Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Brainstorm team-level OKRs aligned with company objectives — qualitative objectives with measurable key results. Use when setting quarterly OKRs, aligning team goals with company strategy, drafting objectives, or learning how to write effective OKRs.
.claude/skills/phuryn-brainstorm-okrs/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | 102% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 124% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 18% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 49% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -42% | 0% |
You are a veteran product leader responsible for defining Objectives and Key Results (OKRs) for the team working on $ARGUMENTS. Your OKRs must be ambitious, measurable, and clearly aligned with company-wide strategy.
OKRs bridge vision and execution by combining inspirational qualitative objectives with measurable quantitative key results. This skill generates three alternative OKR sets to spark strategic discussion.
OKR (Christina Wodtke, Radical Focus):
OKRs, KPIs, and NSM are interconnected — not alternatives. Don't compare them in a table without explaining their relationship:
OKRs are fundamentally about: (1) Setting a single, inspiring goal. (2) Empowering a team to determine the optimal approach. (3) Continuously monitoring progress, learning from failures, and improving.
Objective: Delight new users with an effortless onboarding experience Key Results:
OKRs-[team-name]-[quarter].md| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 14,429 | 19,086 | +32% | 1 | 1 | 0% | 2,684 | 4,502 | +68% | 0 | 0 | — |
case-02 | pass→fail | 13,970 | 16,788 | +20% | 1 | 1 | 0% | 2,346 | 3,918 | +67% | 0 | 0 | — |
case-03 | pass→pass | 27,387 | 39,935 | +46% | 1 | 1 | 0% | 4,770 | 7,135 | +50% | 0 | 0 | — |
case-04 | pass→pass | 18,230 | 13,906 | -24% | 1 | 1 | 0% | 3,119 | 3,400 | +9% | 0 | 0 | — |
case-05 | pass→pass | 10,563 | 15,755 | +49% | 1 | 1 | 0% | 1,830 | 3,714 | +103% | 0 | 0 | — |
case-06 | fail→fail | 15,580 | 19,535 | +25% | 1 | 1 | 0% | 2,215 | 3,386 | +53% | 0 | 0 | — |
case-07 | fail→pass | 9,709 | 14,521 | +50% | 1 | 1 | 0% | 1,658 | 3,343 | +102% | 0 | 0 | — |
case-13 | fail→fail | 9,917 | 14,052 | +42% | 1 | 1 | 0% | 1,762 | 3,486 | +98% | 0 | 0 | — |
case-08 | fail→pass | 5,648 | 9,545 | +69% | 1 | 1 | 0% | 1,048 | 2,351 | +124% | 0 | 0 | — |
case-09 | fail→pass | 13,307 | 10,219 | -23% | 1 | 1 | 0% | 2,318 | 2,738 | +18% | 0 | 0 | — |
case-10 | fail→pass | 13,690 | 14,579 | +6% | 1 | 1 | 0% | 2,231 | 3,316 | +49% | 0 | 0 | — |
case-11 | fail→pass | 43,474 | 12,199 | -72% | 1 | 1 | 0% | 5,377 | 3,140 | -42% | 0 | 0 | — |
case-12 | fail→pass | 13,345 | 12,777 | -4% | 1 | 1 | 0% | 1,840 | 2,974 | +62% | 0 | 0 | — |
case-14 | pass→pass | 13,137 | 16,875 | +28% | 1 | 1 | 0% | 2,249 | 3,240 | +44% | 0 | 0 | — |
case-15 | pass→pass | 13,503 | 12,499 | -7% | 1 | 1 | 0% | 2,208 | 3,113 | +41% | 0 | 0 | — |
case-16 | pass→pass | 9,283 | 14,979 | +61% | 1 | 1 | 0% | 1,648 | 3,552 | +116% | 0 | 0 | — |
case-17 | pass→pass | 13,419 | 17,891 | +33% | 1 | 1 | 0% | 2,050 | 3,382 | +65% | 0 | 0 | — |
case-18 | fail→pass | 17,526 | 24,735 | +41% | 1 | 1 | 0% | 2,685 | 3,681 | +37% | 0 | 0 | — |
case-19 | fail→pass | 10,470 | 17,815 | +70% | 1 | 1 | 0% | 1,425 | 3,371 | +137% | 0 | 0 | — |
case-20 | fail→fail | 6,049 | 7,596 | +26% | 1 | 1 | 0% | 861 | 2,189 | +154% | 0 | 0 | — |
case-21 | fail→fail | 13,890 | 13,864 | -0% | 1 | 1 | 0% | 2,450 | 3,469 | +42% | 0 | 0 | — |
case-22 | pass→pass | 11,992 | 11,811 | -2% | 1 | 1 | 0% | 2,246 | 2,926 | +30% | 0 | 0 | — |
case-23 | fail→pass | 11,397 | 14,605 | +28% | 1 | 1 | 0% | 1,896 | 3,421 | +80% | 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. 23 cases were attempted. The headline lift of +35 percentage points is the difference between those two pass rates over the 23 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
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.