Agent Skills › MaxKmet/idea-validation-agents › retention-predictor

retention-predictor

GitHub

评估B2C应用创意留存潜力，分析使用频率、习惯形成机制及流失风险。通过六项指标打分并预测D1/D7/D30留存率，输出留存判定结果与JSON报告。

skills/retention-predictor/SKILL.md MaxKmet/idea-validation-agents

Trigger Scenarios

需要评估用户留存策略分析应用习惯养成潜力预测不同时间节点的流失风险

Install

npx skills add MaxKmet/idea-validation-agents --skill retention-predictor -g -y

More Options

Use without installing

npx skills use MaxKmet/idea-validation-agents@retention-predictor

指定 Agent (Claude Code)

npx skills add MaxKmet/idea-validation-agents --skill retention-predictor -a claude-code -g -y

安装 repo 全部 skill

npx skills add MaxKmet/idea-validation-agents --all -g -y

预览 repo 内 skill

npx skills add MaxKmet/idea-validation-agents --list

SKILL.md

Frontmatter

{
    "name": "retention-predictor",
    "description": "Predicts retention potential by evaluating usage frequency, habit formation mechanics, and churn risk factors for a B2C app idea."
}

Skill: retention-predictor

Purpose

Retention determines LTV. An app that churns users in week 1 can't build a business regardless of acquisition. This skill evaluates how sticky the idea is structurally — not based on feature lists, but on the underlying usage pattern and habit formation potential.

Input

Idea slug
App concept description
memory/ideas/<slug>/desire_scores.json (desire strength informs habit potential)
memory/ideas/<slug>/user_extraction.json (usage frequency from pain map)

Evaluation Factors

Factor	High Retention Signal	Low Retention Signal
Usage frequency	Daily or multiple times/day	Weekly or less
External trigger	Clear real-world trigger (meal, workout, payday)	No natural trigger
Progress/reward loop	Clear progress visible over time	No feedback loop
Network effects	Gets better with more users	No network component
Data lock-in	User data accumulates	Nothing to lose by leaving
Habit stack	Fits into existing daily routine	Requires behavior change

Process

Estimate natural usage frequency based on the problem (daily tooth brushing vs. annual tax filing).
Identify external triggers that would cue app usage.
Score habit formation potential (1–5) across the six factors above.
Estimate D1, D7, D30 retention benchmarks for the app category.
Flag high churn risk factors.

Output

Write to memory/ideas/<slug>/retention.json:

{
  "natural_usage_frequency": "multiple daily | daily | weekly | monthly | infrequent",
  "external_trigger": "",
  "habit_formation_score": 0,
  "churn_risk_factors": [],
  "estimated_retention": {
    "d1": 0,
    "d7": 0,
    "d30": 0
  },
  "churn_risk": "low | medium | high",
  "retention_verdict": "sticky | moderate | disposable"
}