Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Articulate a compelling north-star product vision that aligns teams and inspires strategic design decisions.
.claude/skills/owl-listener-north-star-vision/SKILL.md| Model | Eval pass | Runs |
|---|---|---|
| gemini-3.6-flash | 100% | 12 |
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 9% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 9% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 14% | 0% |
| case-18 | ✗→✓ | ▲ Improved | 24% | 0% |
| case-19 | ✗→✓ | ▲ Improved | 4% | 0% |
You are an expert in articulating inspiring product visions that unite teams and guide direction.
You help teams define a north-star vision — a compelling future state that inspires alignment and guides trade-offs.
Research synthesis, aspiration workshop, narrative writing, validation, communication.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-06 | pass→pass | 18,396 | 17,640 | -4% | 1 | 1 | 0% | 2,687 | 2,864 | +7% | 0 | 0 | — |
case-01 | fail→pass | 16,808 | 17,158 | +2% | 1 | 1 | 0% | 2,926 | 3,186 | +9% | 0 | 0 | — |
case-02 | pass→pass | 3,914 | 4,233 | +8% | 1 | 1 | 0% | 653 | 993 | +52% | 0 | 0 | — |
case-03 | pass→pass | 6,130 | 7,378 | +20% | 1 | 1 | 0% | 990 | 1,529 | +54% | 0 | 0 | — |
case-04 | pass→pass | 15,419 | 15,774 | +2% | 1 | 1 | 0% | 2,610 | 2,778 | +6% | 0 | 0 | — |
case-05 | pass→pass | 15,206 | 15,562 | +2% | 1 | 1 | 0% | 2,373 | 2,863 | +21% | 0 | 0 | — |
case-07 | pass→pass | 14,922 | 13,356 | -10% | 1 | 1 | 0% | 2,554 | 2,558 | +0% | 0 | 0 | — |
case-08 | fail→pass | 11,567 | 12,934 | +12% | 1 | 1 | 0% | 2,342 | 2,561 | +9% | 0 | 0 | — |
case-09 | fail→pass | 14,033 | 15,443 | +10% | 1 | 1 | 0% | 2,396 | 2,721 | +14% | 0 | 0 | — |
case-10 | pass→pass | 15,711 | 18,027 | +15% | 1 | 1 | 0% | 2,763 | 3,026 | +10% | 0 | 0 | — |
case-11 | pass→pass | 18,631 | 16,852 | -10% | 1 | 1 | 0% | 3,148 | 3,154 | +0% | 0 | 0 | — |
case-20 | pass→pass | 10,732 | 9,976 | -7% | 1 | 1 | 0% | 1,856 | 2,006 | +8% | 0 | 0 | — |
case-12 | pass→pass | 18,881 | 15,044 | -20% | 1 | 1 | 0% | 2,772 | 2,622 | -5% | 0 | 0 | — |
case-13 | pass→pass | 15,224 | 14,671 | -4% | 1 | 1 | 0% | 2,563 | 2,613 | +2% | 0 | 0 | — |
case-14 | pass→pass | 16,306 | 14,604 | -10% | 1 | 1 | 0% | 2,725 | 2,675 | -2% | 0 | 0 | — |
case-15 | pass→pass | 24,013 | 19,815 | -17% | 1 | 1 | 0% | 3,797 | 3,564 | -6% | 0 | 0 | — |
case-16 | pass→pass | 16,222 | 12,590 | -22% | 1 | 1 | 0% | 2,336 | 1,953 | -16% | 0 | 0 | — |
case-17 | pass→pass | 15,793 | 17,345 | +10% | 1 | 1 | 0% | 2,874 | 3,090 | +8% | 0 | 0 | — |
case-18 | fail→pass | 16,868 | 19,965 | +18% | 1 | 1 | 0% | 2,734 | 3,379 | +24% | 0 | 0 | — |
case-19 | fail→pass | 12,246 | 12,211 | -0% | 1 | 1 | 0% | 2,120 | 2,199 | +4% | 0 | 0 | — |
case-21 | pass→pass | 10,995 | 11,611 | +6% | 1 | 1 | 0% | 1,831 | 2,371 | +29% | 0 | 0 | — |
case-22 | pass→pass | 5,061 | 7,443 | +47% | 1 | 1 | 0% | 918 | 1,472 | +60% | 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 +23 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.