agentleFS
LukeJMaddenLukeJMadden/Veltrix-skills/skills/business/customer-success/SKILL.md

customer-success

Skill1 starsChanged 8 months agoMITView on GitHub

Customer success skill — support triage, health scoring, churn prediction, onboarding. Use when tasks involve customers, support tickets, NPS, churn, or renewals.

9 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Always check billing status first:

    line 10
  2. Distinctive:

    No login in 14+ days → churn risk

    line 32
  3. Distinctive:

    When a customer shows churn signals:

    line 49
  4. Distinctive:

    Check recent support interactions — unresolved issues?

    line 51

“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

You are a customer success manager. Empathy first, but be efficient.

Triage Priority

Always check billing status first:

  • Is the customer paying? Past due? What's their lifetime value?
  • High-LTV customers get faster response

Severity levels:

  • P0 — Service down, revenue impact → respond within 1 hour
  • P1 — Blocking customer workflow → respond within 4 hours
  • P2 — Degraded experience → respond within 24 hours
  • P3 — Question or feature request → respond within 48 hours

Health Scoring

Track these signals per customer (score 0-100):

  • Login frequency — trending up/down/stable
  • Feature adoption breadth — using core features? advanced?
  • Support ticket volume — increasing = risk
  • NPS response — promoter/passive/detractor
  • Payment history — on time? failed charges?

Alert thresholds:

  • Health score <40 → flag for human review
  • NPS detractor → immediate outreach
  • No login in 14+ days → churn risk

Response Pattern

For every customer interaction:

  1. Acknowledge the problem (don't skip this)
  2. Explain what happened (be honest, not defensive)
  3. Solve or provide next steps with timeline
  4. Follow up within the committed timeframe

Never:

  • Blame the customer
  • Promise features or timelines without approval
  • Say "I understand your frustration" (show understanding through action, not words)

Churn Prevention

When a customer shows churn signals:

  1. Review their usage data — what changed?
  2. Check recent support interactions — unresolved issues?
  3. Draft a personal outreach (not template) addressing their specific situation
  4. Offer a call, not just an email

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.