Vitally** | Mid-market B2B SaaS, fast setup | Request pricing (3 tiers) | Modern UI, fast time-to-value, AI copilot |
| **Gainsight** | Enterprise, complex orgs | ~$30K+/year | Deepest feature set, Gartner #1 Leader |
| **ChurnZero** | Mid-market, real-time analytics | Custom | Customer Monitoring score (9.2/10), in-app engagement |
| **Totango** | Enterprise, quick implementation | ~$50K+/year | Modular SuccessBLOCs, quick deploy |
| **Custify** | SMB-mid, affordable | From ~$999/mo | Good value, lifecycle-focused |
| **Planhat** | Data-heavy teams | Custom | Strong data modeling, flexible health scores |
**Decision framework:**
- **< 50 customers, < $5K ACV**: Spreadsheets + CRM is fine. Don't buy a CS platform yet.
- **50-500 customers, $5-50K ACV**: Vitally or ChurnZero — fast setup, good mid-market fit
- **500+ customers, $50K+ ACV**: Gainsight or Totango — enterprise features, complex org support
- **PLG / tech-touch**: Vitally (Tech-Touch plan) or ChurnZero — automation-first design
### CS metrics
| Metric | Formula | Benchmark (B2B SaaS) | Why it matters |
|---|---|---|---|
| **NRR** (Net Revenue Retention) | (Start MRR + expansion - contraction - churn) / Start MRR | 100-120% | The single best CS metric — >100% means you grow even without new customers |
| **GRR** (Gross Revenue Retention) | (Start MRR - contraction - churn) / Start MRR | 85-95% | Shows retention without expansion masking churn |
| **Logo retention** | (Customers end - new) / Customers start | 85-95% | Raw customer count retention |
| **Time-to-value** | Days from contract signed to first value milestone | 14-60 days | Shorter = better retention + expansion |
| **CSAT / NPS** | Survey-based | NPS 30-50 | Sentiment indicator, not a target |
## Step 4 — ActionRelated in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.