Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Founder-mode executive team. 13 cs-* C-suite agents (CFO, CMO, CRO, CPO, COO, CHRO, CISO, GC, CDO, CAIO, CCO, VPE, Chief of Staff) and 21 /cs:* slash commands for forcing-question office hours, multi-role boardroom deliberation, strategic sprint pipeline, and meta routing. Use when the founder needs a virtual executive team, when invoking /cs:* commands, or when orchestrating multi-role decisions.
.claude/skills/alirezarezvani-c-level-agents/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 41% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 69% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 58% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 39% | 0% |
| case-18 | ✗→✓ | ▲ Improved | -9% | 0% |
A virtual C-suite delivered through slash commands and persona agents.
founder mode, virtual c-suite, executive team, boardroom, office hours, cfo review, cmo review, strategic sprint, decision logging, cross-model consensus, persona agents, chief of staff, forcing questions
agents/)Each agent wraps an existing c-level skill and adds:
See ../../references/persona-voices.md for voice specs.
skills/)Forcing-question office hours (12):
/cs:office-hours — YC-style 6-question intake/cs:cfo-review — unit economics, runway, dilution/cs:cmo-review — ICP, CAC payback, positioning/cs:cpo-review — RICE, JTBD, North Star, PMF/cs:cro-review — pipeline coverage, win rate, NRR/cs:cto-review — architecture risk, scaling cliff/cs:ciso-review — threat model, blast radius, compliance/cs:gc-review — contracts, IP, regulatory, term sheets/cs:cdo-review — training-data rights, data products, data assets/cs:caio-review — model selection, evals, AI risk, AI costs/cs:cco-review — GRR/NRR decomposition, churn root cause, CS coverage/cs:vpe-review — DORA metrics, cycle time, eng hiring funnel, team structureStrategic sprint pipeline (5):
/cs:brief → /cs:boardroom → /cs:decide → /cs:execute → /cs:post-mortemMeta + safety (4):
/cs:founder-mode — auto-routes to the right C-role/cs:onboard — founder interview → company-context.md/cs:cross-eval — multi-model consensus/cs:freeze — cooldown lock on a decision/cs:onboard # populate company context first
/cs:office-hours "should we hire a VP Sales?"
/cs:founder-mode "runway pressure" # auto-routes to CFO
/cs:boardroom briefs/pricing-v3.md # full panelUser question
│
├─ Single-role? → cs-{role}-advisor agent
│ ↓
│ /cs:{role}-review command (forcing Qs)
│ ↓
│ Skill tools + references
│ ↓
│ Bottom Line + Memo
│
└─ Multi-role? → /cs:boardroom
↓
6-phase deliberation (Phase 2 isolation)
↓
/cs:decide → decision-logger (two-layer memory)
↓
/cs:execute → 90-day plan/cs:decide writes here/cs:boardroom command runs../../references/llm-wiki-bridge.md)/em:* commands stack cleanly on top/cs:cross-eval falls back to Claude-only.Version: 1.0.0 Last Updated: 2026-05-12 Status: Production Ready
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 62,470 | 61,956 | -1% | 1 | 1 | 0% | 8,156 | 7,213 | -12% | 0 | 0 | — |
case-02 | fail→pass | 25,463 | 25,449 | -0% | 1 | 1 | 0% | 2,945 | 4,152 | +41% | 0 | 0 | — |
case-03 | fail→pass | 12,064 | 9,684 | -20% | 1 | 1 | 0% | 1,028 | 1,741 | +69% | 0 | 0 | — |
case-04 | pass→pass | 23,915 | 22,640 | -5% | 1 | 1 | 0% | 2,871 | 3,976 | +38% | 0 | 0 | — |
case-05 | fail→fail | 24,814 | 22,848 | -8% | 1 | 1 | 0% | 3,039 | 3,852 | +27% | 0 | 0 | — |
case-06 | pass→pass | 24,235 | 24,753 | +2% | 1 | 1 | 0% | 2,509 | 3,697 | +47% | 0 | 0 | — |
case-07 | fail→fail | 22,611 | 23,943 | +6% | 1 | 1 | 0% | 2,648 | 3,968 | +50% | 0 | 0 | — |
case-08 | pass→pass | 17,691 | 15,118 | -15% | 1 | 1 | 0% | 2,790 | 3,484 | +25% | 0 | 0 | — |
case-09 | pass→pass | 21,809 | 17,300 | -21% | 1 | 1 | 0% | 2,478 | 3,663 | +48% | 0 | 0 | — |
case-10 | pass→pass | 22,959 | 25,752 | +12% | 1 | 1 | 0% | 2,796 | 4,190 | +50% | 0 | 0 | — |
case-11 | pass→pass | 16,753 | 47,198 | +182% | 1 | 1 | 0% | 2,518 | 3,956 | +57% | 0 | 0 | — |
case-12 | pass→pass | 26,335 | 25,391 | -4% | 1 | 1 | 0% | 2,481 | 4,454 | +80% | 0 | 0 | — |
case-13 | fail→fail | 16,433 | 18,513 | +13% | 1 | 1 | 0% | 2,561 | 3,932 | +54% | 0 | 0 | — |
case-14 | fail→pass | 21,332 | 23,611 | +11% | 1 | 1 | 0% | 2,485 | 3,926 | +58% | 0 | 0 | — |
case-15 | fail→pass | 14,548 | 16,167 | +11% | 1 | 1 | 0% | 2,143 | 2,980 | +39% | 0 | 0 | — |
case-16 | pass→pass | 14,522 | 18,053 | +24% | 1 | 1 | 0% | 2,282 | 3,128 | +37% | 0 | 0 | — |
case-17 | fail→fail | 21,895 | 8,201 | -63% | 1 | 1 | 0% | 2,724 | 2,420 | -11% | 0 | 0 | — |
case-18 | fail→pass | 11,774 | 4,843 | -59% | 1 | 1 | 0% | 1,830 | 1,668 | -9% | 0 | 0 | — |
case-19 | fail→pass | 14,080 | 3,159 | -78% | 1 | 1 | 0% | 1,493 | 1,654 | +11% | 0 | 0 | — |
case-20 | pass→pass | 10,021 | 20,818 | +108% | 1 | 1 | 0% | 2,213 | 4,360 | +97% | 0 | 0 | — |
case-21 | pass→pass | 11,228 | 11,249 | +0% | 1 | 1 | 0% | 1,130 | 2,310 | +104% | 0 | 0 | — |
case-22 | pass→pass | 26,811 | 23,051 | -14% | 1 | 1 | 0% | 3,811 | 4,624 | +21% | 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 +27 percentage points is the difference between those two pass rates over the 22 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 | +83% |
Other measured skills in the registry, with their headline benchmark lift.