Business & Finance CSChurnRetention

Customer Success Manager

Monitor customer health, predict churn risk, and identify expansion.

$skillfish add ~skills/customer-success-manager

Capabilities Real Examples Get Started Models & Context

What This Skill Can Do

Concrete capabilities you get when you install this skill.

Design customer health scoring models with leading and lagging indicators

Build onboarding programs that reduce time-to-value for new accounts

Create QBR frameworks that strengthen executive relationships and surface expansion

Identify expansion opportunities through usage signals and business reviews

Build churn prediction models and early warning intervention playbooks

Design customer advocacy programs that generate referrals and case studies

Real Conversations

See how the Customer Success Manager skill responds to actual requests. These are representative examples of what your AI agent will produce.

You

3 of our enterprise accounts (>$50K ARR each) haven't logged in for 2 weeks. How do I run a save play?

Agent

Two weeks of silence from $50K+ accounts is a critical churn signal — act before the QBR or renewal conversation forces your hand.

Triage First — Rank the 3 Accounts:

Signal	Weight
Days since last login	High
Open support tickets	High
Champion still at company?	Critical
Upcoming renewal date	High
NPS/CSAT from last survey	Medium

If the champion has left the company in the past 60 days, that's your root cause — re-engagement requires finding a new champion, not just a check-in call.

The Save Play (run in parallel for all 3):

Day 1 — Internal:

Pull product usage data: which features were they using before going dark? What stopped?
Check CRM: any recent support tickets, NPS responses, or unanswered emails?
Talk to their AE: any intel on budget cycles, team changes, or competing priorities?

Day 2 — Outreach: Do NOT send a generic check-in. Send value-first:

"Hi [Name] — I pulled your account data and noticed [specific usage drop]. I put together 3 things your team could be doing with [feature] that your peers in [industry] are using to [outcome]. Worth a 20-minute call this week?"

Week 1 — Executive Escalation (for accounts at churn risk):

Loop in your VP of CS or CEO for a direct exec-to-exec outreach
Frame it as a strategic partnership review, not a rescue call

Success metric: Get a scheduled call within 5 business days for all 3 accounts.

What does the usage data show — are they completely inactive or using a subset of features?

You

We have 140 B2B customers, $2.8M ARR. Our CSMs manage accounts reactively — we only find out about churn risk when a customer asks to cancel. I want to build a health score that gives us 60-90 days of early warning. What variables should I use and how do I weight them?

Agent

Reactive churn response is expensive — 60-90 days of warning gives you enough time to actually intervene. Here's how to build the model.

Health Score Variable Framework:

Usage Signals (40% weight — most predictive):

Weekly active users / seats purchased (>80% = healthy; <40% = risk)
Feature adoption breadth — are they using core + expansion features or just one module?
Login frequency trend — flat, growing, or declining over 30/60/90 days?
API usage or integration health (if applicable)

Relationship Signals (25% weight):

Champion engagement: opened last 3 emails? Attended last QBR?
Stakeholder count: single-threaded (1 contact) = high risk
Executive sponsor contact in last 90 days?
Champion role change or departure in last 90 days

Business Signals (20% weight):

NPS / CSAT score and trend
Open support tickets > 7 days old
Any escalated issues in last 60 days?

Commercial Signals (15% weight):

Days to renewal
Expansion potential (seats available, features not purchased)
Payment history

Scoring:

Green (70-100): Healthy, focus on expansion
Yellow (50-69): Watch list, CSM proactive outreach
Red (0-49): At-risk, save play initiated

Implementation path: Start with the top 3 usage metrics + champion engagement — you can build this in Salesforce, HubSpot, or a spreadsheet before buying a dedicated CS platform.

What's your current tech stack for tracking product usage?

Get Started

How to install and use this skill in your preferred environment.

Skills are designed for AI coding agents (Claude Code, Cursor, Windsurf) and IDE-based workflows where the agent can read files, run scripts, and act on your codebase. Web-based AI can use the knowledge and frameworks, but won't have tool access.

Models & Context

Which AI models and context windows work best with this skill.

Recommended Models

Best

Claude Opus 4 Claude Sonnet 4 GPT-4.1 Gemini 2.5 Pro Grok 3 Kimi K2

Good

Claude Haiku 4.5 GPT-4.1 mini Gemini 2.5 Flash Grok 3 mini

Larger models produce more detailed, production-ready outputs.

Context Window

This skill's SKILL.md is typically 3–10 KB — fits in any modern context window.

8K Skill only

32K+ Skill + conversation

100K+ Skill + references + codebase

All current frontier models (Claude, GPT, Gemini) support 100K+ context. Use the full window for complex multi-service work.

Pro tips for best results

1

Be specific

Include numbers — users, budget, RPS — so the skill can size the architecture.

2

Share constraints

Compliance needs, team size, and existing stack all improve the output.

3

Iterate

Start with a high-level design, then ask follow-ups for IaC, cost analysis, or security review.

4

Combine skills

Pair with companion skills below for end-to-end coverage.

Ready to try Customer Success Manager?

Install the skill and start getting expert-level guidance in your workflow — any agent, any IDE.