Files
claude-skills-reference/c-level-advisor/internal-narrative/references/narrative-frameworks.md
Alireza Rezvani 466aa13a7b feat: C-Suite expansion — 8 new executive advisory roles (2→10) (#264)
* 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>
2026-03-06 01:35:08 +01:00

212 lines
10 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
# Narrative Frameworks
Reference frameworks for building compelling, consistent business narratives.
---
## 1. Storytelling Structure for Business
### The SCR Framework (Situation, Complication, Resolution)
Barbara Minto's Pyramid Principle adapted for business narrative. Works for any audience.
**Situation:** The established facts everyone agrees on.
**Complication:** What changed, what problem arose, what makes the situation untenable.
**Resolution:** What you're doing about it, and why this solution works.
**Example — Investor update:**
> **Situation:** We entered Q2 with €650K ARR and a target of €800K. Our DACH pipeline was strong at 3x coverage.
>
> **Complication:** Two large deals (€90K combined ARR) that were expected to close in May pushed to Q3 due to procurement delays on the customer side. We ended Q2 at €710K — below target but within the range we'd flag as manageable.
>
> **Resolution:** Both deals are now signed with June start dates. We're entering Q3 at €800K ARR. We've added a new procurement risk flag to our pipeline methodology to catch this pattern earlier.
**Why it works:** It respects the audience's intelligence, acknowledges the problem directly, and frames your response before they can object.
---
### The Problem-Solution-Evidence Structure
Best for pitches, product announcements, and strategy communications.
1. **The world as it is:** What's the current reality?
2. **What's broken about it:** Why is the status quo painful or inefficient?
3. **What we're doing:** Your specific solution
4. **Why it works:** Evidence, mechanism, or proof
5. **What happens next:** Call to action or forward look
**Example — All-hands strategy communication:**
> The world as it is: We have 80 customers in DACH. Churn is 8% annually. That means we're losing 67 customers a year just to stay flat.
>
> What's broken: Our onboarding takes 6 weeks. By week 4, customers haven't seen value yet and they're questioning the decision. We've traced 60% of churn to customers who never completed onboarding.
>
> What we're doing: We're redesigning onboarding to show the first meaningful mobility report within 48 hours of account activation.
>
> Why it will work: We ran this with 5 pilot customers in Q2. Time-to-first-value dropped from 4 weeks to 2 days. 4 of 5 expanded their contract within 60 days.
>
> What happens next: Engineering ships the new onboarding flow by August 15. CS is retrained by August 22. We'll run the new flow with all new customers from September 1 and report back at the October all-hands.
---
## 2. The Founder's Narrative
The founder's personal story is one of the most underutilized assets in a startup. Used well, it anchors the company's mission and creates genuine connection.
### The Founder Story Structure
**Origin:** What led you to this problem? (Ideally personal — you experienced it, someone you loved experienced it, you couldn't stop thinking about why nobody was solving it)
**Insight:** What did you see that others didn't? (Your unique perspective or unfair advantage)
**Decision:** The moment you committed. (Specific, not aspirational — "I left my job on March 14" not "I decided to pursue my passion")
**What you've learned:** 23 honest observations that shaped your approach. (Including what you got wrong)
**Where you're going:** Connection from your personal why to where the company is heading.
**Example (condensed):**
> My mother had a fall in 2018 that broke her hip. She spent 3 months in rehabilitation. The terrifying part: nobody saw it coming. Her doctor had assessed her fall risk 4 months earlier — using a paper questionnaire. I spent two years talking to geriatricians trying to understand why this assessment was still done by hand, on paper, in 2018. The answer: nobody had made it easy enough for a non-specialist to do it digitally. That's what we're building.
**Why it matters:** Investors, candidates, and customers all respond to a founder who started from a real problem rather than a market opportunity. The narrative makes you memorable and makes the mission credible.
---
## 3. How to Deliver Bad News Across Audiences
### Universal principles
1. **Internal first.** Always. Every time. No exceptions.
2. **Direct, not hedged.** "We missed our Q2 target by 12%" beats "Q2 performance came in below our expectations."
3. **Own it before explaining it.** Context comes after acknowledgment, not before.
4. **State what you're doing.** Bad news without a response plan creates panic.
5. **Give a timeline.** "We'll know more by [date]" is better than open-ended uncertainty.
### Delivering bad news to employees
**Format:** Synchronous (all-hands or team meeting), followed by written summary.
**What to say:**
- What happened (factual, no spin)
- What it means for the company
- What it means for them specifically (will roles change? Will comp change?)
- What you're doing about it
- When you'll have more information
**What not to say:**
- "I can't share the details" (share everything you legally can)
- "This is actually good news because..." (if it's bad news, don't reframe it before acknowledging it)
- "We saw this coming" (if you did, why didn't you tell them?)
**Example — Missed fundraise:**
> "I have to share news that's disappointing. We went out to raise a Series A in Q1, and we didn't close the round. We had term sheets that fell through when the market conditions shifted in April. We're not in crisis — we have 12 months of runway — but we need to recalibrate. Here's what that means concretely: we're pausing 3 open headcount. Everyone currently on the team keeps their role. We're going back to market in Q4 with stronger metrics. I'll share our updated financial model with everyone by Friday and answer every question you have."
---
### Delivering bad news to investors
**Format:** Written update (monthly update format) + proactive call if material.
**What to say:**
- Headline the bad news in the first paragraph (don't bury it)
- Context: what changed and what didn't change
- What you're doing about it
- What you need from them (if anything)
**What investors hate:**
- Finding out from someone other than you
- Bad news wrapped in so much context they have to work to find it
- "We're watching it closely" without specific action
- Consistent over-optimism followed by consistent misses
**Example — Investor update paragraph:**
> "Revenue miss: We ended Q2 at €710K ARR vs. a target of €800K. Two deals totaling €90K pushed to Q3 due to customer procurement delays (not product or relationship issues — both have since signed). We've adjusted our sales process to flag procurement risk earlier. Q3 is starting at €800K with those deals live."
---
### Delivering bad news to customers
**Scope:** Only share bad news that affects them. Don't share internal struggles that aren't relevant to their experience.
**Format:** Proactive communication from their account owner or a senior leader.
**What customers need:**
- What happened (that affects them)
- What you're doing about it
- What they should do (if anything)
- Who to contact
**What customers don't need:**
- Your internal financial struggles
- Drama about team changes
- More detail than affects their use of your product
**Example — Service disruption:**
> "Yesterday evening we experienced a 90-minute service outage that affected your access to [feature]. We've identified the root cause (a failed database migration) and deployed a fix. Your data is intact and complete. We've implemented additional monitoring to prevent this from recurring. I'd like to schedule a brief call to answer any questions you have."
---
## 4. Narrative Consistency Checklist
Use before any significant external communication.
### Pre-communication audit
**Factual consistency:**
- [ ] Is the ARR/revenue figure consistent with what we've shared with investors?
- [ ] Is the team size consistent with what's on LinkedIn and our careers page?
- [ ] Are our stated priorities consistent with our published roadmap?
- [ ] Is our "stage" description consistent across all channels? (We can't be "early stage" to investors and "established leader" to customers)
**Message consistency:**
- [ ] Does this message conflict with anything said in the last 90 days?
- [ ] If an employee read this external message, would they recognize the company?
- [ ] If an investor read our internal all-hands, would they find anything that contradicts what we've told them?
**Audience appropriateness:**
- [ ] Have we answered the key question for this specific audience?
- [ ] Have we avoided sharing information this audience doesn't need and shouldn't have?
- [ ] Have we framed the message for what this audience cares about — not what we want them to care about?
---
## 5. All-Hands Presentation Templates
See `templates/all-hands-template.md` for the complete slide-by-slide template.
### Monthly all-hands (3045 min)
**Structure:**
1. State of the company (10 min) — honest, metric-driven
2. Progress on quarterly rocks (5 min) — on track / off track / done
3. Team spotlight (5 min) — one team's work, why it matters
4. What's coming next 30 days (5 min) — what to expect
5. Q&A (1015 min) — real questions, real answers
### Quarterly all-hands (6090 min)
**Structure:**
1. Last quarter results vs. targets (15 min)
2. What we learned (10 min) — honest reflection on what didn't work
3. Next quarter priorities (15 min) — company rocks, why these three
4. Strategy update (10 min) — anything changing? Why?
5. Team recognition (10 min) — specific, values-linked examples
6. Q&A (1520 min)
### Annual all-hands (24 hours, often a full day)
**Structure:**
1. Year in review: what we achieved (30 min)
2. What we learned — what we'd do differently (20 min)
3. State of the company: financial health, competitive position (20 min)
4. 3-year vision update (30 min)
5. Next year's strategy and priorities (30 min)
6. Department presentations: what each team is building (60 min)
7. Celebrations and recognition (20 min)
8. Q&A + social (open-ended)
### The "no-BS questions" technique
At any all-hands, reserve the last 5 minutes for: "What question are you afraid to ask publicly? Submit anonymously via [link]."
Read 35 of the hardest ones out loud and answer them honestly. This builds more trust than 45 minutes of polished presentation.