Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Brainstorm an inspiring, achievable, and emotional product vision that motivates teams and aligns stakeholders. Use when defining or refining a product vision, creating a vision statement, or aligning the team around a shared direction.
.claude/skills/phuryn-product-vision/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-12 | ✗→✓ | ▲ Improved | -21% | 0% |
| case-01 | ✗→✓ | ▲ Improved | 14% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -13% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 4% | 0% |
| case-13 | ✗→✓ | ▲ Improved | -9% | 0% |
A product vision answers: "How can we inspire people? What are we aspiring to achieve? What values do we uphold?" Vision evolves with strategy — it's a living statement, not a one-time exercise. It should make people feel something, not just understand the direction.
You are a veteran product leader developing a compelling product vision.
Your task is to brainstorm a product vision for $ARGUMENTS.
Provide a vision statement that is:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-12 | fail→pass | 15,750 | 9,992 | -37% | 1 | 1 | 0% | 2,696 | 2,137 | -21% | 0 | 0 | — |
case-09 | pass→pass | 10,636 | 10,438 | -2% | 1 | 1 | 0% | 1,849 | 2,215 | +20% | 0 | 0 | — |
case-10 | pass→pass | 16,683 | 10,416 | -38% | 1 | 1 | 0% | 2,616 | 2,234 | -15% | 0 | 0 | — |
case-01 | fail→pass | 14,579 | 12,049 | -17% | 1 | 1 | 0% | 2,318 | 2,649 | +14% | 0 | 0 | — |
case-02 | fail→fail | 14,074 | 12,763 | -9% | 1 | 1 | 0% | 2,283 | 2,313 | +1% | 0 | 0 | — |
case-03 | fail→fail | 11,939 | 14,646 | +23% | 1 | 1 | 0% | 1,366 | 2,389 | +75% | 0 | 0 | — |
case-11 | fail→pass | 19,097 | 12,689 | -34% | 1 | 1 | 0% | 2,806 | 2,443 | -13% | 0 | 0 | — |
case-04 | pass→pass | 11,424 | 9,858 | -14% | 1 | 1 | 0% | 1,477 | 2,107 | +43% | 0 | 0 | — |
case-05 | fail→fail | 7,988 | 9,920 | +24% | 1 | 1 | 0% | 1,215 | 2,118 | +74% | 0 | 0 | — |
case-06 | fail→pass | 14,490 | 12,939 | -11% | 1 | 1 | 0% | 2,207 | 2,286 | +4% | 0 | 0 | — |
case-07 | pass→pass | 20,725 | 10,312 | -50% | 1 | 1 | 0% | 2,608 | 2,136 | -18% | 0 | 0 | — |
case-08 | fail→fail | 5,002 | 7,812 | +56% | 1 | 1 | 0% | 795 | 1,761 | +122% | 0 | 0 | — |
case-13 | fail→pass | 16,465 | 11,349 | -31% | 1 | 1 | 0% | 2,645 | 2,410 | -9% | 0 | 0 | — |
case-14 | pass→pass | 14,301 | 12,477 | -13% | 1 | 1 | 0% | 2,253 | 2,071 | -8% | 0 | 0 | — |
case-15 | fail→pass | 13,088 | 11,656 | -11% | 1 | 1 | 0% | 2,052 | 2,403 | +17% | 0 | 0 | — |
case-16 | pass→pass | 16,106 | 15,398 | -4% | 1 | 1 | 0% | 2,492 | 2,338 | -6% | 0 | 0 | — |
case-17 | fail→pass | 14,070 | 11,329 | -19% | 1 | 1 | 0% | 2,250 | 2,443 | +9% | 0 | 0 | — |
case-18 | pass→pass | 13,656 | 14,127 | +3% | 1 | 1 | 0% | 1,875 | 2,313 | +23% | 0 | 0 | — |
case-19 | pass→pass | 10,874 | 12,196 | +12% | 1 | 1 | 0% | 1,760 | 2,497 | +42% | 0 | 0 | — |
case-20 | pass→pass | 21,958 | 21,973 | +0% | 1 | 1 | 0% | 2,897 | 3,396 | +17% | 0 | 0 | — |
case-21 | pass→pass | 18,839 | 19,967 | +6% | 1 | 1 | 0% | 3,669 | 3,679 | +0% | 0 | 0 | — |
case-22 | pass→pass | 12,399 | 11,288 | -9% | 1 | 1 | 0% | 2,289 | 2,485 | +9% | 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 +32 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.