* 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>
12 KiB
Change Management Playbook
Deep reference for rolling out organizational changes effectively.
1. ADKAR Deep Dive with Startup Examples
Awareness: The "Why" that actually lands
Most change communications fail at awareness because they confuse informing with explaining.
Informing: "We're moving from Jira to Linear next month." Explaining: "Our engineering team loses ~4 hours per week to Jira configuration, search latency, and reporting setup. At our current team size, that's 60+ hours per month. Linear's benchmarks from teams our size show a 40% reduction in that overhead. That's why we're switching — and here's the timeline."
The explanation activates desire. The announcement just creates work.
Real example: Tool migration
"We tried Asana, we tried Notion tasks, we tried spreadsheets. None of them stuck. After talking to 8 engineering leads at similar companies, the pattern was clear: teams that use Linear stick with it. We're going all-in. Here's why it will be different this time: [specific reasons]."
Real example: Reorg
"The current structure has our customer success team reporting to Sales, which creates a conflict: Sales is measured on new logo count, CS is measured on retention. We've seen this play out in three recent customer losses where CS needed to raise concerns but felt the pressure to stay quiet. We're changing the reporting structure so CS reports directly to me. This is about removing a structural conflict, not about performance."
Desire: Addressing the "What's in it for me?"
Every stakeholder group needs a different answer.
Individual contributor:
- "Will my job change significantly?"
- "Will this make my day easier or harder?"
- "Is my role at risk?"
Manager:
- "What new responsibilities do I take on?"
- "How do I explain this to my team?"
- "What happens if someone on my team doesn't adapt?"
Senior leader:
- "What does this change our strategic posture?"
- "What resources are reallocated and to what?"
- "How does this affect my relationships with other senior leaders?"
Resistance scenario: Senior leader whose team is most affected
They're supportive in the room, silent or undermining outside it. Fix: Give them a role in the change. Make them a named co-leader of the implementation. Invested people don't undermine.
Knowledge: The documentation that actually gets used
The reason most change documentation fails: it's written for the decision-maker, not the user.
Documentation that gets used:
- Short (< 2 pages for most changes)
- Organized by role: "If you're in Sales, here's what changes for you"
- Answers "what do I do when X happens?" with specific answers
- Has a clear owner: "Questions? Ask [person] in #channel"
Documentation that doesn't get used:
- Long rationale sections the user doesn't need
- "See the full policy document for details"
- No named point of contact
- Buried in email threads
Ability: The gap between knowing and doing
Signs of a knowledge gap vs. an ability gap:
| Symptom | Knowledge gap | Ability gap |
|---|---|---|
| People don't know what to do | ✅ | |
| People know what to do but don't do it | ✅ | |
| People do it wrong consistently | Could be either | |
| People revert under pressure | ✅ | |
| Training scores high, behavior unchanged | ✅ |
Ability gaps are fixed by:
- Practice time (before being measured)
- Reduced cognitive load during transition
- Peer support (not just manager support)
- Feedback loops that are fast and low-stakes
What kills ability development:
- Measuring performance on the new way in week 1
- Adding new work simultaneously with the change
- Making it embarrassing to ask for help
Reinforcement: The phase everyone skips
Go-live is not success. Go-live is the beginning of adoption.
Reinforcement calendar (template):
| Week | Action |
|---|---|
| Week 1 (go-live) | High-visibility support. Leadership visible. Point person responsive. |
| Week 2 | First adoption check: who's using it? Who isn't? Targeted help to laggards. |
| Week 4 | Celebrate early adopters publicly. Share a win story. |
| Week 6 | Adoption metric reported to leadership. Decommission old way (if applicable). |
| Week 8 | Full adoption expected. Non-adoption now a performance conversation. |
| Month 3 | Retrospective: What's working? What needs adjustment? |
2. Resistance Patterns and Counter-Strategies
The Vocal Skeptic
Who they are: Asks hard questions in all-hands. Other people follow their lead. What they need: To feel heard and to understand the logic. Strategy: Talk to them before the all-hands. Not to persuade them — to hear their concerns and address what's valid. When they feel respected, they often become your best change advocates.
Script: "I know you have concerns about this change. I want to understand them before we go broader with the announcement. What's your biggest worry?"
The Silent Non-Complier
Who they are: Agrees in meetings, continues the old behavior outside. What they need: To understand that non-compliance is visible and has consequences. Strategy: Direct 1:1 conversation. Name the behavior. Ask what's in the way. Give them a clear path.
Script: "I've noticed you're still using [old way] two weeks after we launched [new way]. I want to understand what's in the way for you — is it a knowledge issue, a time issue, or something else?"
The Grieving Top Performer
Who they are: Was excellent under the old system. The change makes their skills less relevant. What they need: Recognition of their past contribution and a clear path forward. Strategy: Name the loss explicitly. "I know you built your expertise on [old approach] and this change asks you to develop a new one. That's a real transition." Then create a specific development plan.
What not to do: Pretend the change doesn't affect them disproportionately.
The Fearful Middle Manager
Who they are: Middle managers whose authority or role scope is reduced by the change. What they need: A clear picture of their new role and why it's still valuable. Strategy: Individual conversation before the announcement. Walk them through what changes, what stays the same, and what their contribution looks like in the new world.
The "We've Been Here Before" Cynics
Who they are: Long-tenured employees who've seen multiple failed change initiatives. What they need: Evidence that this time is different. Strategy: Acknowledge the history. "I know we've announced changes that didn't stick. Here's specifically what's different this time: [specific differences]." Then prove it fast — show momentum in the first 30 days.
3. Communication Plan Template per Change Type
Template: Tool Migration
COMMUNICATION PLAN — [Tool Name] Migration
AUDIENCE: All-hands / [specific team]
DECISION OWNER: [Name]
GO-LIVE DATE: [Date]
POINT OF CONTACT: [Name] in [channel]
COMMUNICATION TIMELINE:
Week -4: Decision finalized (internal only)
Week -3: Training materials ready
Week -2: All-hands announcement (why + timeline + support plan)
Week -1: Training sessions (2 sessions, different times)
Week 0: Go-live. Point person in Slack. Old system still accessible.
Week 2: First adoption check. Targeted help to non-adopters.
Week 4: Old system access restricted.
Week 8: Old system fully decommissioned.
KEY MESSAGES:
- Why we're switching: [honest 2-sentence reason]
- What changes for you: [role-specific, max 3 bullets]
- What doesn't change: [this matters for change fatigue]
- How to get help: [channel, person, office hours]
- Timeline: [specific dates]
FAQ:
Q: Is the old system going away completely?
A: [Honest answer with date]
Q: What if I have data in the old system?
A: [Migration plan or acknowledgment]
Q: What if I'm not proficient by go-live?
A: [Realistic expectation-setting]
Template: Reorg Announcement
REORG COMMUNICATION PLAN
ANNOUNCEMENT DATE: [Date]
EFFECTIVE DATE: [Date]
FORMAT: Live (synchronous), all affected employees
PRE-ANNOUNCEMENT (1 week before):
- 1:1 with every affected leader
- HR briefed and ready for questions
- FAQ prepared
ANNOUNCEMENT FORMAT:
1. Context: Why this change? (2-3 minutes)
2. What's changing: New structure, new reporting lines (3-4 minutes)
3. What's NOT changing: Roles, comp, team members (2 minutes)
4. Timeline: When does the new structure take effect? (1 minute)
5. Q&A: Open, no time limit (at least 15 minutes)
POST-ANNOUNCEMENT (week 1):
- Each manager runs team meeting to answer team-specific questions
- HR available for private conversations
- FAQ published to all
POST-ANNOUNCEMENT (week 2-4):
- New structure is operational
- Transition check-in: what questions emerged that weren't anticipated?
THINGS NOT TO SAY:
- "We can't share why [person] is leaving" (if they are)
- "This affects everyone equally" (it doesn't)
- "No one's job is at risk" (unless this is 100% certain)
4. The Change Fatigue Problem
How organizations develop change fatigue
Phase 1 — Excitement (first 1-2 changes): People engage, try the new way, hope it sticks.
Phase 2 — Skepticism (3-5 changes): People comply but hedge. "Let's see if this one lasts."
Phase 3 — Detachment (6+ changes without completion): People stop investing in changes. Compliance is surface-level. New announcements get eye-rolls.
Phase 4 — Cynicism (entrenched fatigue): People actively resist changes. "We've been here before." High performers leave because they don't want to work in a chaotic environment.
The change inventory audit
Run this before announcing any new change:
| Change | Status | Started | Expected complete |
|---|---|---|---|
| [Change 1] | In progress / Complete / Stalled | ||
| [Change 2] | |||
| [Change 3] |
Rules:
- If > 2 significant changes are in progress, don't start a third
- If any change is stalled, diagnose it before starting something new
- Define "complete" for every change in progress
Recovery from change fatigue
- Declare a change moratorium. "We're not starting anything new for 60 days. We're finishing what we started."
- Complete visible wins. Ship the changes that are 80% done. Demonstrate follow-through.
- Communicate stability. "Here's what is NOT changing this year."
- Slow down the next announcement. More preparation, more consultation, clearer "this time is different" evidence.
5. Measuring Adoption vs. Compliance
Most change leaders measure go-live, not adoption. These are different things.
Adoption metrics by change type
Tool migration:
- % of team actively using the new tool (not just logged in)
- % of relevant workflows completed in new tool vs. old tool
- Support ticket volume in weeks 1-4 (high = knowledge gap; dropping = adoption)
Process change:
- % of relevant transactions following new process
- Error rates in new process vs. old process (should converge over time)
- Time-to-complete for new process (should improve by week 4)
Org change:
- Decision cycle time in new structure (should improve by month 2)
- Escalation patterns (fewer cross-boundary escalations = alignment improving)
- Employee sentiment (survey at months 1, 3, 6)
Culture change:
- Values referenced in 1:1 conversations (manager self-report)
- Values-linked recognition events per month
- Culture survey scores in relevant dimensions (quarterly)
The compliance trap
Measuring compliance: "Did they use the new system? Yes/No." Measuring adoption: "Did they use the new system because it's better, or because they had to?"
Compliance is unstable. It reverts when enforcement loosens. Adoption is self-sustaining.
Adoption diagnostic: Ask a random sample: "Why do you use [new way] instead of [old way]?"
- "Because I have to" = compliance
- "Because it's faster/easier/better" = adoption
Only adoption makes the change permanent.