メニュー
Scenario planning toolkit — 2x2 matrices, four-case canvas, Monte Carlo setup, sensitivity & tornado, decision-tree EV, war-game, reverse stress test, optionality scoring.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | scenario-planning |
| description | Scenario planning toolkit — 2x2 matrices, four-case canvas, Monte Carlo setup, sensitivity & tornado, decision-tree EV, war-game, reverse stress test, optionality scoring. |
| allowed-tools | ["Read","Write","Glob","Grep"] |
Used by cso, chief-risk-officer, cfo, crisis-warroom, capital-allocation. Provides the analytic toolkit for thinking under uncertainty beyond single-point forecasts.
For any material decision:
| Case | Probability | Description | NPV / outcome | Key drivers |
|---|---|---|---|---|
| Base | (typically 50–60%) | Most-likely path | ||
| Upside | (typically 15–25%) | Drivers break favorably | ||
| Downside | (typically 15–25%) | Drivers break unfavorably | ||
| Black-swan | (typically 1–5%) | Tail event; structural break |
Recommendation lens: would we take this action even in the downside case (or only if upside)? What's our regret if black-swan hits?
| Step | What to do |
|---|---|
| 1. Identify drivers | 5–15 key uncertain inputs (revenue, margin, cost, tax, working capital) |
| 2. Choose distribution per driver | Normal (symmetric), lognormal (asymmetric, multiplicative), triangular (bounded), beta (constrained), empirical (fit history) |
| 3. Specify correlations | Revenue × margin is rarely independent. Use covariance matrix |
| 4. Run iterations | 10k+ for stable tails; 50k+ for P1 / P99 |
| 5. Report distribution | P5 / P25 / P50 / P75 / P95 — not just mean |
| 6. Tail decomposition | Which driver(s) dominate the bad tail? |
For sequential decisions with uncertainty:
Decision node [□]
├── Action A
│ Chance node (○)
│ ├── Outcome A1 (prob × value)
│ └── Outcome A2 (prob × value)
│ EV(A) = Σ p · v
└── Action B
...
Choose the action with highest EV — but report variance / downside too.
For strategy / competitive decisions:
Standard approach: scenario → outcome. Reverse: outcome → scenario.
The research doc highlights reverse stress as critical for black-swan preparedness.
For any bet, compute:
Total value = Static NPV + Option value − Reversibility cost
| Option type | Question | Approximate value |
|---|---|---|
| Defer | Can we wait for more information? | Black-Scholes-style on volatility |
| Expand | Can we scale up if it works? | Lattice on success probability |
| Abandon | Can we exit if it doesn't? | Salvage value relative to commitment |
| Stage | Can we phase commitment? | Multi-period lattice |
| Switch | Can we change use? | Spread option |
| Compound | Does this unlock further options? | Option-on-option |
Bets with high option value justify lower static NPV, especially under high uncertainty.
cso leads)Scenario artifacts saved per the requesting role (typically output/strategy/, output/finance/, output/risk/).
AI governance — EU AI Act Article 9, NIST AI RMF, ISO/IEC 42001 — risk classification, lifecycle gates, model cards, HITL policy, AI incident response.
Crisis response toolkit — classification, trigger thresholds, escalation tiers, war-room activation, rapid liquidity stress, supply-chain alternate-source, holding-statement, AAR.
Adversarial red-team debate protocol — when to use it, the 4-step structure, role-pair recipes, Referee scoring, termination conditions, MAS failure mitigations.
Enterprise risk management — COSO ERM 2017 + ISO 31000 — risk taxonomy, appetite statement, top-risk register, KRIs, Bow-Tie, three-lines-of-defense.
Enterprise executive decision frameworks, memo templates, board protocol, RACI, OKR, escalation rules, dissenting-opinion format.
Deterministic financial tools — WACC, NPV, IRR, payback, EVA, real-options, Monte Carlo, sensitivity, covenant/liquidity checks. The Financial Hardcoding Directive.