* 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>
9.8 KiB
Company Operating System — 90-Day Implementation Guide
Don't implement everything at once. The fastest path to failure is trying to launch the full operating system in week one. Build incrementally. Let the team experience wins before adding complexity.
Before You Start
Prerequisites
Leadership alignment (non-negotiable): Every member of the leadership team must understand why you're doing this and commit to running the system. One holdout destroys the whole model. If the CFO skips the L10 meetings, the system won't work.
Current state audit:
- What meetings currently exist? Which can be replaced?
- Who owns which functions today? (Even informally)
- What metrics are being tracked? (Even inconsistently)
Assign an OS owner: One person is responsible for the implementation and ongoing maintenance of the operating system. Usually the COO or CEO (at smaller companies). This is not a committee job.
Week 1–2: Accountability Chart + Scorecard
Accountability Chart Workshop (Week 1)
Duration: 2–3 hours, full leadership team
Step 1 — List all functions (30 min) On a whiteboard, list every function the company performs:
- Sales (inbound, outbound, partnerships)
- Marketing (content, paid, brand)
- Product (roadmap, design, research)
- Engineering (frontend, backend, devops)
- Customer success (onboarding, support, retention)
- Finance (accounting, FP&A, legal)
- People (recruiting, HR, culture)
- Operations (processes, tools, facilities)
Step 2 — Assign owners (45 min) For each function: "Who is the one person ultimately accountable?" Write their name. Rules: One name only. No joint ownership. One person can own multiple functions at small scale.
Step 3 — Identify gaps and overlaps (30 min)
- Gaps: Functions with no owner → Who should own them? Or do we need a hire?
- Overlaps: Two people said they own the same thing → Resolve now, not later.
Step 4 — Publish and socialize (Week 2) Share with the full company. Explain what an accountability chart is and isn't. "This is about clarity, not hierarchy. It tells everyone who to go to for each function."
Output: A documented accountability chart. Use a simple tool (Miro, Google Slides, Ninety.io).
Scorecard Design (Week 2)
Duration: 90 minutes, leadership team
Step 1 — List candidate metrics (30 min) Each leader lists 3–5 metrics they already track or wish they tracked. No filtering yet.
Step 2 — Filter to 5–15 (30 min) Criteria: Is it measurable weekly? Does it tell us if the company is healthy? Does one person own it? Drop: metrics that are monthly only, metrics without a clear owner, metrics that measure activity not outcomes.
Step 3 — Set weekly targets (20 min) For each metric: what's the weekly target? Not a range — a number. Red/yellow/green thresholds.
Step 4 — Assign owners (10 min) Every metric has one owner who is responsible for reporting it weekly.
Output: A scorecard document. 5–15 metrics, owner, target, weekly tracking column.
First scorecard run: Week 2 or 3. It won't be perfect. That's fine.
Week 3–4: Meeting Pulse (Start With L10)
Don't start all the meetings at once. Start with the weekly L10. Replace existing leadership syncs.
L10 Meeting Setup
Schedule: Same day, same time, every week. Non-negotiable attendance. Duration: 90 minutes. No more, no less. Facilitator: Rotate or assign to COO/CEO. The facilitator keeps time and follows the agenda.
Fixed agenda:
- Good news (5 min) — One personal, one business from each person. No skipping.
- Scorecard review (5 min) — Traffic light only. Red items go to the issues list.
- Rock review (5 min) — Each person: "on track" or "off track." No justification needed at this step.
- Customer/employee headlines (5 min) — One sentence each. No reports.
- Issues (60 min) — IDS process. Prioritize the top 3–5 issues. Solve them.
- To-do review (5 min) — Review last week's commitments (done/not done). No excuses, just data.
- Conclude (5 min) — Rate the meeting 1–10. What would make next week better?
First L10 meeting: It will feel awkward. Run through the agenda anyway. The team needs the repetition to internalize it. By week 4, it should feel natural.
Issues List Setup
Create a shared document (Notion, Google Docs, or dedicated tool):
- Issue title
- Priority (High / Medium / Low)
- Status (Open / In progress / Solved)
- Owner (once assigned)
- Due date
At the first L10, generate the issues list by asking: "What's getting in our way right now?" Expect 10–20 items on the first pass.
Week 5–8: Rocks and Quarterly Planning
Quarterly Planning Session (end of Week 5 or start of Week 6)
Duration: 4–8 hours (or 2 × 4-hour days for larger teams) Who: Full leadership team
Session structure:
Part 1: Review previous quarter (60–90 min)
- What rocks were completed? What were dropped?
- What did we learn?
- What changed in the market or company?
Part 2: Confirm or update company direction (60 min)
- Is the 1-year goal still valid?
- Any major strategy shifts needed?
- Update the V/TO or OPSP if using EOS or Scaling Up.
Part 3: Set company rocks (90 min)
- Brainstorm: What are the 3–7 most important things to accomplish this quarter?
- Prioritize. Be ruthless. 3 rocks done > 7 rocks started.
- Each rock: clear owner, clear definition of done, 90-day timeline.
Part 4: Set individual rocks (60 min)
- Each leader sets their 3–7 rocks (aligned with company rocks where possible)
- Share with group: dependencies? Conflicts? Overloaded people?
Part 5: Communicate (Week 6)
- Share company rocks with the full organization within 1 week
- Each team sets their own rocks, cascaded from company rocks (3–5 per team)
Rock template:
Rock: [What you'll accomplish]
Owner: [One person]
Due date: [Specific date within the quarter]
Definition of done: [How we'll know it's complete]
Dependencies: [What else needs to happen first]
Week 9–12: Issue Resolution Mastery + Communication Cadence
By now the L10 should be running smoothly. Weeks 9–12 focus on deepening IDS skills and establishing the broader communication cadence.
IDS Practice
The issue resolution process often degrades in weeks 5–8. Common problems:
- Issues discussed but never solved (no clear action item)
- Same issues recurring (root cause not addressed)
- Too many issues, not enough resolution (prioritization failing)
IDS calibration exercise (Week 9): In the next L10, after each issue is "solved," ask:
- "Is this actually solved, or are we postponing it?"
- "What's the specific action? Who owns it? When is it due?"
- "Is this the real issue, or a symptom of something deeper?"
Communication Cadence Setup
Build out the full communication calendar:
| Communication | Frequency | Owner | Format | Tool |
|---|---|---|---|---|
| Company all-hands | Monthly | CEO | Update + Q&A | Video call |
| Quarterly planning results | Quarterly | CEO/COO | Written + live | Notion + all-hands |
| Board update | Monthly | CEO + CFO | Board memo | Doc |
| Investor update | Monthly | CEO + CFO | Template | |
| Department L10s | Weekly | Dept lead | L10 format | In-person / Zoom |
| Daily standups | Daily | Team leads | 15 min | Team call |
Company all-hands template:
- State of the company (financial health, key metrics) — 10 min
- Quarterly rocks: what we committed to, where we stand — 10 min
- Wins and recognitions — 5 min
- What's coming next quarter — 10 min
- Q&A — 15–25 min
Post-90 Days: Refinement and Optimization
Month 4 retrospective
After the first full quarter, run a retrospective on the operating system itself:
- What's working? What isn't?
- Which meetings should continue as-is? Which need adjustment?
- Is the scorecard measuring the right things?
- Are rocks the right size and specificity?
- What should we add next?
Scorecard evolution
By month 4, you'll know which metrics matter most. Add 2–3 that are missing. Remove metrics that nobody uses for decisions.
L10 health check
Rate your L10 meetings over the first quarter:
- Average rating < 7: The agenda isn't being followed or issues aren't being resolved. Diagnose.
- Average rating 7–8: Normal. Keep building discipline.
- Average rating > 8: The team is engaged. Start extending the system to department level.
Department L10s (Month 4+)
Once leadership L10 is running well, cascade the meeting structure:
- Each department runs their own weekly L10
- Department rocks cascade from company rocks
- Issues that cross departments are escalated to leadership L10
Year 1 annual planning
End of year 1: run a full-day annual planning session.
- Review the year: what did we accomplish? What did we miss? What did we learn?
- Update 3-year vision (has it changed?)
- Set next year's annual goals
- Set Q1 rocks
- Celebrate. Seriously — mark the milestone.
Implementation Anti-Patterns
Skipping the accountability chart: Without ownership clarity, every other system breaks down. Do this first.
Building a perfect scorecard before starting: Start with 5 imperfect metrics. Improve over time.
Not replacing existing meetings: Adding L10 on top of 3 existing meetings creates meeting overload. Cancel the redundant ones.
Leader non-participation: If one leader consistently skips or is disengaged, the system won't work. Address this directly — it's a culture issue, not a calendar issue.
Changing the L10 agenda: The agenda works because of repetition. Resist the urge to customize it for the first 6 months.
Rocks without accountability: If nobody checks rocks at the L10 ("on track / off track"), they become wish lists. The weekly review is what makes them real.