Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Strategic product leadership toolkit for Head of Product including OKR cascade generation, market analysis, vision setting, and team scaling. Use for strategic planning, goal alignment, competitive analysis, and organizational design.
.claude/skills/davila7-product-strategist/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-06 | ✗→✓ | ▲ Improved | -40% | 0% |
| case-01 | ✗→✓ | ▲ Improved | -56% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -21% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -69% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -46% | 0% |
Strategic toolkit for Head of Product to drive vision, alignment, and organizational excellence.
Automatically cascades company OKRs down to product and team levels with alignment tracking.
Usage: python scripts/okr_cascade_generator.py [strategy]
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-06 | fail→pass | 3,748 | 1,578 | -58% | 1 | 1 | 0% | 658 | 395 | -40% | 0 | 0 | — |
case-01 | fail→pass | 13,029 | 2,026 | -84% | 1 | 1 | 0% | 1,095 | 482 | -56% | 0 | 0 | — |
case-07 | pass→pass | 7,353 | 1,637 | -78% | 1 | 1 | 0% | 1,344 | 413 | -69% | 0 | 0 | — |
case-02 | fail→pass | 3,178 | 3,544 | +12% | 1 | 1 | 0% | 528 | 415 | -21% | 0 | 0 | — |
case-03 | fail→pass | 10,532 | 2,354 | -78% | 1 | 1 | 0% | 1,883 | 578 | -69% | 0 | 0 | — |
case-04 | fail→pass | 6,370 | 2,187 | -66% | 1 | 1 | 0% | 1,008 | 549 | -46% | 0 | 0 | — |
case-05 | fail→pass | 11,276 | 1,673 | -85% | 1 | 1 | 0% | 1,924 | 418 | -78% | 0 | 0 | — |
case-08 | fail→pass | 5,185 | 2,226 | -57% | 1 | 1 | 0% | 943 | 520 | -45% | 0 | 0 | — |
case-09 | pass→pass | 5,570 | 2,236 | -60% | 1 | 1 | 0% | 1,022 | 521 | -49% | 0 | 0 | — |
case-10 | pass→pass | 5,625 | 2,415 | -57% | 1 | 1 | 0% | 1,108 | 507 | -54% | 0 | 0 | — |
case-11 | fail→pass | 3,899 | 1,683 | -57% | 1 | 1 | 0% | 680 | 384 | -44% | 0 | 0 | — |
case-12 | pass→pass | 7,890 | 3,031 | -62% | 1 | 1 | 0% | 1,382 | 705 | -49% | 0 | 0 | — |
case-13 | pass→pass | 4,953 | 2,345 | -53% | 1 | 1 | 0% | 797 | 520 | -35% | 0 | 0 | — |
case-14 | pass→pass | 8,498 | 2,430 | -71% | 1 | 1 | 0% | 1,552 | 483 | -69% | 0 | 0 | — |
case-15 | pass→pass | 5,959 | 2,304 | -61% | 1 | 1 | 0% | 1,043 | 558 | -47% | 0 | 0 | — |
case-16 | pass→pass | 4,916 | 1,622 | -67% | 1 | 1 | 0% | 843 | 388 | -54% | 0 | 0 | — |
case-17 | pass→pass | 6,317 | 1,930 | -69% | 1 | 1 | 0% | 1,076 | 478 | -56% | 0 | 0 | — |
case-18 | pass→pass | 5,272 | 1,762 | -67% | 1 | 1 | 0% | 908 | 395 | -56% | 0 | 0 | — |
case-19 | fail→pass | 3,744 | 1,273 | -66% | 1 | 1 | 0% | 619 | 338 | -45% | 0 | 0 | — |
case-20 | pass→pass | 5,207 | 1,494 | -71% | 1 | 1 | 0% | 835 | 368 | -56% | 0 | 0 | — |
case-21 | pass→pass | 6,795 | 2,353 | -65% | 1 | 1 | 0% | 1,102 | 541 | -51% | 0 | 0 | — |
case-22 | pass→pass | 10,676 | 4,543 | -57% | 1 | 1 | 0% | 1,763 | 936 | -47% | 0 | 0 | — |
case-23 | pass→pass | 12,682 | 12,510 | -1% | 1 | 1 | 0% | 2,656 | 2,453 | -8% | 0 | 0 | — |
case-24 | pass→pass | 17,602 | 16,050 | -9% | 1 | 1 | 0% | 3,125 | 3,068 | -2% | 0 | 0 | — |
case-25 | fail→pass | 8,379 | 1,380 | -84% | 1 | 1 | 0% | 1,625 | 367 | -77% | 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. 25 cases were attempted. The headline lift of +40 percentage points is the difference between those two pass rates over the 25 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.