agentleFS
Infinite-Labs-AIInfinite-Labs-AI/infinite-skills/skills/retention/SKILL.md

retention

Skill43 starsChanged 4 months agoMITView on GitHub

Use when reducing churn, improving activation, cancellation flows, winback, failed payments, renewal, expansion, customer health, or revenue retention.

5 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

3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 3

    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:

    Use product analytics, billing data, CRM notes, cancellation reasons, support tickets, interviews, or lifecycle performance.

    line 12
  2. Distinctive:

    Do not use discounts as the default save tactic.

    line 47
  3. Distinctive:

    Use discounts only when the evidence suggests price or timing is the real barrier.

    line 61

“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

Retention

Find where customers lose momentum and choose practical ways to improve activation, renewal, expansion, or winback.

Map The Customer State

Use product analytics, billing data, CRM notes, cancellation reasons, support tickets, interviews, or lifecycle performance. If unavailable, ask for:

  • Customer lifecycle stages.
  • Activation milestone.
  • Churn or cancellation point.
  • Plan, pricing, and renewal model.
  • Common objections or complaints.
  • Existing save, winback, and dunning flows.

Identify Retention Leaks

Classify by cause:

  • Setup failure: customer never reaches the first useful outcome.
  • Value gap: product works but not enough to justify cost.
  • Habit gap: value exists but usage does not become routine.
  • Champion loss: buyer or user changes.
  • Expectation mismatch: marketing or sales promised the wrong thing.
  • Payment failure: billing breaks an otherwise healthy account.
  • Expansion ceiling: customer cannot grow into the next plan.

Choose Interventions

Match intervention to cause:

  • Activation checklist or concierge setup.
  • Use-case education.
  • Health alerts.
  • Save offer or plan downgrade.
  • Pause option.
  • Failed payment recovery.
  • Renewal proof recap.
  • Expansion trigger.
  • Winback based on prior use case.

Do not use discounts as the default save tactic. If value is unclear, discounting only delays churn.

Choose Retention Plays

Order interventions from least invasive to most commercial:

  • Product fix or setup improvement.
  • Education or lifecycle guidance.
  • Human support or concierge save.
  • Billing repair or dunning.
  • Plan change, pause, or downgrade.
  • Commercial save offer.
  • Winback after exit.

Use discounts only when the evidence suggests price or timing is the real barrier.

Output

Retention map:
Lifecycle stages:
Activation milestone:
Main leak:

Leak diagnosis:
| Stage | Symptom | Evidence | Root cause confidence | First intervention |

Intervention ladder:
1. Product:
2. Education:
3. Human support:
4. Billing:
5. Commercial:

Cancellation flow:
- Ask:
- Route:
- Save option:
- Exit if:

Winback segment:
- Who:
- Why now:
- Message:

Metrics:
- Leading:
- Lagging:

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.