Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Expert product manager specializing in agile sprint planning, feature prioritization, and resource allocation. Focused on maximizing team velocity and business value delivery through data-driven pr...
.claude/skills/dev-dennis-040-product-sprint-prioritizer/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-08 | ✗→✓ | ▲ Improved | 86% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 41% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 75% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 25% | 0% |
| case-17 | ✗→✓ | ▲ Improved | 27% | 0% |
name: Sprint Prioritizer description: Expert product manager specializing in agile sprint planning, feature prioritization, and resource allocation. Focused on maximizing team velocity and business value delivery through data-driven prioritization frameworks. color: green tools: WebFetch, WebSearch, Read, Write, Edit
Expert product manager specializing in agile sprint planning, feature prioritization, and resource allocation. Focused on maximizing team velocity and business value delivery through data-driven prioritization frameworks and stakeholder alignment.
Use this agent when you need:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 2,786 | 4,211 | +51% | 1 | 1 | 0% | 605 | 2,594 | +329% | 0 | 0 | — |
case-02 | pass→pass | 2,929 | 3,704 | +26% | 1 | 1 | 0% | 642 | 2,491 | +288% | 0 | 0 | — |
case-03 | pass→pass | 6,788 | 7,032 | +4% | 1 | 1 | 0% | 1,383 | 3,019 | +118% | 0 | 0 | — |
case-04 | pass→pass | 2,899 | 3,924 | +35% | 1 | 1 | 0% | 596 | 2,415 | +305% | 0 | 0 | — |
case-05 | pass→pass | 4,597 | 4,796 | +4% | 1 | 1 | 0% | 900 | 2,587 | +187% | 0 | 0 | — |
case-06 | pass→pass | 4,473 | 4,207 | -6% | 1 | 1 | 0% | 881 | 2,463 | +180% | 0 | 0 | — |
case-07 | pass→pass | 7,479 | 5,637 | -25% | 1 | 1 | 0% | 1,530 | 2,824 | +85% | 0 | 0 | — |
case-08 | fail→pass | 6,853 | 4,144 | -40% | 1 | 1 | 0% | 1,312 | 2,438 | +86% | 0 | 0 | — |
case-09 | pass→pass | 8,351 | 4,311 | -48% | 1 | 1 | 0% | 1,672 | 2,593 | +55% | 0 | 0 | — |
case-10 | pass→pass | 7,677 | 7,496 | -2% | 1 | 1 | 0% | 1,413 | 3,077 | +118% | 0 | 0 | — |
case-11 | fail→pass | 7,739 | 2,569 | -67% | 1 | 1 | 0% | 1,491 | 2,104 | +41% | 0 | 0 | — |
case-12 | fail→pass | 7,922 | 8,131 | +3% | 1 | 1 | 0% | 1,594 | 2,796 | +75% | 0 | 0 | — |
case-13 | fail→fail | 7,050 | 7,104 | +1% | 1 | 1 | 0% | 1,524 | 3,166 | +108% | 0 | 0 | — |
case-14 | pass→pass | 9,396 | 5,957 | -37% | 1 | 1 | 0% | 1,872 | 2,838 | +52% | 0 | 0 | — |
case-15 | fail→pass | 8,180 | 1,770 | -78% | 1 | 1 | 0% | 1,595 | 2,000 | +25% | 0 | 0 | — |
case-16 | pass→pass | 10,791 | 6,195 | -43% | 1 | 1 | 0% | 2,053 | 2,814 | +37% | 0 | 0 | — |
case-17 | fail→pass | 10,581 | 5,366 | -49% | 1 | 1 | 0% | 2,064 | 2,620 | +27% | 0 | 0 | — |
case-18 | pass→pass | 10,684 | 7,291 | -32% | 1 | 1 | 0% | 1,989 | 3,033 | +52% | 0 | 0 | — |
case-19 | pass→pass | 10,544 | 10,376 | -2% | 1 | 1 | 0% | 2,235 | 3,773 | +69% | 0 | 0 | — |
case-20 | pass→pass | 15,144 | 12,347 | -18% | 1 | 1 | 0% | 3,274 | 4,576 | +40% | 0 | 0 | — |
case-21 | pass→pass | 9,265 | 12,145 | +31% | 1 | 1 | 0% | 1,840 | 3,923 | +113% | 0 | 0 | — |
case-22 | pass→pass | 10,237 | 12,748 | +25% | 1 | 1 | 0% | 2,599 | 4,854 | +87% | 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.
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.