Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Generates structured OKR plans (Objectives and Key Results) for teams and companies following Google/Intel methodology. Takes company goals, team function, quarter, and current metrics to produce a comprehensive okr-plan.md with objectives, key results, scoring criteria, alignment mapping, tracking cadence, and retrospective templates.
.claude/skills/onewave-ai-okr-generator/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 13% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 61% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -47% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 177% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 140% | 0% |
Generate a comprehensive, actionable okr-plan.md from user inputs, applying the Google/Intel OKR framework.
references/methodology.md -- Core OKR principles (non-negotiable rules to apply).references/inputs.md -- The four required inputs plus optional context.references/output-template.md -- Exact structure of the generated okr-plan.md.references/best-practices.md -- Appendix content (common mistakes, OKR cycle, grading by KR type, reading list).references/inputs.md. Collect the four required inputs: company goals, team function, quarter/period, current metrics/baseline. If any are missing, ask for them. Never fabricate baselines.references/methodology.md and apply every core principle. Objectives are qualitative and inspirational (no numbers); key results are quantitative and measurable (always a number).references/best-practices.md.references/output-template.md as okr-plan.md in the working directory (or a user-specified path). Produce at least 400 substantive lines, no filler.okr-plan-engineering.md, okr-plan-marketing.md).[ADJUSTED], and include rationale per change.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 32,250 | 43,302 | +34% | 1 | 1 | 0% | 6,319 | 7,113 | +13% | 0 | 0 | — |
case-02 | fail→pass | 26,857 | 27,833 | +4% | 1 | 1 | 0% | 6,342 | 7,135 | +13% | 0 | 0 | — |
case-03 | fail→fail | 36,037 | 28,874 | -20% | 1 | 1 | 0% | 6,341 | 7,135 | +13% | 0 | 0 | — |
case-04 | fail→pass | 15,529 | 24,048 | +55% | 1 | 1 | 0% | 2,657 | 4,285 | +61% | 0 | 0 | — |
case-05 | fail→pass | 21,523 | 8,950 | -58% | 1 | 1 | 0% | 4,467 | 2,354 | -47% | 0 | 0 | — |
case-06 | fail→fail | 15,700 | 19,070 | +21% | 1 | 1 | 0% | 3,498 | 4,929 | +41% | 0 | 0 | — |
case-07 | fail→fail | 14,005 | 28,880 | +106% | 1 | 1 | 0% | 2,585 | 7,005 | +171% | 0 | 0 | — |
case-08 | fail→fail | 13,022 | 29,895 | +130% | 1 | 1 | 0% | 2,777 | 6,981 | +151% | 0 | 0 | — |
case-09 | fail→fail | 14,843 | 30,623 | +106% | 1 | 1 | 0% | 2,577 | 6,986 | +171% | 0 | 0 | — |
case-10 | fail→pass | 13,173 | 28,992 | +120% | 1 | 1 | 0% | 2,517 | 6,977 | +177% | 0 | 0 | — |
case-11 | pass→pass | 9,559 | 30,232 | +216% | 1 | 1 | 0% | 1,604 | 6,988 | +336% | 0 | 0 | — |
case-12 | pass→pass | 11,870 | 32,554 | +174% | 1 | 1 | 0% | 1,755 | 6,983 | +298% | 0 | 0 | — |
case-13 | fail→pass | 19,178 | 30,628 | +60% | 1 | 1 | 0% | 2,914 | 6,986 | +140% | 0 | 0 | — |
case-14 | pass→pass | 10,975 | 29,599 | +170% | 1 | 1 | 0% | 2,006 | 6,993 | +249% | 0 | 0 | — |
case-15 | fail→pass | 9,362 | 31,622 | +238% | 1 | 1 | 0% | 1,518 | 6,982 | +360% | 0 | 0 | — |
case-16 | fail→fail | 13,763 | 33,264 | +142% | 1 | 1 | 0% | 2,289 | 6,974 | +205% | 0 | 0 | — |
case-17 | fail→fail | 11,810 | 31,736 | +169% | 1 | 1 | 0% | 2,059 | 6,977 | +239% | 0 | 0 | — |
case-18 | pass→pass | 11,851 | 29,281 | +147% | 1 | 1 | 0% | 1,996 | 6,974 | +249% | 0 | 0 | — |
case-19 | fail→fail | 14,669 | 28,151 | +92% | 1 | 1 | 0% | 2,868 | 6,973 | +143% | 0 | 0 | — |
case-20 | fail→fail | 10,213 | 29,449 | +188% | 1 | 1 | 0% | 1,834 | 6,977 | +280% | 0 | 0 | — |
case-21 | pass→fail | 12,288 | 29,636 | +141% | 1 | 1 | 0% | 2,117 | 6,977 | +230% | 0 | 0 | — |
case-22 | fail→fail | 12,577 | 30,533 | +143% | 1 | 1 | 0% | 2,355 | 6,986 | +197% | 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. 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.