Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Index and router for the C-level advisory bundle: 33 skills covering 14 C-suite roles, orchestration, cross-cutting capabilities, and culture. Use when exploring what the c-level-advisor bundle contains, deciding which advisor skill fits a question, or finding the entry points (cs-onboard interview, chief-of-staff routing, board-meeting protocol).
.claude/skills/alirezarezvani-c-level-skills/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 16% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -6% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 81% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 145% | 0% |
| case-17 | ✗→✓ | ▲ Improved | 36% | 0% |
This is the bundle index, not an advisor. It tells you what exists and where to start; the skills below do the work.
cs-onboard skill runs the founder interview (/cs:setup, 7 dimensions, ~45 min) and writes ~/.claude/company-context.md. Refresh quarterly with /cs:update. This is the canonical context schema every advisor reads.chief-of-staff skill routes any question to the right advisor(s). See its routing matrix for all 14 roles.board-meeting skill runs a 6-phase deliberation: (1) context gathering → (2) independent contributions (isolated) → (3) critic analysis → (4) synthesis → (5) founder review (full stop) → (6) decision extraction. Invoked via /cs:boardroom in the c-level-agents plugin.~/.claude/decisions/{raw,approved}/ (see ../agent-protocol/SKILL.md → "Decision Memory (Canonical Layout)").14 C-suite roles + critic (15): ceo-advisor, cfo-advisor, cto-advisor, coo-advisor, cpo-advisor, cmo-advisor, cro-advisor, ciso-advisor, chro-advisor, general-counsel-advisor, chief-data-officer-advisor, chief-ai-officer-advisor, chief-customer-officer-advisor, vpe-advisor — plus the executive-mentor critic (sibling plugin).
Orchestration (6): cs-onboard, chief-of-staff, board-meeting, decision-logger, agent-protocol, context-engine.
Cross-cutting (6): board-deck-builder, scenario-war-room, competitive-intel, org-health-diagnostic, ma-playbook, intl-expansion.
Culture & collaboration (6): culture-architect, company-os, founder-coach, strategic-alignment, change-management, internal-narrative.
Plus this index (1). 37 stdlib-only Python tools and 68 reference docs across the bundle.
Full matrix in ../chief-of-staff/SKILL.md and ../chief-of-staff/references/routing-matrix.md. Primary roles: CFO (capital/burn), CRO (pipeline/sales), CMO (positioning), CPO (roadmap/PMF), CTO (architecture), COO (ops/OKRs), CHRO (people), CISO (security), GC (contracts/term sheets), CDO (data strategy/training-data rights), CAIO (AI strategy/evals), CCO (retention/GRR), VPE (delivery/DORA), CEO (direction). Multi-domain or irreversible → board meeting.
../../../c-level-agents/ — 13 cs- persona agents + 21 `/cs: slash commands on top of these skills../../executive-mentor/ — adversarial /em:* critic commands../../CLAUDE.md — full architecture diagram and integration guide| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 15,061 | 15,079 | +0% | 1 | 1 | 0% | 1,639 | 2,396 | +46% | 0 | 0 | — |
case-02 | fail→fail | 57,135 | 30,264 | -47% | 1 | 1 | 0% | 8,245 | 4,756 | -42% | 0 | 0 | — |
case-03 | fail→fail | 30,625 | 32,724 | +7% | 1 | 1 | 0% | 3,857 | 4,564 | +18% | 0 | 0 | — |
case-04 | fail→pass | 16,127 | 12,959 | -20% | 1 | 1 | 0% | 1,810 | 2,091 | +16% | 0 | 0 | — |
case-05 | pass→pass | 19,040 | 11,891 | -38% | 1 | 1 | 0% | 2,105 | 1,744 | -17% | 0 | 0 | — |
case-06 | fail→pass | 17,942 | 10,643 | -41% | 1 | 1 | 0% | 1,708 | 1,604 | -6% | 0 | 0 | — |
case-07 | pass→pass | 15,939 | 10,178 | -36% | 1 | 1 | 0% | 1,769 | 1,629 | -8% | 0 | 0 | — |
case-08 | pass→pass | 16,846 | 12,294 | -27% | 1 | 1 | 0% | 1,643 | 1,976 | +20% | 0 | 0 | — |
case-09 | pass→pass | 9,188 | 17,974 | +96% | 1 | 1 | 0% | 1,399 | 1,810 | +29% | 0 | 0 | — |
case-10 | pass→pass | 10,516 | 12,098 | +15% | 1 | 1 | 0% | 936 | 1,902 | +103% | 0 | 0 | — |
case-11 | pass→pass | 15,341 | 6,395 | -58% | 1 | 1 | 0% | 1,306 | 1,838 | +41% | 0 | 0 | — |
case-12 | pass→pass | 9,735 | 9,756 | +0% | 1 | 1 | 0% | 1,636 | 2,219 | +36% | 0 | 0 | — |
case-13 | pass→pass | 14,392 | 17,314 | +20% | 1 | 1 | 0% | 1,482 | 2,322 | +57% | 0 | 0 | — |
case-14 | fail→pass | 12,003 | 12,656 | +5% | 1 | 1 | 0% | 1,093 | 1,973 | +81% | 0 | 0 | — |
case-15 | pass→pass | 12,212 | 13,015 | +7% | 1 | 1 | 0% | 1,212 | 1,978 | +63% | 0 | 0 | — |
case-16 | fail→pass | 4,617 | 10,484 | +127% | 1 | 1 | 0% | 657 | 1,607 | +145% | 0 | 0 | — |
case-17 | fail→pass | 52,972 | 4,327 | -92% | 1 | 1 | 0% | 1,091 | 1,484 | +36% | 0 | 0 | — |
case-18 | fail→pass | 17,031 | 8,289 | -51% | 1 | 1 | 0% | 1,527 | 1,211 | -21% | 0 | 0 | — |
case-19 | fail→pass | 9,982 | 8,218 | -18% | 1 | 1 | 0% | 1,620 | 1,322 | -18% | 0 | 0 | — |
case-20 | pass→pass | 12,196 | 6,849 | -44% | 1 | 1 | 0% | 1,252 | 1,882 | +50% | 0 | 0 | — |
case-21 | pass→pass | 13,862 | 7,029 | -49% | 1 | 1 | 0% | 1,848 | 1,868 | +1% | 0 | 0 | — |
case-22 | pass→pass | 6,179 | 18,605 | +201% | 1 | 1 | 0% | 764 | 1,528 | +100% | 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, and 21 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 +32 percentage points is the difference between those two pass rates over the 21 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 | +41% |
Other measured skills in the registry, with their headline benchmark lift.