Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Select and design navigation patterns that match product structure, user tasks, and platform conventions.
.claude/skills/owl-listener-navigation-patterns/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-15 | ✗→✓ | ▲ Improved | 98% | 0% |
| case-01 | ✓→✓ | ＝ Same ✓ | 23% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | 27% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | 55% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | 4% | 0% |
You are an expert in designing navigation systems that make products legible, traversable, and orientating.
You select and design the right navigation patterns for a product's information architecture, platform, and usage patterns — so users always know where they are, where they can go, and how to get back.
Present on every screen; provides access to top-level sections.
Scoped to the current section.
High-reach, low-frequency: account, notifications, search, settings, help.
Links between related content.
| Situation | Recommended pattern | |---|---| | Mobile, 3–5 primary destinations | Tab bar | | Desktop app, many destinations or nested structure | Side navigation | | Simple marketing site or docs | Top nav bar | | Deep content hierarchy | Breadcrumbs + local sidebar | | Parallel views of the same content | Tabs or segmented control | | Occasional, non-primary access | Utility nav or overflow menu |
Every navigation item needs a clear active/selected state that survives:
Active state must be distinguishable by more than color alone (weight, underline, indicator bar).
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 11,336 | 7,886 | -30% | 1 | 1 | 0% | 1,722 | 2,122 | +23% | 0 | 0 | — |
case-02 | pass→pass | 15,566 | 16,678 | +7% | 1 | 1 | 0% | 2,498 | 3,162 | +27% | 0 | 0 | — |
case-03 | pass→pass | 12,534 | 14,271 | +14% | 1 | 1 | 0% | 2,013 | 3,121 | +55% | 0 | 0 | — |
case-04 | pass→pass | 12,558 | 8,483 | -32% | 1 | 1 | 0% | 2,197 | 2,289 | +4% | 0 | 0 | — |
case-05 | pass→pass | 12,468 | 13,403 | +7% | 1 | 1 | 0% | 2,074 | 2,923 | +41% | 0 | 0 | — |
case-06 | pass→pass | 11,662 | 12,049 | +3% | 1 | 1 | 0% | 1,951 | 2,680 | +37% | 0 | 0 | — |
case-07 | pass→pass | 6,973 | 6,990 | +0% | 1 | 1 | 0% | 1,225 | 2,014 | +64% | 0 | 0 | — |
case-08 | pass→pass | 9,147 | 11,251 | +23% | 1 | 1 | 0% | 1,488 | 2,836 | +91% | 0 | 0 | — |
case-09 | pass→pass | 8,672 | 8,646 | -0% | 1 | 1 | 0% | 1,409 | 2,176 | +54% | 0 | 0 | — |
case-10 | pass→pass | 11,682 | 12,608 | +8% | 1 | 1 | 0% | 1,941 | 2,792 | +44% | 0 | 0 | — |
case-11 | pass→pass | 10,858 | 10,908 | +0% | 1 | 1 | 0% | 1,934 | 2,540 | +31% | 0 | 0 | — |
case-12 | pass→pass | 10,770 | 8,993 | -16% | 1 | 1 | 0% | 1,701 | 2,213 | +30% | 0 | 0 | — |
case-13 | pass→pass | 6,448 | 5,673 | -12% | 1 | 1 | 0% | 1,022 | 1,648 | +61% | 0 | 0 | — |
case-14 | pass→pass | 14,124 | 13,393 | -5% | 1 | 1 | 0% | 2,129 | 2,818 | +32% | 0 | 0 | — |
case-15 | fail→pass | 7,040 | 8,837 | +26% | 1 | 1 | 0% | 1,087 | 2,153 | +98% | 0 | 0 | — |
case-16 | pass→pass | 8,705 | 10,714 | +23% | 1 | 1 | 0% | 1,384 | 2,465 | +78% | 0 | 0 | — |
case-17 | pass→pass | 13,670 | 12,559 | -8% | 1 | 1 | 0% | 2,175 | 2,834 | +30% | 0 | 0 | — |
case-18 | pass→pass | 12,287 | 12,598 | +3% | 1 | 1 | 0% | 2,197 | 2,885 | +31% | 0 | 0 | — |
case-19 | pass→pass | 13,475 | 13,114 | -3% | 1 | 1 | 0% | 2,341 | 2,968 | +27% | 0 | 0 | — |
case-20 | pass→pass | 9,335 | 9,672 | +4% | 1 | 1 | 0% | 1,836 | 2,556 | +39% | 0 | 0 | — |
case-21 | pass→pass | 3,177 | 3,087 | -3% | 1 | 1 | 0% | 610 | 1,356 | +122% | 0 | 0 | — |
case-22 | pass→pass | 2,103 | 2,192 | +4% | 1 | 1 | 0% | 368 | 1,175 | +219% | 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 +5 percentage points is the difference between those two pass rates over the 22 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.