Board Meeting

What This Skill Does

The Board Meeting Protocol facilitates structured, multi-agent deliberations to enhance decision-making quality. It aims to prevent groupthink, capture diverse perspectives, and produce actionable decisions. This skill is designed for C-suite executives and chiefs of staff looking to improve board meeting effectiveness and strategic decision-making.

When to Use

• Evaluating market expansion opportunities.
• Determining product direction and strategy.
• Making key hiring and organizational decisions.
• Setting pricing strategies for products or services.
• Assessing technology investments and risks.
• Facilitating strategic discussions on critical topics.

Key Features

• Employs a 6-phase protocol for structured deliberation.
• Gathers context from company memory and past decisions.
• Activates relevant roles based on the discussion topic.
• Ensures independent contributions from each agent.
• Utilizes specific reasoning techniques for each role.
• Captures key points, recommendations, and confidence levels.

Manual Installation

Manual installation

View Full Skill Content

The complete markdown content that gets installed

Board Meeting Protocol

Structured multi-agent deliberation that prevents groupthink, captures minority views, and produces clean, actionable decisions.

Keywords

board meeting, executive deliberation, strategic decision, C-suite, multi-agent, /cs:board, founder review, decision extraction, independent perspectives

Invoke

/cs:board [topic] — e.g. /cs:board Should we expand to Spain in Q3?

The 6-Phase Protocol

P

HASE 1: Context Gathering

Load memory/company-context.md Load memory/board-meetings/decisions.md (Layer 2 O

NLY — never raw transcripts) Reset session state — no bleed from previous conversations Present agenda + activated roles → wait for founder confirmation

Chief of Staff selects relevant roles based on topic (not all 9 every time):

EO, C

MO, C

FO, C

RO, C

OO | | Product direction | C

EO, C

PO, C

TO, C

MO | | Hiring/org | C

EO, C

HRO, C

FO, C

OO | | Pricing | C

MO, C

FO, C

RO, C

PO | | Technology | C

TO, C

PO, C

FO, C

ISO |

P

HASE 2: Independent Contributions (I

SOLATED)

No cross-pollination. Each agent runs before seeing others' outputs.

Order: Research (if needed) → C

MO → C

FO → C

EO → C

TO → C

OO → C

HRO → C

RO → C

ISO → C

PO

Reasoning techniques: C

EO: Tree of Thought (3 futures) | C

FO: Chain of Thought (show the math) | C

MO: Recursion of Thought (draft→critique→refine) | C

PO: First Principles | C

RO: Chain of Thought (pipeline math) | C

OO: Step by Step (process map) | C

TO: Re

Act (research→analyze→act) | C

ISO: Risk-Based (P×I) | C

HRO: Empathy + Data

Contribution format (max 5 key points, self-verified):

[R

OLE] — [D

ATE]

Key points (max 5): • [Finding] — [V

ERIFIED/A

SSUMED] — 🟢/🟡/🔴 • [Finding] — [V

ERIFIED/A

SSUMED] — 🟢/🟡/🔴

Recommendation: [clear position] Confidence: High / Medium / Low What would change my mind: [specific condition]

Each agent self-verifies before contributing: source attribution, assumption audit, confidence scoring. No untagged claims.

P

HASE 3: Critic Analysis

Executive Mentor receives A

LL Phase 2 outputs simultaneously. Role: adversarial reviewer, not synthesizer.

Checklist: Where did agents agree too easily? (suspicious consensus = red flag) What assumptions are shared but unvalidated? Who is missing from the room? (customer voice? front-line ops?) What risk has nobody mentioned? Which agent operated outside their domain?

P

HASE 4: Synthesis

Chief of Staff delivers using the Board Meeting Output format (defined in agent-protocol/S

KILL.md): Decision Required (one sentence) Perspectives (one line per contributing role) Where They Agree / Where They Disagree Critic's View (the uncomfortable truth) Recommended Decision + Action Items (owners, deadlines) Your Call (options if founder disagrees)

P

HASE 5: Human in the Loop ⏸️

Full stop. Wait for the founder.

⏸️ F

OUNDER R

EVIEW — [Paste synthesis]

Options: ✅ Approve | ✏️ Modify | ❌ Reject | ❓ Ask follow-up

Rules: User corrections O

VERRIDE agent proposals. No pushback. No "but the C

FO said..." 30-min inactivity → auto-close as "pending review" Reopen any time with /cs:board resume

P

HASE 6: Decision Extraction

After founder approval: Layer 1: Write full transcript → memory/board-meetings/Y

YYY-MM-DD-raw.md Layer 2: Append approved decisions → memory/board-meetings/decisions.md Mark rejected proposals [D

O_NOT_RESURFACE] Confirm to founder with count of decisions logged, actions tracked, flags added

Memory Structure

memory/board-meetings/ ├── decisions.md # Layer 2 — founder-approved only (Phase 1 loads this) ├── Y

YYY-MM-DD-raw.md # Layer 1 — full transcripts (never auto-loaded) └── archive/Y

YYY/ # Raw transcripts after 90 days

Future meetings load Layer 2 only. Never Layer 1. This prevents hallucinated consensus.

Failure Mode Quick Reference

FO making product calls) | Critic flags; exclude from synthesis | | Layer contamination | Phase 1 loads decisions.md only — hard rule |

References

templates/meeting-agenda.md — agenda format templates/meeting-minutes.md — final output format references/meeting-facilitation.md — conflict handling, timing, failure modes

Board Meeting Protocol

Structured multi-agent deliberation that prevents groupthink, captures minority views, and produces clean, actionable decisions.

Keywords

board meeting, executive deliberation, strategic decision, C-suite, multi-agent, /cs:board, founder review, decision extraction, independent perspectives

Invoke

/cs:board [topic] — e.g. /cs:board Should we expand to Spain in Q3?

The 6-Phase Protocol

[R

OLE] — [D

ATE]

Key points (max 5): • [Finding] — [V

ERIFIED/A

SSUMED] — 🟢/🟡/🔴 • [Finding] — [V

ERIFIED/A

SSUMED] — 🟢/🟡/🔴

Recommendation: [clear position] Confidence: High / Medium / Low What would change my mind: [specific condition]

Each agent self-verifies before contributing: source attribution, assumption audit, confidence scoring. No untagged claims.

P

HASE 3: Critic Analysis

Executive Mentor receives A

LL Phase 2 outputs simultaneously. Role: adversarial reviewer, not synthesizer.

Checklist: Where did agents agree too easily? (suspicious consensus = red flag) What assumptions are shared but unvalidated? Who is missing from the room? (customer voice? front-line ops?) What risk has nobody mentioned? Which agent operated outside their domain?