# expected-value

The expected-value skill weighs possible gains and losses by their probabilities to compare uncertain choices. Use it to assess a product bet, rank projects, or map a decision tree.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 142 installs · ★ 203 repo stars
- Author: lyndonkl
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/lyndonkl/claude/tree/HEAD/skills/expected-value/SKILL.md
- Updated: 2026-09-01
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/expected-value

## What it does

The skill guides an analysis from defining alternatives through listing outcomes, estimating probabilities and payoffs, and calculating expected values. It then helps interpret the result in light of risk preferences and factors such as learning or reputation, which may not translate neatly into money.

Reference materials include templates in `resources/template.md`, methods in `resources/methodology.md`, and an evaluation rubric at `resources/evaluators/rubric_expected_value.json`. Outcomes should be mutually exclusive and cover all possibilities, with probabilities adding up to 1.0. For rare, irreversible choices, a high expected value alone does not settle the decision; risk aversion matters too. The skill also covers decision trees, project portfolio allocation, and continuous outcomes using Monte Carlo.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add lyndonkl/claude --skill expected-value -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/expected-value/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/expected-value/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add lyndonkl/claude --skill expected-value -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/expected-value/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add lyndonkl/claude --skill expected-value -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/expected-value/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install lyndonkl/claude skills/expected-value
```

2. **Manually: put the files in place**
- File: `.github/skills/expected-value/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add lyndonkl/claude --skill expected-value -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/lyndonkl/claude --path skills/expected-value
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/expected-value/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add lyndonkl/claude --skill expected-value -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/lyndonkl/claude/tree/HEAD/skills/expected-value/SKILL.md

## When to use it
- compare risky options by expected value
- estimate whether a product launch is worth pursuing
- allocate a budget across projects with different risk profiles
- map a sequence of choices as a decision tree

## Example prompts
- Compare launching this feature with not launching it, using my probability and revenue estimates.
- Help allocate this budget across projects by expected return and risk.
- Build a decision tree for this plan and compare the options using outcome probabilities.

## Similar
- [value](https://affpapa.org/en/nevibecode/skills/value.md) — skill · 35500 installs
- [deal-value-calc](https://affpapa.org/en/nevibecode/skills/deal-value-calc.md) — skill · 33300 installs
- [event-sponsor-value-proposition](https://affpapa.org/en/nevibecode/skills/event-sponsor-value-proposition.md) — skill · 6600 installs
- [platform-value-set-generate](https://affpapa.org/en/nevibecode/skills/platform-value-set-generate.md) — skill · 5300 installs
- [value-dividend-screener](https://affpapa.org/en/nevibecode/skills/value-dividend-screener.md) — skill · 4100 installs
- [longbridge-value-investing](https://affpapa.org/en/nevibecode/skills/longbridge-value-investing.md) — skill · 3500 installs

From the same set: [lyndonkl/claude](https://affpapa.org/en/nevibecode/by/lyndonkl/claude.md) — 49 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
