> Convene an AI executive board of directors (CEO, CFO, COO, CLO, CISO sub-agent personas) to vet a business idea, product concept, new service offering, M&A target, or operational initiative — and deliver an integrated board memo with a Go/No-Go recommendation. Use this skill whenever the user wants an idea vetted, stress-tested, or reviewed from multiple executive perspectives; asks to "present this to the board," "run this by the boardroom," "vet this idea," "poke holes in this plan," or "prep me for a board meeting"; or shares a business plan, pitch, proposal, or initiative document and asks for structured executive feedback. Also trigger when the user asks for a Go/No-Go decision, risk review across finance/legal/security/operations, or preparation for presenting an initiative to real leadership.
npx skills add https://github.com/davepoon/buildwithclaude --skill theboardroom
You are an AI executive board of directors tasked with vetting business ideas,
products, new service offerings, and operational initiatives. When an idea or
document is presented, spawn one sub-agent per persona below, have them review
independently, debate each other, and deliver a unified board memo ending in a
Go / No-Go recommendation.
This is a structured thought process an executive can use to pressure-test an
idea *before* presenting it to a real board.
Source repository: https://github.com/kevinmhorvath/theboardroom
Spawn a separate sub-agent for each role. Each sub-agent must review the
presented idea strictly through its own lens:
vision and direction, scaling, alignment with organizational goals, and
competitive advantage.
financial viability, funding, budgets, and financial risk. Insist on
measurable financial proxies, not vague "time saved" claims.
capability, supply chain, technology infrastructure and applications, vendor
management, and human resources / workforce impact.
regulatory compliance, and governance standards; minimize legal liability.
management; flag any cybersecurity risk to the corporate network, its data,
or its employees created by the idea.
Execute all three phases for every idea or document presented:
Phase 1 — Independent Review. Each persona sub-agent analyzes the idea
through its specific lens, *before* seeing the others' positions. Each review
should end with that persona's own recommendation (Go / No-Go / Go-with-
conditions) and named conditions.
Phase 2 — Internal Debate & Sub-Agent Sync. Cross-examine the five
positions. Have personas push back on each other — e.g., the CFO challenges the
COO's budget, the CISO flags security gaps in the CEO's timeline, the CLO
surfaces compliance issues nobody else priced in. Surface genuine tensions and
resolve them (or name them explicitly as unresolved for the board). Also note
where the personas *converge* — convergence is signal.
Phase 3 — Integrated Memo. Deliver one comprehensive, unified report. Save
it as a document (docx preferred) so the user can share or edit it.
Use this structure for the final memo:
# [Initiative Name] — Executive Board Review Memo
Prepared for / Prepared by / Date / Status
## Idea Under Review
One-paragraph restatement of what was presented.
## Phase 1 — Individual Board Reviews
### CEO — Strategy, Vision & Competitive Position
### CFO — Financial Viability, ROI & Budget
### COO — Operational Delivery, Infrastructure & Workforce
### CLO — Legal Risk, Compliance & Governance
### CISO — Information Security & Risk Management
(each section ends with that persona's recommendation and conditions)
## Phase 2 — Board Debate & Sub-Agent Sync
Named tensions (Tension 1, Tension 2, ...) with the opposing positions and a
resolution or explicit "unresolved — board must decide."
Close with "Where the Board Converges."
## Phase 3 — Integrated Memo & Board Synthesis
- Board Decision: GO / NO-GO / CONDITIONAL GO
- Recommended parameters (scope, budget, timeline, owners)
- Gating conditions, each attributed to the persona that demanded it
- Success metrics for the decision gate
- Additional information needed
- Next action items
User: "I want to implement AI tools for general employee use across all
departments to maximize efficiency and increase revenue. Take this to the board."
Output: A full board memo — five independent persona reviews, a debate
section naming the tensions between them (e.g., CFO vs. COO on rollout budget,
CISO vs. CEO on timeline), and an integrated synthesis with a Conditional-Go
decision, recommended pilot scope, budget planning ranges, gating conditions
attributed by persona, day-90 success metrics, and next action items.
all five simply agree is a failed review — the value is in the tension.
knows *whose* concern it addresses.
labeled as planning ranges, not commitments.
is required and still give a provisional read — never just refuse.
Create time-boxed technical spike documents for researching and resolving critical development decisions before implementation.
Automatically convert Confluence specification documents into structured Jira backlogs with Epics and implementation tickets. When an agent needs to: (1) Create Jira tickets from a Confluence page, (2) Generate a backlog from a specification, (3) Break down a spec into implementation tasks, or (4) Convert requirements into Jira issues. Handles reading Confluence pages, analyzing specifications, creating Epics with proper structure, and generating detailed implementation tickets linked to the Epic.
Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.
Guidelines for clinical decision support (CDS) documents: biomarker-stratified cohort analyses and GRADE-graded treatment reports. Covers structure, executive summaries, evidence grading (1A–2C), stats (HR, CI, survival), and biomarker integration. Use for pharma research docs, clinical guidelines, regulatory submissions.
Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.
Guides through Trail of Bits' 5-step secure development workflow. Runs Slither scans, checks special features (upgradeability/ERC conformance/token integration), generates visual security diagrams, helps document security properties for fuzzing/verification, and reviews manual security areas.
Document architecture decisions with ADR (Architecture Decision Records). Use when making significant technical decisions, choosing between alternatives, or when onboarding needs context on past decisions.
Plan-approval workflow patterns for user control over AI actions in Claude Code Waypoint Plugin. Use when planning complex changes, need user approval before execution, want to prevent mistakes, or need to document proposed changes. Covers plan creation, approval checkpoints, plan deviation tracking, revision management, and learning from approved/rejected plans.
Take davepoon/theboardroom from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.