retention-analysis
Skill9 starsChanged 7 months agoMITView on GitHub
Template-driven analysis of retention metrics. Guides through interpreting D1/D7/D30, session metrics, and funnel analysis. Generates actionable improvement plan.
5 other projects use a version of this.
Adopted by
Most recently taken up by
- liangdabiao/claudesdk-data-chattheir own version, first seen May 24, 2026
- talgacapri/pm-ostheir own version, first seen May 23, 2026
- liangdabiao/claude-data-analysis-ultra-maintheir own version, first seen May 9, 2026
- nbirkner/digital-braintheir own version, first seen Apr 12, 2026
- SkeneTechnologies/plg-skillstheir own version, first seen Jan 26, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- liangdabiao/claude-data-analysis-ultra-main★ 282same name
- SkeneTechnologies/plg-skills★ 19same name
- liangdabiao/claudesdk-data-chat★ 4same name
- nbirkner/digital-brain★ 0same name
- talgacapri/pm-os★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository51 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- asset-auditSkill
- asset-from-imageSkill
- balance-checkSkill
- brainstormSkill
- bug-reportSkill
- changelogSkill
- code-reviewSkill
- datastore-reviewSkill
- design-reviewSkill
- design-systemSkill
- doctorSkill
- economy-auditSkill
- estimateSkill
- exploit-checkSkill
- gate-checkSkill
- gddSkill
- generate-assetSkill
- hotfixSkill
- launch-checklistSkill
- luau-lintSkill
- map-systemsSkill
- milestone-reviewSkill
- monetization-modelSkill
- onboardSkill
- patch-notesSkill
- perf-profileSkill
- project-stage-detectSkill
- prototypeSkill
- publish-reviewSkill
- release-checklistSkill
- remotes-auditSkill
- retrospectiveSkill
- reverse-documentSkill
- scope-checkSkill
- sprint-planSkill
- startSkill
- studio-inspectSkill
- studio-screenshotSkill
- studio-testSkill
- team-combatSkill
- team-economySkill
- team-polishSkill
- team-releaseSkill
- team-uiSkill
- tech-debtSkill
- wiki-ingestSkill
- wiki-lintSkill
- wiki-querySkill
- wiki-seedSkill
- wiki-updateSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
2
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
- Distinctive: line 13
Ask the user to provide or pull from Roblox Analytics:
- Distinctive: line 44
No reason to come back
“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.
Files
/retention-analysis — Retention Metrics Analysis
Delegate to: analytics-retention-specialist
Steps
1. Gather Data
Ask the user to provide or pull from Roblox Analytics:
- Retention: D1, D7, D30 percentages (current + last 30 days)
- Sessions: Average session length, sessions per day per user
- Funnel: New player funnel step completion rates
- Concurrent Users: Peak CCU, average CCU trends
- Revenue: ARPDAU, conversion rate (if applicable)
- Platform split: Mobile vs. PC vs. console %
2. Benchmark Against Targets
| Metric | Target | Current | Delta | Status |
| D1 Retention | > 25% | ?% | ? | 🟢/🟡/🔴 |
| D7 Retention | > 12% | ?% | ? | 🟢/🟡/🔴 |
| D30 Retention | > 5% | ?% | ? | 🟢/🟡/🔴 |
| Avg Session | > 15 min | ? | ? | 🟢/🟡/🔴 |
| Sessions/Day | > 1.5 | ? | ? | 🟢/🟡/🔴 |
| Conversion | > 3% | ?% | ? | 🟢/🟡/🔴 |
3. Identify Weakness
Which metric is furthest from target? That's the priority.
4. Hypothesis Generation
For the weak metric, brainstorm causes:
Low D1 Retention:
- FTUE is confusing or slow
- No first-session reward
- Performance issues on first load
- Crashes on first play
Low D7 Retention:
- No reason to come back
- Daily reward not compelling
- Content runs out quickly
- Social features missing
Low Session Length:
- Session loop too short
- Nothing to do after core loop
- AFK handling kicks players
Low Conversion:
- Monetization not discoverable
- Items not appealing
- Too expensive for perceived value
- Pay-to-win pushback
5. Recommend Experiments
For top 2-3 hypotheses, recommend experiments:
- Change: What to change
- Measure: What metric will tell us if it worked
- Duration: How long to run
- Sample: How many players needed
6. Generate Report
Save to production/analytics/retention-<date>.md on approval using .claude/docs/templates/retention-report-template.md.
# Retention Analysis: [Period]
**Date**: YYYY-MM-DD
**Period analyzed**: [start] to [end]
## Summary
[1-3 sentences on overall health]
## Metric Status
[Table from step 2]
## Primary Concern
**[Metric name]** is [X%] below target.
## Hypotheses
1. [Hypothesis 1 with reasoning]
2. [Hypothesis 2 with reasoning]
3. [Hypothesis 3 with reasoning]
## Recommended Experiments
### Experiment A: [Name]
- Hypothesis: [What we think will work]
- Change: [Specific change to make]
- Measure: [Metric to watch]
- Duration: 7 days
- Required sample: 500 players per variant
## Next Steps
1. Decide which experiment to run first
2. Implement via live-ops-specialist
3. Monitor metric daily
4. Review results in 7-14 daysDoes 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
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.

