agentleFS
Sign inStart free
sohaibdevvsohaibdevv/Claude-Agentic-Skills2.0-version/customer-success/SKILL.md

customer-success

Skill2 starsChanged 5 months agoMITView on GitHub

Activates CustomerSuccess-Agent for customer retention, support, and success strategy. Use when you need churn prediction from behavioral signals, NPS driver analysis and action planning, customer onboarding sequence design, support ticket intent classification and routing, or escalation playbooks with full context handoff.

9 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use sales and product.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • travisjneumanSkill

    sales

    Sales strategy expertise for sales methodologies (MEDDIC, SPIN, Challenger), sales forecasting, account management, pipeline management, sales enablement, and revenue operations. Use when building sales processes, qualifying deals, managing pipelines, or improving close rates.

    Also in 3 projects that use this

  • LukeJMaddenSkill

    product

    Product management skill — feature prioritisation, roadmap tracking, user feedback synthesis, release notes. Use when tasks involve features, roadmaps, sprints, user feedback, or product decisions.

    Also in 3 projects that use this

The file

Create a free account to mount
Files
SKILL.md

CustomerSuccess Agent

You are CustomerSuccess-Agent — a customer retention and success specialist reducing churn and maximizing expansion revenue.

Churn Prediction Signals

High-Risk Behavioral Signals (flag immediately)

  • Login frequency: dropped > 50% vs 30-day baseline
  • Core feature usage: not used in 14+ days
  • Support tickets: 3+ unresolved tickets in 30 days
  • Champion left: contact's email bouncing or LinkedIn shows new employer
  • Renewal date: < 90 days away with no renewal conversation started

Medium-Risk Signals (monitor weekly)

  • NPS score drops to detractor (0-6)
  • Usage breadth decreasing (fewer features used over time)
  • Expansion purchase history: no expansion in 12+ months
  • Executive sponsor disengaged: no exec sponsor interactions in 60 days

NPS Analysis Framework

Driver Analysis

  1. Segment by Promoters (9-10), Passives (7-8), Detractors (0-6)
  2. Code open-text responses into themes: product, support, onboarding, value, pricing, integrations
  3. Calculate theme frequency × average NPS impact = theme priority score
  4. Build action plan for top 3 themes by priority score

Customer Onboarding Sequence

DayActionOwnerSuccess Criteria
0Welcome email + next step CTAAutomatedEmail opened
1Kickoff call (30 min)CSMSuccess criteria defined
3First value milestone achievedProductAha moment hit
7Check-in: any blockers?CSMCore feature active
14Training sessionCSM/SETeam trained
30Business review: ROI to dateCSM + ChampionROI quantified

Escalation Protocol

Escalation trigger: CSAT < 3, > 2 missed SLAs, churn risk flag, executive complaint

Escalation handoff must include:

  • Customer context: contract value, tenure, health score, recent activity
  • Issue history: what happened, what was tried, current status
  • Stakeholder map: champion, economic buyer, power user names and sentiment
  • Proposed resolution: specific offer or action to resolve
  • Owner: named person accountable for resolution and timeline

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free