Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Growth Strategist agent for revenue operations, sales engineering, customer success, and business development. Orchestrates business-growth skills. Spawn when users need pipeline analysis, churn prevention, expansion scoring, sales demos, or proposal writing.
.claude/skills/alirezarezvani-cs-growth-strategist/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-08 | ✗→✓ | ▲ Improved | 22% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 8% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 51% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 19% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 11% | 0% |
Growth-focused operator covering the full revenue lifecycle: pipeline management, sales engineering, customer success, and commercial proposals.
business-growth/revenue-operations — Pipeline analysis, forecast accuracy, GTM efficiencybusiness-growth/sales-engineer — POC planning, competitive positioning, technical demosbusiness-growth/customer-success-manager — Health scoring, churn risk, expansion opportunitiesbusiness-growth/contract-and-proposal-writer — Commercial proposals, SOWs, pricing structurespipeline_analyzer.py on deal dataforecast_accuracy_tracker.pyhealth_score_calculator.pychurn_risk_analyzer.pyexpansion_opportunity_scorer.pycontract-and-proposal-writercompetitive_matrix_builder.pypoc_planner.py| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 35,073 | 21,458 | -39% | 1 | 1 | 0% | 5,412 | 4,610 | -15% | 0 | 0 | — |
case-02 | fail→fail | 16,391 | 15,248 | -7% | 1 | 1 | 0% | 2,745 | 3,689 | +34% | 0 | 0 | — |
case-03 | fail→fail | 12,597 | 15,340 | +22% | 1 | 1 | 0% | 2,210 | 2,892 | +31% | 0 | 0 | — |
case-04 | pass→fail | 11,748 | 13,700 | +17% | 1 | 1 | 0% | 2,525 | 2,930 | +16% | 0 | 0 | — |
case-05 | pass→pass | 11,814 | 11,199 | -5% | 1 | 1 | 0% | 2,222 | 2,667 | +20% | 0 | 0 | — |
case-06 | pass→pass | 20,169 | 4,876 | -76% | 1 | 1 | 0% | 1,823 | 1,414 | -22% | 0 | 0 | — |
case-07 | fail→fail | 15,388 | 20,554 | +34% | 1 | 1 | 0% | 2,395 | 3,660 | +53% | 0 | 0 | — |
case-08 | fail→pass | 13,446 | 12,219 | -9% | 1 | 1 | 0% | 2,194 | 2,679 | +22% | 0 | 0 | — |
case-09 | fail→pass | 8,356 | 5,623 | -33% | 1 | 1 | 0% | 1,483 | 1,603 | +8% | 0 | 0 | — |
case-10 | fail→pass | 18,144 | 17,259 | -5% | 1 | 1 | 0% | 2,379 | 3,584 | +51% | 0 | 0 | — |
case-11 | pass→fail | 16,654 | 14,146 | -15% | 1 | 1 | 0% | 2,520 | 2,896 | +15% | 0 | 0 | — |
case-12 | fail→fail | 13,881 | 11,268 | -19% | 1 | 1 | 0% | 2,191 | 2,532 | +16% | 0 | 0 | — |
case-13 | fail→pass | 9,418 | 12,436 | +32% | 1 | 1 | 0% | 1,403 | 1,663 | +19% | 0 | 0 | — |
case-14 | fail→pass | 10,072 | 8,176 | -19% | 1 | 1 | 0% | 1,803 | 1,997 | +11% | 0 | 0 | — |
case-15 | pass→pass | 12,279 | 12,653 | +3% | 1 | 1 | 0% | 2,109 | 2,768 | +31% | 0 | 0 | — |
case-16 | fail→pass | 12,148 | 14,328 | +18% | 1 | 1 | 0% | 2,132 | 2,992 | +40% | 0 | 0 | — |
case-17 | fail→fail | 24,440 | 8,786 | -64% | 1 | 1 | 0% | 2,338 | 1,775 | -24% | 0 | 0 | — |
case-18 | pass→pass | 10,703 | 8,530 | -20% | 1 | 1 | 0% | 1,899 | 2,099 | +11% | 0 | 0 | — |
case-19 | pass→pass | 15,511 | 11,650 | -25% | 1 | 1 | 0% | 2,238 | 2,458 | +10% | 0 | 0 | — |
case-20 | pass→pass | 16,007 | 15,736 | -2% | 1 | 1 | 0% | 2,925 | 3,387 | +16% | 0 | 0 | — |
case-21 | pass→fail | 11,128 | 4,377 | -61% | 1 | 1 | 0% | 2,032 | 1,221 | -40% | 0 | 0 | — |
case-22 | pass→pass | 17,999 | 15,937 | -11% | 1 | 1 | 0% | 3,561 | 3,423 | -4% | 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 +14 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.