Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Design first-run experiences that get users to value quickly without overwhelming them.
.claude/skills/owl-listener-onboarding-design/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-20 | ✓→✗ | ▼ Worse | 23% | 0% |
| case-01 | ✓→✓ | = Same ✓ | 50% | 0% |
| case-02 | ✓→✓ | = Same ✓ | 20% | 0% |
| case-03 | ✓→✓ | = Same ✓ | 54% | 0% |
| case-05 | ✓→✓ | = Same ✓ | 87% | 0% |
You are an expert in designing onboarding flows that orient users, build confidence, and accelerate time-to-value.
You design the end-to-end first-run experience — from sign-up through the first meaningful action — so new users understand what the product does, why it matters to them, and how to get started.
Teach features in context, at the moment they're relevant, rather than in a dedicated onboarding flow. Best for complex tools with many features and experienced users.
A linear sequence that walks users through required configuration before they can use the product. Best for products that can't function without initial setup (team tools, data integrations, configuration-heavy apps).
Pre-populate the product with example content so users experience a fully-functional product before adding their own data. Best for products where an empty state defeats comprehension (dashboards, project tools, CRMs).
Guided walkthrough of the actual product UI, highlighting key areas. Best used sparingly for 3–5 core concepts; avoid encyclopedic tours.
The empty state a new user sees is their first experience of the core loop. Design it intentionally:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 9,917 | 8,865 | -11% | 1 | 1 | 0% | 1,571 | 2,362 | +50% | 0 | 0 | — |
case-02 | pass→pass | 9,047 | 6,613 | -27% | 1 | 1 | 0% | 1,641 | 1,977 | +20% | 0 | 0 | — |
case-03 | pass→pass | 12,992 | 14,012 | +8% | 1 | 1 | 0% | 2,039 | 3,149 | +54% | 0 | 0 | — |
case-04 | fail→fail | 10,432 | 7,107 | -32% | 1 | 1 | 0% | 1,681 | 2,137 | +27% | 0 | 0 | — |
case-05 | pass→pass | 7,169 | 7,935 | +11% | 1 | 1 | 0% | 1,190 | 2,230 | +87% | 0 | 0 | — |
case-06 | pass→pass | 12,097 | 11,764 | -3% | 1 | 1 | 0% | 2,008 | 2,906 | +45% | 0 | 0 | — |
case-07 | pass→pass | 11,938 | 10,572 | -11% | 1 | 1 | 0% | 2,227 | 2,915 | +31% | 0 | 0 | — |
case-08 | pass→pass | 14,333 | 13,183 | -8% | 1 | 1 | 0% | 2,240 | 3,182 | +42% | 0 | 0 | — |
case-09 | pass→pass | 13,100 | 12,178 | -7% | 1 | 1 | 0% | 2,019 | 2,894 | +43% | 0 | 0 | — |
case-19 | pass→pass | 14,572 | 13,877 | -5% | 1 | 1 | 0% | 2,605 | 3,397 | +30% | 0 | 0 | — |
case-10 | pass→pass | 8,978 | 7,399 | -18% | 1 | 1 | 0% | 1,511 | 2,250 | +49% | 0 | 0 | — |
case-11 | fail→fail | 8,266 | 9,849 | +19% | 1 | 1 | 0% | 1,500 | 2,603 | +74% | 0 | 0 | — |
case-12 | pass→pass | 10,642 | 10,439 | -2% | 1 | 1 | 0% | 1,752 | 2,639 | +51% | 0 | 0 | — |
case-13 | pass→pass | 13,044 | 15,959 | +22% | 1 | 1 | 0% | 2,049 | 3,468 | +69% | 0 | 0 | — |
case-14 | pass→pass | 11,141 | 9,631 | -14% | 1 | 1 | 0% | 1,838 | 2,357 | +28% | 0 | 0 | — |
case-15 | pass→pass | 12,483 | 10,811 | -13% | 1 | 1 | 0% | 2,076 | 2,681 | +29% | 0 | 0 | — |
case-16 | pass→pass | 11,683 | 12,167 | +4% | 1 | 1 | 0% | 1,950 | 2,962 | +52% | 0 | 0 | — |
case-17 | pass→pass | 10,298 | 11,215 | +9% | 1 | 1 | 0% | 1,816 | 2,789 | +54% | 0 | 0 | — |
case-18 | pass→pass | 12,542 | 10,302 | -18% | 1 | 1 | 0% | 2,288 | 2,847 | +24% | 0 | 0 | — |
case-20 | pass→fail | 15,583 | 15,872 | +2% | 1 | 1 | 0% | 2,920 | 3,595 | +23% | 0 | 0 | — |
case-21 | pass→pass | 12,678 | 13,914 | +10% | 1 | 1 | 0% | 2,284 | 3,249 | +42% | 0 | 0 | — |
case-22 | pass→pass | 8,258 | 7,654 | -7% | 1 | 1 | 0% | 1,602 | 2,397 | +50% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of -100 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Other measured skills in the registry, with their headline benchmark lift.