Back to Details

board-meeting

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Board Meeting Protocol

董事会会议协议

Structured multi-agent deliberation that prevents groupthink, captures minority views, and produces clean, actionable decisions.
结构化多Agent审议机制，可防止群体思维偏差，捕捉少数派观点，并生成清晰、可执行的决策。

Keywords

关键词

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

Invoke

调用方式

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

The 6-Phase Protocol

六阶段流程

PHASE 1: Context Gathering

PHASE 1: 上下文收集

  1. Load 
    memory/company-context.md
  2. Load 
    memory/board-meetings/decisions.md
    (Layer 2 ONLY — never raw transcripts)
  3. Reset session state — no bleed from previous conversations
  4. Present agenda + activated roles → wait for founder confirmation
Chief of Staff selects relevant roles based on topic (not all 9 every time):
TopicActivate
Market expansionCEO, CMO, CFO, CRO, COO
Product directionCEO, CPO, CTO, CMO
Hiring/orgCEO, CHRO, CFO, COO
PricingCMO, CFO, CRO, CPO
TechnologyCTO, CPO, CFO, CISO
  1. 加载
    memory/company-context.md
  2. 加载
    memory/board-meetings/decisions.md
    (仅加载第二层内容——绝不加载原始会议记录)
  3. 重置会话状态——无之前对话的内容残留
  4. 展示议程+激活角色→等待创始人确认
首席幕僚根据议题选择相关角色（无需每次激活全部9个角色）：
议题激活角色
市场拓展CEO, CMO, CFO, CRO, COO
产品方向CEO, CPO, CTO, CMO
招聘/组织架构CEO, CHRO, CFO, COO
定价策略CMO, CFO, CRO, CPO
技术规划CTO, CPO, CFO, CISO

PHASE 2: Independent Contributions (ISOLATED)

PHASE 2: 独立贡献阶段（隔离式）

No cross-pollination. Each agent runs before seeing others' outputs.
Order: Research (if needed) → CMO → CFO → CEO → CTO → COO → CHRO → CRO → CISO → CPO
Reasoning techniques: CEO: Tree of Thought (3 futures) | CFO: Chain of Thought (show the math) | CMO: Recursion of Thought (draft→critique→refine) | CPO: First Principles | CRO: Chain of Thought (pipeline math) | COO: Step by Step (process map) | CTO: ReAct (research→analyze→act) | CISO: Risk-Based (P×I) | CHRO: Empathy + Data
Contribution format (max 5 key points, self-verified):
undefined
无观点交叉影响。每个Agent在提交输出前不会查看其他Agent的内容。
顺序：调研（如有需要）→ CMO → CFO → CEO → CTO → COO → CHRO → CRO → CISO → CPO
推理方法： CEO: Tree of Thought（三种未来场景）| CFO: Chain of Thought（展示计算过程）| CMO: Recursion of Thought（草稿→批评→优化）| CPO: 第一性原理 | CRO: Chain of Thought（销售漏斗计算）| COO: 逐步分析法（流程地图）| CTO: ReAct（调研→分析→行动）| CISO: 风险导向法（概率×影响）| CHRO: 共情+数据
贡献格式（最多5个要点，需自行验证）：
undefined

[ROLE] — [DATE]

[ROLE] — [DATE]

Key points (max 5): • [Finding] — [VERIFIED/ASSUMED] — 🟢/🟡/🔴 • [Finding] — [VERIFIED/ASSUMED] — 🟢/🟡/🔴
Recommendation: [clear position] Confidence: High / Medium / Low Source: [where the data came from] What would change my mind: [specific condition]

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

---
Key points (max 5): • [Finding] — [VERIFIED/ASSUMED] — 🟢/🟡/🔴 • [Finding] — [VERIFIED/ASSUMED] — 🟢/🟡/🔴
Recommendation: [clear position] Confidence: High / Medium / Low Source: [where the data came from] What would change my mind: [specific condition]

每个Agent在提交贡献前需自行验证：来源归因、假设审核、信心评分。禁止无标记的主张。

---

PHASE 3: Critic Analysis

PHASE 3: 批评分析阶段

Executive Mentor receives ALL 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?
高管导师同时接收所有第二阶段的输出。角色：反方评审者，而非综合者。
检查清单：
  • 哪些地方Agent们过于轻易达成一致？（可疑的共识=危险信号）
  • 哪些是共同但未验证的假设？
  • 哪些角色缺席？（客户声音？一线运营？）
  • 哪些风险无人提及？
  • 哪个Agent超出了自身职责范围？

PHASE 4: Synthesis

PHASE 4: 综合汇总阶段

Chief of Staff delivers using the Board Meeting Output format (defined in 
agent-protocol/SKILL.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)
首席幕僚使用董事会会议输出格式（定义于
agent-protocol/SKILL.md
）提交结果：
  • 需决策事项（一句话）
  • 各角色观点（每个贡献角色一句话）
  • 共识点/分歧点
  • 批评者观点（令人不安的真相）
  • 推荐决策+行动项（负责人、截止日期）
  • 备选方案（若创始人不同意时的选项）

PHASE 5: Human in the Loop ⏸️

PHASE 5: 人工介入环节 ⏸️

Full stop. Wait for the founder.
⏸️ FOUNDER REVIEW — [Paste synthesis]

Options: ✅ Approve | ✏️ Modify | ❌ Reject | ❓ Ask follow-up
Rules:
  • User corrections OVERRIDE agent proposals. No pushback. No "but the CFO said..."
  • 30-min inactivity → auto-close as "pending review"
  • Reopen any time with 
    /cs:board resume
完全暂停。等待创始人操作。
⏸️ FOUNDER REVIEW — [Paste synthesis]

Options: ✅ Approve | ✏️ Modify | ❌ Reject | ❓ Ask follow-up
规则：
  • 用户修正优先级高于Agent提议。不得反驳。不得提及“但CFO说过...”
  • 30分钟无操作→自动标记为“待审核”并关闭
  • 随时可通过
    /cs:board resume
    重新开启

PHASE 6: Decision Extraction

PHASE 6: 决策提取阶段

After founder approval:
  • Layer 1: Write full transcript → 
    memory/board-meetings/YYYY-MM-DD-raw.md
  • Layer 2: Append approved decisions → 
    memory/board-meetings/decisions.md
  • Mark rejected proposals 
    [DO_NOT_RESURFACE]
  • Confirm to founder with count of decisions logged, actions tracked, flags added
创始人批准后：
  • 第一层： 撰写完整会议记录→
    memory/board-meetings/YYYY-MM-DD-raw.md
  • 第二层： 将获批决策追加至→
    memory/board-meetings/decisions.md
  • 标记被否决的提案为
    [DO_NOT_RESURFACE]
  • 向创始人确认已记录的决策数量、跟踪的行动项及添加的标记

Memory Structure

记忆结构

memory/board-meetings/
├── decisions.md          # Layer 2 — founder-approved only (Phase 1 loads this)
├── YYYY-MM-DD-raw.md     # Layer 1 — full transcripts (never auto-loaded)
└── archive/YYYY/         # Raw transcripts after 90 days
Future meetings load Layer 2 only. Never Layer 1. This prevents hallucinated consensus.
memory/board-meetings/
├── decisions.md          # Layer 2 — founder-approved only (Phase 1 loads this)
├── YYYY-MM-DD-raw.md     # Layer 1 — full transcripts (never auto-loaded)
└── archive/YYYY/         # Raw transcripts after 90 days
未来会议仅加载第二层内容，绝不加载第一层。这可防止生成幻觉式共识。

Failure Mode Quick Reference

故障模式速查指南

FailureFix
Groupthink (all agree)Re-run Phase 2 isolated; force "strongest argument against"
Analysis paralysisCap at 5 points; force recommendation even with Low confidence
BikesheddingLog as async action item; return to main agenda
Role bleed (CFO making product calls)Critic flags; exclude from synthesis
Layer contaminationPhase 1 loads decisions.md only — hard rule
故障类型修复方案
群体思维偏差（全员一致同意）重新执行第二阶段的隔离式审议；强制要求提出“最有力的反对论据”
分析瘫痪限制最多5个要点；即使信心低也要强制给出建议
无关细节争论（Bikeshedding）记录为异步行动项；回到主议程
角色越界（CFO做出产品决策）批评者标记；排除在综合汇总之外
层级内容污染第一阶段仅加载decisions.md——硬性规则

References

参考资料

  • templates/meeting-agenda.md
    — agenda format
  • templates/meeting-minutes.md
    — final output format
  • references/meeting-facilitation.md
    — conflict handling, timing, failure modes
  • templates/meeting-agenda.md
    — 议程格式
  • templates/meeting-minutes.md
    — 最终输出格式
  • references/meeting-facilitation.md
    — 冲突处理、时间管理、故障模式