Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Score deal velocity based on email response times, meeting frequency, and stakeholder engagement. Predict which deals will close vs stall.
.claude/skills/onewave-ai-deal-momentum-analyzer/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 5% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 27% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -2% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 22% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 16% | 0% |
Score deal velocity based on email response times, meeting frequency, and stakeholder engagement. Predict which deals will close vs stall.
You are an expert at sales analytics and deal forecasting. Analyze deal engagement patterns, calculate momentum scores, and predict close probability with action recommendations.
markdown# Deal Momentum Analyzer Output **Generated**: {timestamp} --- ## Results [Your formatted output here] --- ## Recommendations [Actionable next steps]
Trigger Phrases:
Example Request: > "Sample user request here]"
Response Approach:
Remember: Focus on delivering value quickly and clearly!
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 19,241 | 26,171 | +36% | 1 | 1 | 0% | 2,936 | 3,070 | +5% | 0 | 0 | — |
case-02 | fail→pass | 12,963 | 15,502 | +20% | 1 | 1 | 0% | 2,172 | 2,763 | +27% | 0 | 0 | — |
case-03 | fail→fail | 10,597 | 16,924 | +60% | 1 | 1 | 0% | 1,526 | 2,949 | +93% | 0 | 0 | — |
case-04 | fail→pass | 14,470 | 12,454 | -14% | 1 | 1 | 0% | 2,278 | 2,231 | -2% | 0 | 0 | — |
case-05 | fail→pass | 12,325 | 13,499 | +10% | 1 | 1 | 0% | 1,904 | 2,325 | +22% | 0 | 0 | — |
case-06 | pass→pass | 21,555 | 15,537 | -28% | 1 | 1 | 0% | 2,926 | 2,583 | -12% | 0 | 0 | — |
case-07 | fail→pass | 16,570 | 14,541 | -12% | 1 | 1 | 0% | 2,223 | 2,577 | +16% | 0 | 0 | — |
case-08 | fail→pass | 15,646 | 14,402 | -8% | 1 | 1 | 0% | 2,282 | 2,289 | +0% | 0 | 0 | — |
case-09 | pass→pass | 15,192 | 12,794 | -16% | 1 | 1 | 0% | 2,325 | 2,246 | -3% | 0 | 0 | — |
case-10 | fail→pass | 16,667 | 17,520 | +5% | 1 | 1 | 0% | 2,227 | 2,712 | +22% | 0 | 0 | — |
case-11 | pass→pass | 18,145 | 15,941 | -12% | 1 | 1 | 0% | 2,612 | 2,497 | -4% | 0 | 0 | — |
case-12 | fail→pass | 16,076 | 13,058 | -19% | 1 | 1 | 0% | 2,554 | 2,221 | -13% | 0 | 0 | — |
case-13 | fail→pass | 20,525 | 17,258 | -16% | 1 | 1 | 0% | 3,248 | 2,749 | -15% | 0 | 0 | — |
case-14 | pass→pass | 17,116 | 15,983 | -7% | 1 | 1 | 0% | 2,665 | 2,760 | +4% | 0 | 0 | — |
case-15 | fail→pass | 11,001 | 11,970 | +9% | 1 | 1 | 0% | 1,646 | 2,113 | +28% | 0 | 0 | — |
case-16 | pass→pass | 13,391 | 15,775 | +18% | 1 | 1 | 0% | 1,947 | 2,541 | +31% | 0 | 0 | — |
case-17 | pass→pass | 14,156 | 15,474 | +9% | 1 | 1 | 0% | 1,899 | 2,453 | +29% | 0 | 0 | — |
case-18 | fail→pass | 16,699 | 14,894 | -11% | 1 | 1 | 0% | 2,634 | 2,398 | -9% | 0 | 0 | — |
case-19 | fail→pass | 14,779 | 13,747 | -7% | 1 | 1 | 0% | 1,948 | 2,174 | +12% | 0 | 0 | — |
case-20 | pass→fail | 5,608 | 10,591 | +89% | 1 | 1 | 0% | 977 | 1,840 | +88% | 0 | 0 | — |
case-21 | pass→pass | 11,991 | 11,546 | -4% | 1 | 1 | 0% | 1,743 | 1,911 | +10% | 0 | 0 | — |
case-22 | pass→fail | 17,818 | 16,339 | -8% | 1 | 1 | 0% | 3,163 | 3,152 | -0% | 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 +45 percentage points is the difference between those two pass rates over the 22 comparable cases. 2 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.