Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →/cs:cpo-review <plan> — JTBD-driven interrogation of product roadmap, PMF signal, and portfolio focus. Use when committing a quarter's roadmap, deciding whether to kill a feature, or claiming PMF without a retention curve.
.claude/skills/alirezarezvani-cpo-review/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -40% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 25% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -3% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 19% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -5% | 0% |
Command: /cs:cpo-review <plan>
The JTBD-driven builder cuts the roadmap in half. Six questions to surface what to ship and what to kill.
What job is this feature hired to do, in the user's words?
What user behavior does this move, and how does that ladder to the North Star?
What's the retention curve for users who hire this job — is it flat, decaying, or smiling?
Reach, Impact, Confidence, Effort — what's the score and where does this rank in the queue?
bashpython product-team/skills/product-manager-toolkit/scripts/rice_prioritizer.py
What gets cut if this ships? Name the specific initiative or feature.
What signal would tell you in 90 days that this was the wrong bet?
bash python ../../../c-level-advisor/skills/cpo-advisor/scripts/pmf_scorer.py python ../../../c-level-advisor/skills/cpo-advisor/scripts/portfolio_analyzer.py
markdown# CPO Review: <feature/plan> **Date:** YYYY-MM-DD ## JTBD > <one sentence in user voice> ## North Star Link - Metric moved: <name> - Expected delta: <%> ## PMF Signal - Retention curve shape: flat / smiling / decaying - Cohort sample size: N ## Score - RICE: <number> - Rank in queue: #N of M ## Cut List - Cut: <initiative> - Reason: <why this matters more> ## Kill Criteria (90 days) - Metric: <name> - Threshold: <value> - Action if missed: <kill | iterate> ## Verdict 🟢 SHIP | 🟡 SHARPEN | 🔴 KILL
/cs:cmo-review — does the positioning support this feature?/cs:execute — build the 90-day plan/cs:post-mortem — if kill criteria triggeredcs-cpo-advisorcpo-advisorproduct-team/skills/product-manager-toolkit/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-09 | pass→pass | 15,882 | 20,697 | +30% | 1 | 1 | 0% | 1,894 | 2,902 | +53% | 0 | 0 | — |
case-01 | fail→pass | 39,885 | 26,299 | -34% | 1 | 1 | 0% | 6,420 | 3,881 | -40% | 0 | 0 | — |
case-08 | fail→pass | 20,566 | 18,716 | -9% | 1 | 1 | 0% | 2,466 | 3,079 | +25% | 0 | 0 | — |
case-02 | fail→fail | 19,592 | 20,625 | +5% | 1 | 1 | 0% | 3,107 | 4,268 | +37% | 0 | 0 | — |
case-03 | fail→pass | 31,605 | 21,077 | -33% | 1 | 1 | 0% | 4,474 | 4,319 | -3% | 0 | 0 | — |
case-04 | fail→pass | 24,267 | 21,005 | -13% | 1 | 1 | 0% | 2,879 | 3,412 | +19% | 0 | 0 | — |
case-05 | fail→pass | 31,486 | 24,736 | -21% | 1 | 1 | 0% | 4,743 | 4,494 | -5% | 0 | 0 | — |
case-06 | fail→fail | 24,385 | 20,731 | -15% | 1 | 1 | 0% | 2,992 | 3,209 | +7% | 0 | 0 | — |
case-07 | fail→pass | 19,862 | 10,259 | -48% | 1 | 1 | 0% | 2,154 | 2,505 | +16% | 0 | 0 | — |
case-10 | fail→fail | 11,038 | 7,597 | -31% | 1 | 1 | 0% | 2,036 | 1,253 | -38% | 0 | 0 | — |
case-11 | fail→pass | 9,440 | 3,147 | -67% | 1 | 1 | 0% | 1,443 | 1,417 | -2% | 0 | 0 | — |
case-12 | fail→pass | 13,770 | 2,559 | -81% | 1 | 1 | 0% | 1,342 | 1,289 | -4% | 0 | 0 | — |
case-13 | fail→pass | 18,526 | 23,416 | +26% | 1 | 1 | 0% | 2,533 | 3,284 | +30% | 0 | 0 | — |
case-14 | pass→pass | 17,915 | 18,636 | +4% | 1 | 1 | 0% | 2,844 | 3,120 | +10% | 0 | 0 | — |
case-15 | fail→pass | 8,519 | 7,666 | -10% | 1 | 1 | 0% | 1,345 | 2,232 | +66% | 0 | 0 | — |
case-16 | fail→pass | 13,117 | 9,808 | -25% | 1 | 1 | 0% | 1,295 | 1,699 | +31% | 0 | 0 | — |
case-17 | fail→pass | 9,150 | 9,985 | +9% | 1 | 1 | 0% | 1,057 | 1,685 | +59% | 0 | 0 | — |
case-18 | fail→pass | 17,393 | 14,110 | -19% | 1 | 1 | 0% | 1,940 | 3,167 | +63% | 0 | 0 | — |
case-19 | fail→pass | 20,562 | 11,354 | -45% | 1 | 1 | 0% | 2,365 | 2,729 | +15% | 0 | 0 | — |
case-20 | pass→pass | 11,292 | 7,124 | -37% | 1 | 1 | 0% | 1,742 | 1,982 | +14% | 0 | 0 | — |
case-21 | fail→pass | 30,889 | 7,839 | -75% | 1 | 1 | 0% | 1,067 | 1,382 | +30% | 0 | 0 | — |
case-22 | fail→pass | 12,484 | 3,187 | -74% | 1 | 1 | 0% | 2,115 | 1,341 | -37% | 0 | 0 | — |
case-23 | fail→pass | 8,929 | 7,825 | -12% | 1 | 1 | 0% | 1,394 | 1,171 | -16% | 0 | 0 | — |
case-24 | fail→pass | 19,336 | 7,427 | -62% | 1 | 1 | 0% | 1,568 | 1,118 | -29% | 0 | 0 | — |
case-25 | fail→pass | 14,510 | 3,877 | -73% | 1 | 1 | 0% | 1,589 | 1,182 | -26% | 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. 25 cases were attempted, and 24 counted toward the lift figure. The other 1 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 +76 percentage points is the difference between those two pass rates over the 24 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.
| Model | Method | Date | Lift |
|---|---|---|---|
| gemini-3.6-flash | verified | 8/4/2026 | +56% |
Other measured skills in the registry, with their headline benchmark lift.