home / skills / shaul1991 / shaul-agents-plugin / growth-retention

growth-retention skill

/skills/growth-retention

This skill analyzes cohort retention, uncovers churn drivers, and designs engagement campaigns to boost long-term user participation.

npx playbooks add skill shaul1991/shaul-agents-plugin --skill growth-retention

Review the files below or copy the command above to add this skill to your agents.

Files (1)
SKILL.md
607 B
---
name: growth-retention
description: Retention Manager Agent. 사용자 유지, 참여도 향상, 이탈 방지를 담당합니다.
allowed-tools: Read, Write, Edit, Glob, Grep, WebSearch, WebFetch
---

# Retention Manager Agent

## 역할
사용자 유지율을 분석하고 참여도를 향상시킵니다.

## 담당 업무
- 코호트 리텐션 분석
- 이탈 원인 분석
- 참여도 향상 전략
- 재참여 캠페인 설계
- 습관 형성 설계

## 트리거 키워드
유지, retention, 이탈, 참여, engagement, 리텐션

## 산출물 위치
- 리텐션 분석: `docs/growth/retention/`

Overview

This skill is a Retention Manager Agent that analyzes user retention and designs interventions to reduce churn and boost engagement. It focuses on cohort analysis, churn root cause identification, and building re-engagement and habit-forming strategies. The agent produces actionable recommendations and campaign blueprints to improve long-term user value.

How this skill works

The agent inspects cohort-level metrics, session patterns, and user lifecycle signals to quantify retention and identify drop-off points. It segments users by behavior, runs root-cause diagnostics, and prioritizes fixes by potential impact and effort. Finally, it drafts re-engagement campaigns, onboarding improvements, and habit-forming flows with measurable goals and KPIs.

When to use it

  • You see declining retention or unexplained spikes in churn.
  • You need data-driven prioritization of product fixes and growth experiments.
  • You plan to launch re-engagement campaigns or onboarding updates.
  • You want to design habit-forming flows to increase long-term engagement.

Best practices

  • Start with cohort analysis to compare retention across acquisition channels and release versions.
  • Quantify impact using simple metrics (e.g., D1/D7/D30 retention, churn rate, LTV uplift).
  • Tie recommendations to measurable experiments and define success criteria before launch.
  • Segment users by intent and behavior to tailor re-engagement messaging and incentives.
  • Iterate quickly: run small A/B tests and scale strategies that move key metrics.

Example use cases

  • Diagnose why a recent release saw a D7 retention drop and recommend prioritized fixes.
  • Design a 30-day habit-building onboarding flow for new users with milestone nudges.
  • Create a win-back email and push campaign targeting at-risk cohorts with tailored offers.
  • Build an experiment plan that tests pricing, messaging, and feature nudges to lift retention.

FAQ

What inputs does the agent need?

User event data, cohort definitions, timeframe, and any recent product changes or campaigns to correlate with retention shifts.

How does it prioritize recommendations?

By estimated impact on retention, required implementation effort, and confidence from observed data patterns.