Install any skill in seconds. Free to start, no credit card required.
Get Started Free →OKR brainstorming and validation using the Radical Focus framework — outcome objectives, measurable key results, counter-metrics. Use for setting or validating quarterly OKRs, aligning team goals, or teaching outcomes vs outputs.
.claude/skills/borghei-brainstorm-okrs/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 35% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 35% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 71% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 35% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -12% | 0% |
The agent generates and validates outcome-focused OKR sets using Christina Wodtke's Radical Focus methodology. It produces inspirational objectives with measurable key results, applies counter-metric tests, and scores quality against proven criteria.
okr_validator.py scores sets and flags disguised tasks, missing metrics, output-framed KRs, and missing counter-metricsBefore generating the OKR sets, confirm these inputs. If any is unknown or vague, ASK — do not assume:
Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the artifact.
bashpython scripts/okr_validator.py --input okrs.json # validate & score python scripts/okr_validator.py --demo # built-in good/bad demo
Any OKR set scoring below 70% must be revised before committing. See the references for the full workflow and input schema.
Load the reference that matches the task — keep this file lean and pull detail on demand:
okr_validator.py flag + JSON-schema reference. Read when generating OKRs or wiring up the validator.In Scope:
Out of Scope:
senior-pm/ for portfolio alignment)Important Caveats:
| Integration | Direction | Description | |------------|-----------|-------------| | scrum-master/ | Receives from | Sprint velocity and capacity data inform realistic KR target-setting | | senior-pm/ | Receives from | Portfolio strategic priorities shape quarterly OKR themes | | execution/outcome-roadmap/ | Feeds into | OKR key results become success metrics for roadmap Now/Next items | | execution/prioritization-frameworks/ | Complements | Prioritized initiatives inform which OKR theme to focus on | | discovery/identify-assumptions/ | Receives from | Validated assumptions increase confidence in OKR target feasibility | | discovery/brainstorm-experiments/ | Feeds into | Experiment metrics may become OKR key results when validated |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 16,387 | 14,715 | -10% | 1 | 1 | 0% | 2,497 | 3,532 | +41% | 0 | 0 | — |
case-02 | fail→pass | 16,453 | 15,338 | -7% | 1 | 1 | 0% | 2,659 | 3,602 | +35% | 0 | 0 | — |
case-03 | fail→fail | 15,695 | 13,955 | -11% | 1 | 1 | 0% | 2,362 | 3,429 | +45% | 0 | 0 | — |
case-04 | fail→pass | 15,349 | 13,170 | -14% | 1 | 1 | 0% | 2,402 | 3,241 | +35% | 0 | 0 | — |
case-05 | pass→pass | 15,814 | 12,867 | -19% | 1 | 1 | 0% | 2,487 | 3,349 | +35% | 0 | 0 | — |
case-06 | fail→pass | 9,167 | 10,130 | +11% | 1 | 1 | 0% | 1,633 | 2,792 | +71% | 0 | 0 | — |
case-07 | pass→pass | 9,823 | 5,892 | -40% | 1 | 1 | 0% | 1,607 | 2,029 | +26% | 0 | 0 | — |
case-08 | fail→pass | 7,122 | 1,943 | -73% | 1 | 1 | 0% | 1,031 | 1,393 | +35% | 0 | 0 | — |
case-09 | pass→pass | 5,740 | 2,754 | -52% | 1 | 1 | 0% | 879 | 1,511 | +72% | 0 | 0 | — |
case-10 | fail→pass | 12,518 | 5,842 | -53% | 1 | 1 | 0% | 2,362 | 2,067 | -12% | 0 | 0 | — |
case-11 | fail→pass | 17,217 | 14,943 | -13% | 1 | 1 | 0% | 2,562 | 3,417 | +33% | 0 | 0 | — |
case-12 | pass→pass | 13,164 | 11,232 | -15% | 1 | 1 | 0% | 2,169 | 2,778 | +28% | 0 | 0 | — |
case-13 | pass→pass | 11,596 | 10,004 | -14% | 1 | 1 | 0% | 1,797 | 2,661 | +48% | 0 | 0 | — |
case-14 | fail→pass | 7,087 | 1,535 | -78% | 1 | 1 | 0% | 978 | 1,355 | +39% | 0 | 0 | — |
case-15 | fail→pass | 15,458 | 9,392 | -39% | 1 | 1 | 0% | 2,150 | 2,332 | +8% | 0 | 0 | — |
case-16 | pass→pass | 13,250 | 6,807 | -49% | 1 | 1 | 0% | 1,883 | 2,115 | +12% | 0 | 0 | — |
case-17 | pass→pass | 13,369 | 11,251 | -16% | 1 | 1 | 0% | 1,976 | 2,784 | +41% | 0 | 0 | — |
case-18 | pass→pass | 16,453 | 13,228 | -20% | 1 | 1 | 0% | 2,434 | 2,902 | +19% | 0 | 0 | — |
case-19 | pass→pass | 16,865 | 14,630 | -13% | 1 | 1 | 0% | 2,287 | 3,205 | +40% | 0 | 0 | — |
case-20 | fail→fail | 16,279 | 18,309 | +12% | 1 | 1 | 0% | 2,591 | 4,038 | +56% | 0 | 0 | — |
case-21 | fail→pass | 15,184 | 10,915 | -28% | 1 | 1 | 0% | 2,388 | 2,718 | +14% | 0 | 0 | — |
case-22 | fail→pass | 17,999 | 10,404 | -42% | 1 | 1 | 0% | 3,247 | 2,684 | -17% | 0 | 0 | — |
case-23 | fail→fail | 25,455 | 18,451 | -28% | 1 | 1 | 0% | 4,184 | 3,831 | -8% | 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 +43 percentage points is the difference between those two pass rates over the 23 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.