Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Creates structured hiring scorecards for any role. Takes job title, requirements, and team context. Generates comprehensive scorecard with weighted scoring rubric, interview questions per competency, evaluation matrix, red/green flags, and reference check questions.
.claude/skills/onewave-ai-hiring-scorecard/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | 73% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -7% | 0% |
| case-14 | ✓→✗ | ▼ Worse | 812% | 0% |
| case-18 | ✓→✗ | ▼ Worse | 119% | 0% |
| case-20 | ✓→✗ | ▼ Worse | 104% | 0% |
Build a structured, bias-reducing hiring scorecard that lets an interview panel make consistent, evidence-based decisions for any role.
references/output-template.md -- the full 9-section scorecard.md structure with every block, table, and per-section guideline.references/competency-library.md -- which competencies to score by role type (technical IC, non-technical IC, manager, executive).references/usage-and-customization.md -- how to use the output, focus modes, biases prevented, format adaptations, and legal/compliance reminders.Job Title and Requirements are required; ask before generating if either is missing. The rest sharpen the output: Team Context, Level/Seniority, Role Type, Industry, Interview Panel, Compensation Band, Urgency/Timeline.
references/output-template.md Section 2.references/competency-library.md.references/output-template.md Section 3.references/output-template.md Section 4.scorecard.md in the working directory (or a user-specified path), assembled from all nine sections and ready to hand to a panel without further editing.For focus modes (technical, leadership, sales/GTM, creative, operations, culture-heavy), format adaptations, and legal/compliance reminders, see references/usage-and-customization.md.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 29,800 | 44,502 | +49% | 1 | 1 | 0% | 4,736 | 6,829 | +44% | 0 | 0 | — |
case-02 | pass→pass | 39,581 | 39,475 | -0% | 1 | 1 | 0% | 6,241 | 6,825 | +9% | 0 | 0 | — |
case-03 | fail→pass | 24,103 | 33,561 | +39% | 1 | 1 | 0% | 3,648 | 6,316 | +73% | 0 | 0 | — |
case-04 | pass→pass | 14,760 | 17,553 | +19% | 1 | 1 | 0% | 2,348 | 3,228 | +37% | 0 | 0 | — |
case-05 | pass→pass | 11,779 | 10,975 | -7% | 1 | 1 | 0% | 2,033 | 2,414 | +19% | 0 | 0 | — |
case-06 | pass→pass | 7,916 | 8,249 | +4% | 1 | 1 | 0% | 1,250 | 1,735 | +39% | 0 | 0 | — |
case-07 | fail→pass | 15,480 | 10,983 | -29% | 1 | 1 | 0% | 2,410 | 2,238 | -7% | 0 | 0 | — |
case-08 | fail→fail | 13,052 | 41,049 | +215% | 1 | 1 | 0% | 2,087 | 6,767 | +224% | 0 | 0 | — |
case-09 | fail→fail | 12,010 | 35,805 | +198% | 1 | 1 | 0% | 2,108 | 5,843 | +177% | 0 | 0 | — |
case-10 | fail→fail | 12,820 | 34,625 | +170% | 1 | 1 | 0% | 2,588 | 6,785 | +162% | 0 | 0 | — |
case-11 | fail→fail | 13,511 | 33,557 | +148% | 1 | 1 | 0% | 2,582 | 6,763 | +162% | 0 | 0 | — |
case-12 | fail→fail | 7,728 | 28,739 | +272% | 1 | 1 | 0% | 1,172 | 5,437 | +364% | 0 | 0 | — |
case-13 | fail→fail | 22,814 | 39,771 | +74% | 1 | 1 | 0% | 3,912 | 6,759 | +73% | 0 | 0 | — |
case-14 | pass→fail | 4,158 | 35,961 | +765% | 1 | 1 | 0% | 742 | 6,766 | +812% | 0 | 0 | — |
case-15 | fail→fail | 11,475 | 34,570 | +201% | 1 | 1 | 0% | 2,179 | 6,775 | +211% | 0 | 0 | — |
case-16 | pass→pass | 17,330 | 34,846 | +101% | 1 | 1 | 0% | 3,179 | 6,758 | +113% | 0 | 0 | — |
case-17 | pass→pass | 18,805 | 36,356 | +93% | 1 | 1 | 0% | 3,315 | 6,771 | +104% | 0 | 0 | — |
case-22 | pass→pass | 12,126 | 42,155 | +248% | 1 | 1 | 0% | 2,069 | 6,753 | +226% | 0 | 0 | — |
case-18 | pass→fail | 18,099 | 35,506 | +96% | 1 | 1 | 0% | 3,087 | 6,762 | +119% | 0 | 0 | — |
case-19 | pass→pass | 15,542 | 34,332 | +121% | 1 | 1 | 0% | 2,522 | 6,756 | +168% | 0 | 0 | — |
case-20 | pass→fail | 19,729 | 40,635 | +106% | 1 | 1 | 0% | 3,309 | 6,756 | +104% | 0 | 0 | — |
case-21 | pass→pass | 13,838 | 34,965 | +153% | 1 | 1 | 0% | 2,716 | 6,763 | +149% | 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 -5 percentage points is the difference between those two pass rates over the 22 comparable cases. 3 cases got worse with the skill loaded, and they are 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.