留存数据对比 · Retention Data Comparator
对比不同版本、渠道与人群的留存曲线,输出差异、归因与优化建议。 Compare retention curves across versions, channels, and audiences, with differences, attribution, and optimization advice.
$7
Works with the AI Agents you already use
Claude Code
Cursor
Codex CLI
Muse
Dots+22 moreClaude CodeCursorCodex CLIMuseDots
OpenClaw
Manus
Grok
Grok Bot+18 agents留存数据对比 · Retention Data Comparator
Example session with this skill installed
请对比 3 月与 4 月的 D7/D30 留存,以及付费渠道和自然渠道的留存差异。
- Read your context and instructions
- Compiled the retention data comparator
留存数据对比完成。
| 人群 | D7 | D30 | 样本 | 结论 |
|---|---|---|---|---|
| 3 月全量 | 32% | 15% | 80k | 基线 |
| 4 月全量 | 35% | 17% | 88k | 提升显著 |
| 付费渠道 | 28% | 11% | 30k | 低于基线 |
| 自然渠道 | 40% | 20% | 50k | 最优 |
归因
- 4 月提升主要来自新引导流程(覆盖 60% 新用户)。
- 付费渠道首日留存低,疑似素材承诺与产品不符。
Next steps
- 对 4 月新用户按引导版本细分。
- 付费素材做承诺对齐 review。
- 下周复核 D30 是否维持。
Connects securely to your tools. The creator never sees your data.
About this skill
它解决什么问题
保留报告比较原始百分比，没有控制群组、渠道或样本大小，因此团队会追逐虚假的获胜者。
这个技能做什么
- 跨版本、渠道和细分市场调整保留指标。
- 对队列大小和时间窗口进行标准化。
- 突出显示具有统计意义的差异。
- 生成包含可能原因和后续测试的比较表。
为什么比裸提示词强
它强制执行一个比较框架：指标、队列、窗口、增量、置信度、原因，因此保留争论以证据结束。
典型用例
- 比较入职变更前后的 D7 保留率。
- 对付费用户保留率与自然用户保留率进行基准测试。
- 寻找保留率最高的采集渠道。
局限
它会比较您提供的数据；显着性取决于您确认的样本量。
English · 英文介绍
The problem
Retention reports compare raw percentages without controlling for cohorts, channels, or sample size, so teams chase false winners.
What it does
- Aligns retention metrics across versions, channels, and segments.
- Normalizes for cohort size and time windows.
- Highlights statistically meaningful differences.
- Produces a comparison table with likely causes and next tests.
Why this beats prompting it yourself
It enforces a comparison frame: metric, cohort, window, delta, confidence, cause, so retention debates end with evidence.
Use cases
- Comparing D7 retention before and after onboarding changes.
- Benchmarking paid vs organic user retention.
- Finding the highest-retention acquisition channel.
Known limitations
It compares the data you provide; significance depends on sample sizes you confirm.
How to use
Skills on Agensi run inside your AI agent. Copy the prompt, paste it into your agent, and it connects to Agensi and installs this skill for you. If a payment is needed, your agent shows it to you first.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scanned
Verified clean 1 month ago
- Passed all security checks, Safe to install