Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →/cs:cro-review <plan> — Pipeline-paranoid interrogation of revenue, win rate, NRR, and ramp time. Use when the forecast misses pipeline coverage, win rates drop, or before scaling the sales team.
.claude/skills/alirezarezvani-cro-review/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -30% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -42% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -1% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 34% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 1% | 0% |
Command: /cs:cro-review <plan>
The pipeline-paranoid operator pressure-tests revenue assumptions. Six questions that surface next-quarter pain this quarter.
What is pipeline coverage for the current quarter, by stage?
What's win rate this quarter vs the last 4 — and what's the leak point?
What's gross retention, contraction, and expansion separately?
For the last 4 hires, how many days to first deal and to quota?
What's the median discount this quarter vs last 4? Where is it creeping?
What % of pipeline is marketing-sourced, sales-sourced, partner-sourced?
bashpython ../../../c-level-advisor/skills/cro-advisor/scripts/revenue_forecast_model.py python ../../../c-level-advisor/skills/cro-advisor/scripts/churn_analyzer.py
markdown# CRO Review: <plan> **Date:** YYYY-MM-DD ## Pipeline - Coverage: X.Xx (target 3x+) - Win rate: X% (4Q trend: ↑ / → / ↓) - Top leaking stage: <name> ## Retention - Gross retention: X% - NRR: X% - Expansion: X% - Contraction: X% ## Ramp - New hires last quarter: N - Median days to first deal: X - Median days to quota: X ## Discount - Median discount this quarter: X% - Trend vs 4Q ago: <delta> ## Source Mix - Marketing: X% | Sales: X% | Partner: X% ## Verdict 🟢 ON PLAN | 🟡 GAP | 🔴 PIPELINE CRISIS ## Next Steps [3 concrete actions]
/cs:cfo-review — does this hit the cash plan?/cs:cmo-review — is pipeline source-mix healthy?/cs:execute — quarterly plan if GREEN/cs:boardroom — if REDcs-cro-advisorcro-advisor../../../business-growth/Version: 1.0.0
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 32,739 | 24,457 | -25% | 1 | 1 | 0% | 5,673 | 3,986 | -30% | 0 | 0 | — |
case-02 | fail→pass | 33,625 | 14,355 | -57% | 1 | 1 | 0% | 5,755 | 3,352 | -42% | 0 | 0 | — |
case-03 | fail→fail | 51,508 | 29,205 | -43% | 1 | 1 | 0% | 6,757 | 5,131 | -24% | 0 | 0 | — |
case-04 | pass→pass | 19,941 | 10,210 | -49% | 1 | 1 | 0% | 2,341 | 2,601 | +11% | 0 | 0 | — |
case-05 | pass→fail | 16,086 | 18,938 | +18% | 1 | 1 | 0% | 2,487 | 2,972 | +20% | 0 | 0 | — |
case-06 | pass→pass | 11,741 | 11,356 | -3% | 1 | 1 | 0% | 1,778 | 2,773 | +56% | 0 | 0 | — |
case-07 | fail→pass | 12,769 | 14,589 | +14% | 1 | 1 | 0% | 2,153 | 2,139 | -1% | 0 | 0 | — |
case-08 | pass→pass | 16,255 | 16,001 | -2% | 1 | 1 | 0% | 2,526 | 3,291 | +30% | 0 | 0 | — |
case-09 | pass→pass | 12,293 | 17,507 | +42% | 1 | 1 | 0% | 2,074 | 2,989 | +44% | 0 | 0 | — |
case-10 | pass→pass | 13,805 | 20,944 | +52% | 1 | 1 | 0% | 2,147 | 2,976 | +39% | 0 | 0 | — |
case-11 | fail→fail | 17,740 | 11,689 | -34% | 1 | 1 | 0% | 1,949 | 2,746 | +41% | 0 | 0 | — |
case-12 | fail→pass | 20,000 | 14,507 | -27% | 1 | 1 | 0% | 2,443 | 3,264 | +34% | 0 | 0 | — |
case-13 | fail→pass | 8,448 | 4,607 | -45% | 1 | 1 | 0% | 1,350 | 1,361 | +1% | 0 | 0 | — |
case-14 | pass→pass | 18,084 | 15,265 | -16% | 1 | 1 | 0% | 1,983 | 2,488 | +25% | 0 | 0 | — |
case-15 | pass→pass | 16,357 | 22,228 | +36% | 1 | 1 | 0% | 2,498 | 3,481 | +39% | 0 | 0 | — |
case-24 | pass→pass | 25,273 | 25,828 | +2% | 1 | 1 | 0% | 3,019 | 3,965 | +31% | 0 | 0 | — |
case-16 | pass→pass | 21,966 | 16,170 | -26% | 1 | 1 | 0% | 2,250 | 2,543 | +13% | 0 | 0 | — |
case-17 | pass→pass | 19,749 | 9,856 | -50% | 1 | 1 | 0% | 1,932 | 1,523 | -21% | 0 | 0 | — |
case-18 | fail→pass | 11,698 | 6,411 | -45% | 1 | 1 | 0% | 1,599 | 1,429 | -11% | 0 | 0 | — |
case-19 | fail→pass | 22,023 | 4,074 | -82% | 1 | 1 | 0% | 2,085 | 1,556 | -25% | 0 | 0 | — |
case-20 | fail→pass | 20,055 | 10,050 | -50% | 1 | 1 | 0% | 1,557 | 1,690 | +9% | 0 | 0 | — |
case-21 | fail→fail | 25,414 | 26,026 | +2% | 1 | 1 | 0% | 3,152 | 5,050 | +60% | 0 | 0 | — |
case-22 | pass→pass | 18,091 | 24,812 | +37% | 1 | 1 | 0% | 3,290 | 4,618 | +40% | 0 | 0 | — |
case-23 | pass→pass | 16,823 | 27,030 | +61% | 1 | 1 | 0% | 2,643 | 3,971 | +50% | 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. 24 cases were attempted. The headline lift of +29 percentage points is the difference between those two pass rates over the 24 comparable cases. 1 case got worse with the skill loaded, and it is 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.
| Model | Method | Date | Lift |
|---|---|---|---|
| gemini-3.6-flash | verified | 8/4/2026 | +36% |
Other measured skills in the registry, with their headline benchmark lift.