Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Plan and run a customer advisory board (CAB). Use when asked to design a customer advisory board, plan a CAB meeting agenda, choose CAB members, or write CAB invitations and follow-ups. Produces a CAB program plan — objectives, member selection criteria, a meeting agenda, discussion guides, roles, logistics, and a follow-up and value-capture plan.
.claude/skills/mohitagw15856-customer-advisory-board/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-18 | ✗→✓ | ▲ Improved | 97% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 72% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 22% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 11% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 56% | 0% |
Design a customer advisory board that gives you honest strategic input and deepens relationships with your most important customers — not a thinly disguised sales pitch. A good CAB is member-first: they come for peer exchange and influence, not a roadmap presentation.
Ask for these if not provided:
Keep it member-value-led; flag anything that risks feeling like a sales meeting.
Objective: strategic input / validation / advocacy] · Cadence: frequency · format] · Sponsor: exec]
| Criterion | Target | |---|---| | Size | 8–15] | | Segment mix | enterprise / mid-market / …] | | Persona mix | economic buyer / practitioner / …] | | Guardrails | no direct competitors together · NDA] |
Candidate roster: names/segments or [to confirm]]
| Time | Segment | Format | Owner | |---|---|---|---| | 00:00] | Welcome & member intros / context | Round-robin | Facilitator | | 00:xx] | Topic 1] | Facilitated discussion | Facilitator | | 00:xx] | Topic 2 / roadmap input] | Discussion (listen mode) | Product | | 00:xx] | Synthesis & next steps | Group | Facilitator |
Topic]:
Location/platform · date · pre-reads · confidentiality · travel/hospitality — or [to confirm]]
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 37,362 | 28,746 | -23% | 1 | 1 | 0% | 6,258 | 5,857 | -6% | 0 | 0 | — |
case-02 | fail→fail | 34,940 | 26,280 | -25% | 1 | 1 | 0% | 5,394 | 5,187 | -4% | 0 | 0 | — |
case-03 | fail→fail | 39,130 | 23,889 | -39% | 1 | 1 | 0% | 6,247 | 4,765 | -24% | 0 | 0 | — |
case-04 | pass→pass | 18,567 | 33,878 | +82% | 1 | 1 | 0% | 2,990 | 3,486 | +17% | 0 | 0 | — |
case-18 | fail→pass | 20,408 | 28,023 | +37% | 1 | 1 | 0% | 3,057 | 6,016 | +97% | 0 | 0 | — |
case-05 | pass→pass | 16,445 | 18,304 | +11% | 1 | 1 | 0% | 2,997 | 3,756 | +25% | 0 | 0 | — |
case-06 | pass→pass | 15,731 | 21,607 | +37% | 1 | 1 | 0% | 2,546 | 4,108 | +61% | 0 | 0 | — |
case-07 | fail→pass | 18,235 | 13,373 | -27% | 1 | 1 | 0% | 2,089 | 3,583 | +72% | 0 | 0 | — |
case-08 | pass→pass | 19,307 | 20,550 | +6% | 1 | 1 | 0% | 3,328 | 4,531 | +36% | 0 | 0 | — |
case-09 | fail→pass | 18,018 | 14,983 | -17% | 1 | 1 | 0% | 3,027 | 3,701 | +22% | 0 | 0 | — |
case-10 | pass→pass | 19,763 | 15,738 | -20% | 1 | 1 | 0% | 3,334 | 3,795 | +14% | 0 | 0 | — |
case-11 | pass→pass | 17,801 | 14,180 | -20% | 1 | 1 | 0% | 3,069 | 3,496 | +14% | 0 | 0 | — |
case-12 | pass→pass | 20,113 | 19,252 | -4% | 1 | 1 | 0% | 3,286 | 4,221 | +28% | 0 | 0 | — |
case-13 | fail→pass | 22,065 | 15,663 | -29% | 1 | 1 | 0% | 3,464 | 3,849 | +11% | 0 | 0 | — |
case-14 | fail→pass | 16,220 | 16,893 | +4% | 1 | 1 | 0% | 2,451 | 3,820 | +56% | 0 | 0 | — |
case-15 | pass→fail | 15,839 | 17,349 | +10% | 1 | 1 | 0% | 2,706 | 3,935 | +45% | 0 | 0 | — |
case-16 | pass→pass | 18,993 | 14,506 | -24% | 1 | 1 | 0% | 3,272 | 3,413 | +4% | 0 | 0 | — |
case-17 | fail→pass | 38,941 | 19,856 | -49% | 1 | 1 | 0% | 3,403 | 4,052 | +19% | 0 | 0 | — |
case-19 | pass→pass | 21,480 | 18,353 | -15% | 1 | 1 | 0% | 2,987 | 3,964 | +33% | 0 | 0 | — |
case-20 | pass→pass | 22,041 | 25,257 | +15% | 1 | 1 | 0% | 3,516 | 4,910 | +40% | 0 | 0 | — |
case-21 | pass→pass | 21,272 | 24,984 | +17% | 1 | 1 | 0% | 3,338 | 3,808 | +14% | 0 | 0 | — |
case-22 | pass→pass | 26,968 | 28,924 | +7% | 1 | 1 | 0% | 3,873 | 5,285 | +36% | 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 +23 percentage points is the difference between those two pass rates over the 22 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.
Other measured skills in the registry, with their headline benchmark lift.