Install any skill in seconds. Free to start, no credit card required.
Get Started Free →C-suite orchestration layer. Routes founder questions to the right advisor role(s), triggers multi-role board meetings for complex decisions, synthesizes outputs, and tracks decisions. Every C-suite interaction starts here. Loads company context automatically. Use when a founder question needs routing to the right advisor — e.g. 'should we raise now or cut burn?' — or when a multi-domain decision needs a board meeting convened.
.claude/skills/alirezarezvani-chief-of-staff/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | 37% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 174% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 58% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -11% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 39% | 0% |
The orchestration layer between founder and C-suite. Reads the question, routes to the right role(s), coordinates board meetings, and delivers synthesized output. Loads company context for every interaction.
chief of staff, orchestrator, routing, c-suite coordinator, board meeting, multi-agent, advisor coordination, decision log, synthesis
[INVOKE:role|question]Examples:
[INVOKE:cfo|What's the right runway target given our growth rate?]
[INVOKE:board|Should we raise a bridge or cut to profitability?]If loop detected: return to founder with "The advisors are deadlocked. Here's where they disagree: summary]."
| Score | Signal | Action | |-------|--------|--------| | 1–2 | Single domain, clear answer | 1 role | | 3 | 2 domains intersect | 2 roles, synthesize | | 4–5 | 3+ domains, major tradeoffs, irreversible | Board meeting |
+1 for each: affects 2+ functions, irreversible, expected disagreement between roles, direct team impact, compliance dimension.
Full rules in references/routing-matrix.md.
| Topic | Primary | Secondary | |-------|---------|-----------| | Fundraising, burn, financial model | CFO | CEO | | Hiring, firing, culture, performance | CHRO | COO | | Product roadmap, prioritization | CPO | CTO | | Architecture, tech debt | CTO | CPO | | Revenue, sales, GTM, pricing | CRO | CFO | | Process, OKRs, execution | COO | CFO | | Security, compliance, risk | CISO | COO | | Company direction, investor relations | CEO | Board | | Market strategy, positioning | CMO | CRO | | M&A, pivots | CEO | Board | | Contracts, term sheets, legal exposure, IP | GC | CEO | | Data strategy, training-data rights, data assets | CDO | CAIO | | AI strategy, model selection, evals, AI risk | CAIO | CTO | | Retention, churn, customer success, NRR/GRR | CCO | CRO | | Eng delivery, DORA metrics, eng hiring, team structure | VPE | CTO |
Trigger: Score ≥ 4, or multi-function irreversible decision.
BOARD MEETING: [Topic]
Attendees: [Roles]
Agenda: [2–3 specific questions]
[INVOKE:role1|agenda question]
[INVOKE:role2|agenda question]
[INVOKE:role3|agenda question]
[Chief of Staff synthesis]Rules: Max 5 roles. Each role one turn, no back-and-forth. Chief of Staff synthesizes. Conflicts surfaced, not resolved — founder decides.
Full framework in references/synthesis-framework.md.
Output format:
## What We Agree On
[2–3 consensus themes]
## The Disagreement
[Named conflict + each side's reasoning + what it's really about]
## Recommended Actions
1. [Action] — [Owner] — [Timeline]
...
## Your Decision Point
[One question. Two options with trade-offs. No recommendation — just clarity.]Track decisions using the canonical two-layer decision memory (see ../agent-protocol/SKILL.md → "Decision Memory (Canonical Layout)"):
~/.claude/decisions/raw/YYYY-MM-DD-{slug}.md — full deliberation transcript~/.claude/decisions/approved/YYYY-MM-DD-{slug}.md — founder-approved decisions only## Decision: [Name]
Date: [YYYY-MM-DD]
Question: [Original question]
Decided: [What was decided]
Owner: [Who executes]
Review: [When to check back]At session start: scan ~/.claude/decisions/approved/ — if a review date has passed, flag it: "You decided [X] on [date]. Worth a check-in?"
Migration: a legacy single-file log at ~/.claude/decision-log.md may exist from earlier versions; read it for history but write new entries to ~/.claude/decisions/.
Before delivering ANY output to the founder:
../agent-protocol/SKILL.md)The Chief of Staff routes to 33 skills total:
See references/routing-matrix.md for complete trigger mapping.
references/routing-matrix.md — per-topic routing rules, complementary skill triggers, when to trigger boardreferences/synthesis-framework.md — full synthesis process, conflict types, output format| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 22,671 | 15,142 | -33% | 1 | 1 | 0% | 2,859 | 3,937 | +38% | 0 | 0 | — |
case-02 | fail→fail | 19,753 | 33,847 | +71% | 1 | 1 | 0% | 2,954 | 4,436 | +50% | 0 | 0 | — |
case-03 | fail→fail | 16,142 | 13,577 | -16% | 1 | 1 | 0% | 2,733 | 3,725 | +36% | 0 | 0 | — |
case-04 | fail→fail | 15,874 | 20,247 | +28% | 1 | 1 | 0% | 2,835 | 4,477 | +58% | 0 | 0 | — |
case-05 | fail→fail | 13,109 | 15,854 | +21% | 1 | 1 | 0% | 2,790 | 4,446 | +59% | 0 | 0 | — |
case-06 | fail→fail | 12,184 | 13,261 | +9% | 1 | 1 | 0% | 2,298 | 3,887 | +69% | 0 | 0 | — |
case-07 | fail→pass | 25,142 | 17,140 | -32% | 1 | 1 | 0% | 3,253 | 4,468 | +37% | 0 | 0 | — |
case-08 | fail→pass | 6,973 | 7,996 | +15% | 1 | 1 | 0% | 1,080 | 2,956 | +174% | 0 | 0 | — |
case-09 | fail→pass | 7,842 | 3,190 | -59% | 1 | 1 | 0% | 1,335 | 2,109 | +58% | 0 | 0 | — |
case-10 | fail→pass | 16,981 | 3,255 | -81% | 1 | 1 | 0% | 2,410 | 2,144 | -11% | 0 | 0 | — |
case-11 | fail→fail | 8,259 | 4,317 | -48% | 1 | 1 | 0% | 1,108 | 2,316 | +109% | 0 | 0 | — |
case-12 | fail→pass | 9,355 | 4,979 | -47% | 1 | 1 | 0% | 1,558 | 2,172 | +39% | 0 | 0 | — |
case-13 | fail→pass | 6,477 | 3,960 | -39% | 1 | 1 | 0% | 1,109 | 2,104 | +90% | 0 | 0 | — |
case-14 | fail→pass | 10,009 | 3,286 | -67% | 1 | 1 | 0% | 1,652 | 2,168 | +31% | 0 | 0 | — |
case-15 | pass→pass | 10,130 | 5,195 | -49% | 1 | 1 | 0% | 1,239 | 2,474 | +100% | 0 | 0 | — |
case-16 | pass→pass | 5,837 | 7,716 | +32% | 1 | 1 | 0% | 994 | 2,942 | +196% | 0 | 0 | — |
case-17 | fail→pass | 16,395 | 10,713 | -35% | 1 | 1 | 0% | 3,175 | 3,445 | +9% | 0 | 0 | — |
case-18 | fail→pass | 9,711 | 7,590 | -22% | 1 | 1 | 0% | 1,813 | 2,828 | +56% | 0 | 0 | — |
case-19 | pass→pass | 6,459 | 4,967 | -23% | 1 | 1 | 0% | 1,046 | 2,275 | +117% | 0 | 0 | — |
case-20 | fail→pass | 10,303 | 9,205 | -11% | 1 | 1 | 0% | 1,732 | 3,009 | +74% | 0 | 0 | — |
case-21 | fail→pass | 9,032 | 5,630 | -38% | 1 | 1 | 0% | 1,724 | 2,374 | +38% | 0 | 0 | — |
case-22 | fail→fail | 11,307 | 12,522 | +11% | 1 | 1 | 0% | 1,913 | 3,122 | +63% | 0 | 0 | — |
case-23 | fail→pass | 10,763 | 6,234 | -42% | 1 | 1 | 0% | 1,855 | 2,681 | +45% | 0 | 0 | — |
case-24 | fail→pass | 11,742 | 6,334 | -46% | 1 | 1 | 0% | 1,884 | 2,659 | +41% | 0 | 0 | — |
case-25 | fail→pass | 14,179 | 6,931 | -51% | 1 | 1 | 0% | 2,245 | 2,634 | +17% | 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. The headline lift of +56 percentage points is the difference between those two pass rates over the 25 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.
Other measured skills in the registry, with their headline benchmark lift.