Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Analyzes a deal in progress and generates a comprehensive closing strategy. Researches the target company, maps the buying committee, builds objection responses, creates competitive positioning, and outputs a tactical deal-playbook.md with next-best-actions and a mutual close plan.
.claude/skills/onewave-ai-deal-closer-playbook/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-12 | ✗→✓ | ▲ Improved | 92% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 37% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 73% | 0% |
| case-17 | ✗→✓ | ▲ Improved | -43% | 0% |
| case-19 | ✗→✓ | ▲ Improved | 37% | 0% |
Take a deal in progress -- at any stage from discovery to negotiation -- and produce a tactical closing playbook combining company research, stakeholder mapping, competitive intelligence, and deal mechanics into a single actionable document.
references/intelligence-gathering.md -- context intake, company research, buying-committee map, MEDDIC and velocity risk scoringreferences/playbook-strategy.md -- objection matrix, competitive positioning, stage-specific closing strategy, mutual close plan, proposal talking pointsreferences/output-template.md -- full deal-playbook.md structure to writeOperate in two phases: gather intelligence, then generate the playbook. Be thorough but fast. Tie every section to a specific action.
[UNKNOWN] and work around them. See references/intelligence-gathering.md.references/intelligence-gathering.md.references/intelligence-gathering.md.references/intelligence-gathering.md.references/playbook-strategy.md.references/playbook-strategy.md.references/playbook-strategy.md.references/playbook-strategy.md.references/playbook-strategy.md.deal-playbook.md using references/output-template.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 | 24,958 | 38,514 | +54% | 1 | 1 | 0% | 3,822 | 1,576 | -59% | 0 | 0 | — |
case-02 | fail→fail | 31,190 | 6,758 | -78% | 1 | 1 | 0% | 4,514 | 1,420 | -69% | 0 | 0 | — |
case-03 | fail→fail | 41,707 | 34,216 | -18% | 1 | 1 | 0% | 5,910 | 1,447 | -76% | 0 | 0 | — |
case-04 | pass→pass | 21,890 | 19,776 | -10% | 1 | 1 | 0% | 2,885 | 3,903 | +35% | 0 | 0 | — |
case-05 | pass→pass | 17,111 | 20,042 | +17% | 1 | 1 | 0% | 2,852 | 3,953 | +39% | 0 | 0 | — |
case-06 | pass→fail | 16,104 | 21,189 | +32% | 1 | 1 | 0% | 2,381 | 4,215 | +77% | 0 | 0 | — |
case-07 | fail→fail | 19,942 | 9,533 | -52% | 1 | 1 | 0% | 2,868 | 1,544 | -46% | 0 | 0 | — |
case-08 | pass→fail | 16,958 | 10,122 | -40% | 1 | 1 | 0% | 2,587 | 2,516 | -3% | 0 | 0 | — |
case-09 | pass→pass | 21,292 | 37,961 | +78% | 1 | 1 | 0% | 2,915 | 6,404 | +120% | 0 | 0 | — |
case-10 | fail→fail | 20,917 | 39,661 | +90% | 1 | 1 | 0% | 3,304 | 5,526 | +67% | 0 | 0 | — |
case-11 | fail→fail | 9,522 | 13,206 | +39% | 1 | 1 | 0% | 1,535 | 1,669 | +9% | 0 | 0 | — |
case-12 | fail→pass | 11,734 | 19,041 | +62% | 1 | 1 | 0% | 1,610 | 3,093 | +92% | 0 | 0 | — |
case-13 | fail→pass | 14,213 | 14,566 | +2% | 1 | 1 | 0% | 2,254 | 3,089 | +37% | 0 | 0 | — |
case-14 | fail→pass | 15,258 | 19,225 | +26% | 1 | 1 | 0% | 2,167 | 3,748 | +73% | 0 | 0 | — |
case-15 | fail→fail | 23,264 | 24,192 | +4% | 1 | 1 | 0% | 3,142 | 4,158 | +32% | 0 | 0 | — |
case-16 | pass→pass | 17,678 | 28,706 | +62% | 1 | 1 | 0% | 2,247 | 5,115 | +128% | 0 | 0 | — |
case-17 | fail→pass | 22,290 | 6,216 | -72% | 1 | 1 | 0% | 3,183 | 1,799 | -43% | 0 | 0 | — |
case-18 | pass→pass | 12,922 | 17,162 | +33% | 1 | 1 | 0% | 2,016 | 3,491 | +73% | 0 | 0 | — |
case-19 | fail→pass | 18,461 | 18,103 | -2% | 1 | 1 | 0% | 2,496 | 3,427 | +37% | 0 | 0 | — |
case-20 | pass→pass | 13,203 | 29,934 | +127% | 1 | 1 | 0% | 1,982 | 4,930 | +149% | 0 | 0 | — |
case-21 | fail→pass | 12,694 | 7,005 | -45% | 1 | 1 | 0% | 1,958 | 2,133 | +9% | 0 | 0 | — |
case-22 | fail→fail | 15,140 | 8,548 | -44% | 1 | 1 | 0% | 2,341 | 1,595 | -32% | 0 | 0 | — |
case-23 | fail→pass | 15,193 | 20,968 | +38% | 1 | 1 | 0% | 2,514 | 4,409 | +75% | 0 | 0 | — |
case-24 | fail→fail | 14,432 | 11,128 | -23% | 1 | 1 | 0% | 2,245 | 2,733 | +22% | 0 | 0 | — |
case-25 | fail→fail | 13,357 | 12,368 | -7% | 1 | 1 | 0% | 2,402 | 2,827 | +18% | 0 | 0 | — |
case-26 | fail→pass | 10,610 | 12,174 | +15% | 1 | 1 | 0% | 1,295 | 2,618 | +102% | 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. 26 cases were attempted, and 20 counted toward the lift figure. The other 6 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +23 percentage points is the difference between those two pass rates over the 20 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.