playbooks

home / skills / menkesu / awesome-pm-skills / decision-frameworks

decision-frameworks skill

/decision-frameworks

This skill helps you structure tough product decisions using expected value thinking and regret minimization to reduce paralysis.

npx playbooks add skill menkesu/awesome-pm-skills --skill decision-frameworks

Review the files below or copy the command above to add this skill to your agents.

Files (1)
SKILL.md
2.4 KB
---
name: decision-frameworks
description: Structures difficult decisions using Annie Duke's probabilistic thinking and Ben Horowitz's hard decisions frameworks. Use when facing tough choices, applying expected value thinking, or reducing decision paralysis with regret minimization and pre-mortems.
---

# Decision Architecture

## When This Skill Activates

Claude uses this skill when:
- Facing difficult product decisions
- Choosing between multiple options
- Reducing decision paralysis
- Evaluating tradeoffs

## Core Frameworks

### 1. Expected Value Thinking (Source: Annie Duke)

**The Formula:**
```
Expected Value = (Probability of Success × Value if Successful) 
                - (Probability of Failure × Cost if Fails)
```

**Example:**
```markdown
Decision: Build feature A or B?

Feature A:
- 70% chance of +$100K revenue = $70K
- 30% chance of -$20K cost = -$6K
- Expected value: +$64K

Feature B:
- 30% chance of +$500K revenue = $150K
- 70% chance of -$50K cost = -$35K
- Expected value: +$115K

Choose B (higher EV despite lower probability)
```

### 2. Regret Minimization (Source: Jeff Bezos)

**The Question:**
> "When I'm 80 years old, will I regret not trying this?"

**Framework:**
- Imagine yourself in the future
- Work backwards
- Minimize long-term regret

---

## Action Templates

### Template: Decision Matrix

```markdown
# Decision: [Choice A vs Choice B]

## Expected Value

### Option A
- Success probability: [X]%
- Success value: [$Y]
- Failure probability: [Z]%
- Failure cost: [$W]
- **Expected value:** [$EV]

### Option B
- Success probability: [X]%
- Success value: [$Y]
- Failure probability: [Z]%
- Failure cost: [$W]
- **Expected value:** [$EV]

## Regret Minimization
- If I choose A, will I regret not trying B?
- If I choose B, will I regret not trying A?

## Reversibility
- Can we reverse this? [Yes/No]
- Cost to reverse: [Low/Medium/High]

## Decision: [Option] because [reasoning]
```

---

## Quick Reference

### 🎲 Decision Checklist

**Analysis:**
- [ ] Expected value calculated
- [ ] Regret minimization applied
- [ ] Reversibility assessed
- [ ] Pre-mortem completed

**Decision:**
- [ ] Choice made
- [ ] Reasoning documented
- [ ] Success criteria defined

---

## Key Quotes

**Annie Duke:**
> "Life is poker, not chess. We're making decisions with incomplete information."

**Jeff Bezos:**
> "Most decisions should probably be made with somewhere around 70% of the information you wish you had."

Overview

This skill structures difficult choices using probabilistic thinking and hard-decision techniques inspired by Annie Duke and Ben Horowitz. It helps product leaders convert uncertainty into expected value calculations, apply regret-minimization, and run quick pre-mortems to avoid paralysis. Use it to make clear, documented decisions with defensible tradeoffs and reversal plans.

How this skill works

The skill guides you through an expected value calculation for each option: estimate probability of success, quantify upside, and quantify downside to compute EV. It then prompts regret-minimization and reversibility checks, and captures a short decision matrix and pre-mortem to surface risks. The output is a concise decision record: choice, rationale, success criteria, and rollback plan.

When to use it

  • Choosing between two or more product features or bets with uncertain outcomes
  • Facing analysis paralysis when information is incomplete
  • Evaluating tradeoffs between short-term cost and long-term upside
  • Deciding whether a move is reversible or a one-way commitment
  • Prioritizing roadmap items under time or budget constraints

Best practices

  • Work in ranges, not false precision: use probability bands (e.g., 30–50%)
  • Quantify outcomes in monetary terms or clear business metrics whenever possible
  • Document assumptions and update probabilities as new evidence arrives
  • Perform a quick pre-mortem: list ways the decision could fail and mitigate them
  • Prefer options with higher expected value unless long-term regret or irreversibility changes the choice

Example use cases

  • Deciding whether to build feature A (steady but small revenue) vs feature B (low probability of a breakout)
  • Choosing to invest in hiring a specialist now versus outsourcing temporarily
  • Determining whether to pivot product strategy after mixed early signals
  • Assessing acquisition offers: calculate EV of integration success vs cost of failure
  • Prioritizing technical debt repayment vs new customer-facing features

FAQ

What if I can't assign reliable probabilities?

Use wide probability ranges, leverage analogues or historical data, and run sensitivity tests to see how the decision changes across plausible values.

When should regret minimization override expected value?

When the decision has outsized personal or long-term strategic consequences that EV doesn't capture, or when the option is irreversible and you expect lasting regret.