deanpeters/Product-Manager-Skills / skills/usage-data-investigation
usage-data-investigation
VerifiedInvestigate what customers actually do from product analytics, with every claim labeled Fact, Inference, or Assumption. Use when you need behavior evidence, not opinions, before deciding.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 12.5 KB |
| examples/sample-industrial.md | markdown | 2.1 KB |
| examples/sample.md | markdown | 2.1 KB |
| template.md | markdown | 1.6 KB |
examples/sample.md
View on GitHub# Usage Data Investigation Example: SaaS
**Question:** trials of the Route Optimizer start, but few reach a first optimized route. Where do they stall, and who?
**Unit:** trial account · **Window:** March trials · **Decision:** where to focus onboarding work
**Why this example exists:** the funnel showed one step, but the segment cut showed it was really
one kind of account, and the data had nothing to say about why.
---
```markdown
## Data check
- Tracking: "first optimized route" fires on route save; verified on three test accounts.
- Definition: unchanged in window.
- Missing: 6 internal test accounts removed; 3 trials from a partner API not tracked (noted).
- Sample: 212 trial accounts. Enough to read the funnel; thin for segments under 20.
## Funnel (March trials, N = 212)
| Step | Count | To next |
|---|---|---|
| Trial started | 212 | 78% |
| Dispatcher invited | 165 | 71% |
| Day loaded | 117 | 42% |
| First route optimized | 49 | n/a |
**Biggest drop:** day loaded → first optimized (117 → 49).
## Segments
| Segment | N | Reached first route |
|---|---|---|
| 50-100 technicians | 88 | 24 (27%) |
| 101-300 technicians | 84 | 22 (26%) |
| Over 300 | 40 | 3 (8%) |
## Findings
1. **Fact:** 49 of 212 trials (23%) reached a first optimized route within 7 days.
2. **Fact:** the biggest drop is between loading a day and optimizing it (117 to 49).
3. **Fact:** accounts over 300 technicians reached it at 8% (3 of 40) vs about 27% elsewhere.
4. **Inference:** large accounts may need a configuration step the smaller ones skip. (Not shown.)
5. **Assumption:** dispatchers don't see value. (The data can't show this.)
## What people must answer
| Question | Who | Ask |
|---|---|---|
| Why do large accounts stop after loading a day? | Dispatchers at 5 large trial accounts | "Walk me through what you did after the day loaded." |
```
## What to learn from this
- **The average (23%) hid a segment (8%).** The finding was in the cut.
- **Finding 4 is labeled an Inference,** and finding 5 an Assumption nobody should act on.
- **The investigation ends with five phone calls,** which is what the data pointed toward.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| deprecation-and-migrationaddyosmani/agent-skillsManages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another. Use when migrating a database schema in production, such as renaming or dropping a column without downtime (expand/contract). Use when deciding whether to maintain or sunset existing code. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| performance-optimizationaddyosmani/agent-skillsOptimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when N+1 query patterns need fixing, or when profiling reveals bottlenecks. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| agent-cost-reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |
| agent-cost-reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |