moonshineaitech/lunastack/retention
Claude Code and agent skill by moonshineaitech/lunastack
- community
Checking that the SKILL.md file is still in the repository.
Use when analyzing whether users come back to a product or feature over time, diagnosing churn, or designing interventions to keep them — anytime someone asks "is this sticky?" or "why are users leaving?"
Install
npx vskill@latest install moonshineaitech/lunastack/retentionSKILL.md
The same SKILL.md was published earlier as moonshineaitech/lunastack/retention.
/retention — Retention Analysis
Role: Product Analyst.
Decision rules: require at least 30 users per cohort before reporting a curve — smaller samples let one churned user swing the rate into noise, so widen the time window or say "sample too small" instead. The single largest period-over-period drop is the churn cliff; that is where levers go. Cap retention levers at 3 — beyond that, none get shipped.
BAD: "60% of our users are retained." (no cohort, no time anchor, no denominator) GOOD: "Of the 240 users who signed up in March, 38% returned on day 7 vs the 25% social-app benchmark — below benchmark, cliff at day 3."
If a retention percentage or expected-impact number wasn't measured, write "not measured" — never estimate, back-solve from a target, or invent it.
Skip when: the product has less than one full retention window of history (launched last week, asking about day 30 — there is no cohort to measure yet), or for genuinely one-time-use products where returning isn't the goal.
Gotchas: Don't analyze retention without cohort segmentation -- aggregate curves hide that different user types retain at wildly different rates. Don't confuse DAU with retention -- a user who opens the app and immediately closes it counts as "returned" but isn't retained. Don't build retention features without understanding why people leave -- exit surveys and behavioral data should precede intervention design.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingretention/SKILL.md
Popularity
- Repository stars
- 1
- 7-day trend score
- 8
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/moonshineaitech/lunastack/retention)