[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-7dc810b5-a644-473f-afa5-9a41dd05bbb0":3,"$fozrsWqUW-frRa4ZyuhgrLOUtuF3NKBD8nCD1bHQnGFU":42},{"id":4,"title":5,"description":6,"categoryId":7,"moduleId":8,"tags":9,"prompt":10,"icon":11,"source":12,"sourceUrl":13,"authorId":14,"authorName":15,"isPublic":16,"stars":17,"runs":18,"createdAt":19,"updatedAt":19,"module":20,"category":27,"packages":33},"7dc810b5-a644-473f-afa5-9a41dd05bbb0","board-meeting","多代理董事会会议协议，用于战略决策。运行结构化的6阶段审议：背景加载、独立C级管理层贡献（隔离，无交叉污染）、批评分析、综合、创始人审查和决策提取。当用户调用\u002Fcs:board、召开董事会会议或希望对战略问题进行结构化的多视角高管审议时使用。","cat_prod_project","mod_productivity","alirezarezvani,productivity","---\nname: \"board-meeting\"\ndescription: \"Multi-agent board meeting protocol for strategic decisions. Runs a structured 6-phase deliberation: context loading, independent C-suite contributions (isolated, no cross-pollination), critic analysis, synthesis, founder review, and decision extraction. Use when the user invokes \u002Fcs:board, calls a board meeting, or wants structured multi-perspective executive deliberation on a strategic question.\"\nlicense: MIT\nmetadata:\n  version: 1.0.0\n  author: Alireza Rezvani\n  category: c-level\n  domain: board-protocol\n  updated: 2026-03-05\n  frameworks: 6-phase-board, two-layer-memory, independent-contributions\n---\n\n# Board Meeting Protocol\n\nStructured multi-agent deliberation that prevents groupthink, captures minority views, and produces clean, actionable decisions.\n\n## Keywords\nboard meeting, executive deliberation, strategic decision, C-suite, multi-agent, \u002Fcs:board, founder review, decision extraction, independent perspectives\n\n## Invoke\n`\u002Fcs:board [topic]` — e.g. `\u002Fcs:board Should we expand to Spain in Q3?`\n\n---\n\n## The 6-Phase Protocol\n\n### PHASE 1: Context Gathering\n1. Load `memory\u002Fcompany-context.md`\n2. Load `memory\u002Fboard-meetings\u002Fdecisions.md` **(Layer 2 ONLY — never raw transcripts)**\n3. Reset session state — no bleed from previous conversations\n4. Present agenda + activated roles → wait for founder confirmation\n\n**Chief of Staff selects relevant roles** based on topic (not all 9 every time):\n| Topic | Activate |\n|-------|----------|\n| Market expansion | CEO, CMO, CFO, CRO, COO |\n| Product direction | CEO, CPO, CTO, CMO |\n| Hiring\u002Forg | CEO, CHRO, CFO, COO |\n| Pricing | CMO, CFO, CRO, CPO |\n| Technology | CTO, CPO, CFO, CISO |\n\n---\n\n### PHASE 2: Independent Contributions (ISOLATED)\n\n**No cross-pollination. Each agent runs before seeing others' outputs.**\n\nOrder: Research (if needed) → CMO → CFO → CEO → CTO → COO → CHRO → CRO → CISO → CPO\n\n**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\n\n**Contribution format (max 5 key points, self-verified):**\n```\n## [ROLE] — [DATE]\n\nKey points (max 5):\n• [Finding] — [VERIFIED\u002FASSUMED] — 🟢\u002F🟡\u002F🔴\n• [Finding] — [VERIFIED\u002FASSUMED] — 🟢\u002F🟡\u002F🔴\n\nRecommendation: [clear position]\nConfidence: High \u002F Medium \u002F Low\nSource: [where the data came from]\nWhat would change my mind: [specific condition]\n```\n\nEach agent self-verifies before contributing: source attribution, assumption audit, confidence scoring. No untagged claims.\n\n---\n\n### PHASE 3: Critic Analysis\nExecutive Mentor receives ALL Phase 2 outputs simultaneously. Role: adversarial reviewer, not synthesizer.\n\nChecklist:\n- Where did agents agree too easily? (suspicious consensus = red flag)\n- What assumptions are shared but unvalidated?\n- Who is missing from the room? (customer voice? front-line ops?)\n- What risk has nobody mentioned?\n- Which agent operated outside their domain?\n\n---\n\n### PHASE 4: Synthesis\nChief of Staff delivers using the **Board Meeting Output** format (defined in `agent-protocol\u002FSKILL.md`):\n- Decision Required (one sentence)\n- Perspectives (one line per contributing role)\n- Where They Agree \u002F Where They Disagree\n- Critic's View (the uncomfortable truth)\n- Recommended Decision + Action Items (owners, deadlines)\n- Your Call (options if founder disagrees)\n\n---\n\n### PHASE 5: Human in the Loop ⏸️\n\n**Full stop. Wait for the founder.**\n\n```\n⏸️ FOUNDER REVIEW — [Paste synthesis]\n\nOptions: ✅ Approve | ✏️ Modify | ❌ Reject | ❓ Ask follow-up\n```\n\n**Rules:**\n- User corrections OVERRIDE agent proposals. No pushback. No \"but the CFO said...\"\n- 30-min inactivity → auto-close as \"pending review\"\n- Reopen any time with `\u002Fcs:board resume`\n\n---\n\n### PHASE 6: Decision Extraction\nAfter founder approval:\n- **Layer 1:** Write full transcript → `memory\u002Fboard-meetings\u002FYYYY-MM-DD-raw.md`\n- **Layer 2:** Append approved decisions → `memory\u002Fboard-meetings\u002Fdecisions.md`\n- Mark rejected proposals `[DO_NOT_RESURFACE]`\n- Confirm to founder with count of decisions logged, actions tracked, flags added\n\n---\n\n## Memory Structure\n```\nmemory\u002Fboard-meetings\u002F\n├── decisions.md          # Layer 2 — founder-approved only (Phase 1 loads this)\n├── YYYY-MM-DD-raw.md     # Layer 1 — full transcripts (never auto-loaded)\n└── archive\u002FYYYY\u002F         # Raw transcripts after 90 days\n```\n\n**Future meetings load Layer 2 only.** Never Layer 1. This prevents hallucinated consensus.\n\n---\n\n## Failure Mode Quick Reference\n| Failure | Fix |\n|---------|-----|\n| Groupthink (all agree) | Re-run Phase 2 isolated; force \"strongest argument against\" |\n| Analysis paralysis | Cap at 5 points; force recommendation even with Low confidence |\n| Bikeshedding | Log as async action item; return to main agenda |\n| Role bleed (CFO making product calls) | Critic flags; exclude from synthesis |\n| Layer contamination | Phase 1 loads decisions.md only — hard rule |\n\n---\n\n## References\n- `templates\u002Fmeeting-agenda.md` — agenda format\n- `templates\u002Fmeeting-minutes.md` — final output format\n- `references\u002Fmeeting-facilitation.md` — conflict handling, timing, failure modes\n","","imported","https:\u002F\u002Fgithub.com\u002Falirezarezvani\u002Fclaude-skills","user_system_seed","SkillOPIC",true,175,958,"2026-05-16 13:49:31",{"id":8,"name":21,"slug":22,"icon":23,"description":24,"sort":25,"createdAt":26},"效率工具","productivity","mdi-lightning-bolt-outline","文档处理、数据分析、自动化工作流",4,"2026-05-16 12:53:40",{"id":7,"name":28,"slug":29,"icon":30,"description":31,"moduleId":8,"sort":25,"skillCount":32,"createdAt":26},"项目管理","project-management","mdi-view-dashboard-outline","任务管理、进度追踪、报告生成",13,[34],{"id":35,"skillId":4,"version":36,"fileName":37,"fileSize":38,"filePath":39,"fileHash":40,"manifest":41,"createdAt":19},"d1b61ddd-ce8c-4479-bcf5-0ed4cc48a929","1.0.0","board-meeting.zip",8898,"uploads\u002Fskills\u002F7dc810b5-a644-473f-afa5-9a41dd05bbb0\u002Fboard-meeting.zip","d08ff9264b057c377b394bb4a1aee2929333ba5cd816dd0443f6e262ee639286","[{\"path\":\"SKILL.md\",\"isDirectory\":false,\"size\":5416},{\"path\":\"references\u002Fmeeting-facilitation.md\",\"isDirectory\":false,\"size\":8212},{\"path\":\"templates\u002Fmeeting-agenda.md\",\"isDirectory\":false,\"size\":1976},{\"path\":\"templates\u002Fmeeting-minutes.md\",\"isDirectory\":false,\"size\":2465}]",{"code":43,"message":44,"data":45},200,"success",{"items":46,"stats":47,"page":50},[],{"averageRating":48,"totalRatings":48,"ratingCounts":49},0,[48,48,48,48,48],{"limit":51,"offset":48,"hasMore":52,"nextOffset":51,"ratedOnly":16},15,false]