466aa13a7b
* feat: C-Suite expansion — 8 new executive advisory roles Add COO, CPO, CMO, CFO, CRO, CISO, CHRO advisors and Executive Mentor. Expands C-level advisory from 2 to 10 roles with 74 total files. Each role includes: - SKILL.md (lean, <5KB, ~1200 tokens for context efficiency) - Reference docs (loaded on demand, not at startup) - Python analysis scripts (stdlib only, runnable CLI) Executive Mentor features /em: slash commands (challenge, board-prep, hard-call, stress-test, postmortem) with devil's advocate agent. 21 Python tools, 24 reference frameworks, 28,379 total lines. All SKILL.md files combined: ~17K tokens (8.5% of 200K context window). Badge: 88 → 116 skills * feat: C-Suite orchestration layer + 18 complementary skills ORCHESTRATION (new): - cs-onboard: Founder interview → company-context.md - chief-of-staff: Routing, synthesis, inter-agent orchestration - board-meeting: 6-phase multi-agent deliberation protocol - decision-logger: Two-layer memory (raw transcripts + approved decisions) - agent-protocol: Inter-agent invocation with loop prevention - context-engine: Company context loading + anonymization CROSS-CUTTING CAPABILITIES (new): - board-deck-builder: Board/investor update assembly - scenario-war-room: Cascading multi-variable what-if modeling - competitive-intel: Systematic competitor tracking + battlecards - org-health-diagnostic: Cross-functional health scoring (8 dimensions) - ma-playbook: M&A strategy (acquiring + being acquired) - intl-expansion: International market entry frameworks CULTURE & COLLABORATION (new): - culture-architect: Values → behaviors, culture code, health assessment - company-os: EOS/Scaling Up operating system selection + implementation - founder-coach: Founder development, delegation, blind spots - strategic-alignment: Strategy cascade, silo detection, alignment scoring - change-management: ADKAR-based change rollout framework - internal-narrative: One story across employees/investors/customers UPGRADES TO EXISTING ROLES: - All 10 roles get reasoning technique directives - All 10 roles get company-context.md integration - All 10 roles get board meeting isolation rules - CEO gets stage-adaptive temporal horizons (seed→C) Key design decisions: - Two-layer memory prevents hallucinated consensus from rejected ideas - Phase 2 isolation: agents think independently before cross-examination - Executive Mentor (The Critic) sees all perspectives, others don't - 25 Python tools total (stdlib only, no dependencies) 52 new files, 10 modified, 10,862 new lines. Total C-suite ecosystem: 134 files, 39,131 lines. * fix: connect all dots — Chief of Staff routes to all 28 skills - Added complementary skills registry to routing-matrix.md - Chief of Staff SKILL.md now lists all 28 skills in ecosystem - Added integration tables to scenario-war-room and competitive-intel - Badge: 116 → 134 skills - README: C-Level Advisory count 10 → 28 Quality audit passed: ✅ All 10 roles: company-context, reasoning, isolation, invocation ✅ All 6 phases in board meeting ✅ Two-layer memory with DO_NOT_RESURFACE ✅ Loop prevention (no self-invoke, max depth 2, no circular) ✅ All /em: commands present ✅ All complementary skills cross-reference roles ✅ Chief of Staff routes to every skill in ecosystem * refactor: CEO + CTO advisors upgraded to C-suite parity Both roles now match the structural standard of all new roles: - CEO: 11.7KB → 6.8KB SKILL.md (heavy content stays in references) - CTO: 10KB → 7.2KB SKILL.md (heavy content stays in references) Added to both: - Integration table (who they work with and when) - Key diagnostic questions - Structured metrics dashboard table - Consistent section ordering (Keywords → Quick Start → Responsibilities → Questions → Metrics → Red Flags → Integration → Reasoning → Context) CEO additions: - Stage-adaptive temporal horizons (seed=3m/6m/12m → B+=1y/3y/5y) - Cross-references to culture-architect and board-deck-builder CTO additions: - Key Questions section (7 diagnostic questions) - Structured metrics table (DORA + debt + team + architecture + cost) - Cross-references to all peer roles All 10 roles now pass structural parity: ✅ Keywords ✅ QuickStart ✅ Questions ✅ Metrics ✅ RedFlags ✅ Integration * feat: add proactive triggers + output artifacts to all 10 roles Every C-suite role now specifies: - Proactive Triggers: 'surface these without being asked' — context-driven early warnings that make advisors proactive, not reactive - Output Artifacts: concrete deliverables per request type (what you ask → what you get) CEO: runway alerts, board prep triggers, strategy review nudges CTO: deploy frequency monitoring, tech debt thresholds, bus factor flags COO: blocker detection, scaling threshold warnings, cadence gaps CPO: retention curve monitoring, portfolio dog detection, research gaps CMO: CAC trend monitoring, positioning gaps, budget staleness CFO: runway forecasting, burn multiple alerts, scenario planning gaps CRO: NRR monitoring, pipeline coverage, pricing review triggers CISO: audit overdue alerts, compliance gaps, vendor risk CHRO: retention risk, comp band gaps, org scaling thresholds Executive Mentor: board prep triggers, groupthink detection, hard call surfacing This transforms the C-suite from reactive advisors into proactive partners. * feat: User Communication Standard — structured output for all roles Defines 3 output formats in agent-protocol/SKILL.md: 1. Standard Output: Bottom Line → What → Why → How to Act → Risks → Your Decision 2. Proactive Alert: What I Noticed → Why It Matters → Action → Urgency (🔴🟡⚪) 3. Board Meeting: Decision Required → Perspectives → Agree/Disagree → Critic → Action Items 10 non-negotiable rules: - Bottom line first, always - Results and decisions only (no process narration) - What + Why + How for every finding - Actions have owners and deadlines ('we should consider' is banned) - Decisions framed as options with trade-offs - Founder is the highest authority — roles recommend, founder decides - Risks are concrete (if X → Y, costs $Z) - Max 5 bullets per section - No jargon without explanation - Silence over fabricated updates All 10 roles reference this standard. Chief of Staff enforces it as a quality gate. Board meeting Phase 4 uses the Board Meeting Output format. * feat: Internal Quality Loop — verification before delivery No role presents to the founder without passing verification: Step 1: Self-Verification (every role, every time) - Source attribution: where did each data point come from? - Assumption audit: [VERIFIED] vs [ASSUMED] tags on every finding - Confidence scoring: 🟢 high / 🟡 medium / 🔴 low per finding - Contradiction check against company-context + decision log - 'So what?' test: every finding needs a business consequence Step 2: Peer Verification (cross-functional) - Financial claims → CFO validates math - Revenue projections → CRO validates pipeline backing - Technical feasibility → CTO validates - People/hiring impact → CHRO validates - Skip for single-domain, low-stakes questions Step 3: Critic Pre-Screen (high-stakes only) - Irreversible decisions, >20% runway impact, strategy changes - Executive Mentor finds weakest point before founder sees it - Suspicious consensus triggers mandatory pre-screen Step 4: Course Correction (after founder feedback) - Approve → log + assign actions - Modify → re-verify changed parts - Reject → DO_NOT_RESURFACE + learn why - 30/60/90 day post-decision review Board meeting contributions now require self-verified format with confidence tags and source attribution on every finding. * fix: resolve PR review issues 1, 4, and minor observation Issue 1: c-level-advisor/CLAUDE.md — completely rewritten - Was: 2 skills (CEO, CTO only), dated Nov 2025 - Now: full 28-skill ecosystem map with architecture diagram, all roles/orchestration/cross-cutting/culture skills listed, design decisions, integration with other domains Issue 4: Root CLAUDE.md — updated all stale counts - 87 → 134 skills across all 3 references - C-Level: 2 → 33 (10 roles + 5 mentor commands + 18 complementary) - Tool count: 160+ → 185+ - Reference count: 200+ → 250+ Minor observation: Documented plugin.json convention - Explained in c-level-advisor/CLAUDE.md that only executive-mentor has plugin.json because only it has slash commands (/em: namespace) - Other skills are invoked by name through Chief of Staff or directly Also fixed: README.md 88+ → 134 in two places (first line + skills section) * fix: update all plugin/index registrations for 28-skill C-suite 1. c-level-advisor/.claude-plugin/plugin.json — v2.0.0 - Was: 2 skills, generic description - Now: all 28 skills listed with descriptions, all 25 scripts, namespace 'cs', full ecosystem description 2. .codex/skills-index.json — added 18 complementary skills - Was: 10 roles only - Now: 28 total c-level entries (10 roles + 6 orchestration + 6 cross-cutting + 6 culture) - Each with full description for skill discovery 3. .claude-plugin/marketplace.json — updated c-level-skills entry - Was: generic 2-skill description - Now: v2.0.0, full 28-skill ecosystem description, skills_count: 28, scripts_count: 25 * feat: add root SKILL.md for c-level-advisor ClawHub package --------- Co-authored-by: Leo <leo@openclaw.ai>
5.3 KiB
5.3 KiB
name, description, license, metadata
| name | description | license | metadata | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| board-meeting | 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 /cs:board, calls a board meeting, or wants structured multi-perspective executive deliberation on a strategic question. | MIT |
|
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
PHASE 1: Context Gathering
- Load
memory/company-context.md - Load
memory/board-meetings/decisions.md(Layer 2 ONLY — 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):
| Topic | Activate |
|---|---|
| Market expansion | CEO, CMO, CFO, CRO, COO |
| Product direction | CEO, CPO, CTO, CMO |
| Hiring/org | CEO, CHRO, CFO, COO |
| Pricing | CMO, CFO, CRO, CPO |
| Technology | CTO, CPO, CFO, CISO |
PHASE 2: Independent Contributions (ISOLATED)
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):
## [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.
PHASE 3: Critic Analysis
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?
PHASE 4: Synthesis
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)
PHASE 5: Human in the Loop ⏸️
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
PHASE 6: Decision Extraction
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
Memory Structure
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.
Failure Mode Quick Reference
| Failure | Fix |
|---|---|
| Groupthink (all agree) | Re-run Phase 2 isolated; force "strongest argument against" |
| Analysis paralysis | Cap at 5 points; force recommendation even with Low confidence |
| Bikeshedding | Log as async action item; return to main agenda |
| Role bleed (CFO making product calls) | Critic flags; exclude from synthesis |
| Layer contamination | Phase 1 loads decisions.md only — hard rule |
References
templates/meeting-agenda.md— agenda formattemplates/meeting-minutes.md— final output formatreferences/meeting-facilitation.md— conflict handling, timing, failure modes