# forecast-premortem

forecast-premortem is a Claude Code skill that stress-tests probabilistic forecasts by assuming failure before launch. It reveals overlooked risks and recalibrates overconfident estimates.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 108 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/forecast-premortem/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/forecast-premortem

## What it does

The skill implements Gary Klein's premortem technique for forecasting and decision-making. Rather than estimating success chances upfront, the workflow assumes failure already happened and traces the timeline backward. This perspective brings hidden threats, black swans, and unexamined dependencies into view.

Available modes cover failure premortems, success analyses for pessimistic outcomes below 20%, and multi-angle reviews through critic and observer personas. The process asks for your target prediction, initial probability, and confidence interval. It calculates the cumulative impact of specific breakdown modes to adjust probability figures.

Quantitative recalibration requires numeric inputs for probabilities and intervals. Without those baseline figures, the assessment remains purely qualitative.

## Install

### Claude Code (native platform)

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

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

### Codex

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

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

### Cursor

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

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install lyndonkl/claude skills/forecast-premortem
```

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

### Gemini CLI

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

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

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add lyndonkl/claude --skill forecast-premortem -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/forecast-premortem/SKILL.md

## When to use it
- uncover hidden failure modes behind high-confidence projections
- stress-test pessimistic outcomes with probabilities under 20%
- calculate adjustments for overly narrow confidence intervals
- evaluate plans through conflicting skeptic and neutral viewpoints

## Example prompts
- Run a failure premortem on our target to hit $10M ARR with 75% confidence
- Stress-test this pessimistic 10% commercialization forecast using backcasting
- Evaluate our release plan through the dragonfly eye perspective

## Similar
- [premortem](https://affpapa.org/en/nevibecode/skills/premortem.md) — skill · 914 installs
- [sales-forecast](https://affpapa.org/en/nevibecode/skills/sales-forecast.md) — skill · ★ 12746 repo stars
- [predictive-analytics-construction](https://affpapa.org/en/nevibecode/skills/predictive-analytics-construction.md) — skill · 116 installs
- [clinical-trial-forecast](https://affpapa.org/en/nevibecode/skills/clinical-trial-forecast.md) — skill · ★ 654 repo stars
- [inversion](https://affpapa.org/en/nevibecode/commands/inversion.md) — command · ★ 1988 repo stars
- [forecast](https://affpapa.org/en/nevibecode/skills/forecast.md) — skill · 3200 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
