# decide

Adopt this skill: https://proskills.md/skills/other/alonmichael-founders-brain-decide

Page: https://proskills.md/skills/other/alonmichael-founders-brain-decide
This document is the public skill bundle for that page. It contains SKILL.md and every helper file the catalog carries. No login is required.

## File: decide/SKILL.md
size: 4354
sha: e968e633cff3726ad46b709f07800fadd3be0e95
upstream: https://github.com/alonmichael/founders-brain/blob/main/decide/SKILL.md

```text
---
name: decide
description: "Use when the thinker faces a consequential decision, is paralyzed by uncertainty, or needs a framework for choosing between imperfect options. Activate when analysis has become a substitute for action."
---

# Decide — Making Irreversible Decisions Under Uncertainty

> **"All that matters is to survive. The rest is just words."**

> **"Always more audacity. Always more audacity."** — Napoleon (via Senra)

---

## Maxims from the Archive

- **"All that matters is to survive. The rest is just words."** — The first decision is always: survive. Everything else follows.
- **"Always more audacity. Always more audacity."** (Napoleon) — When in doubt, act. The bias toward action appears across the entire archive.
- **"If you do everything, you will win."** (LBJ) — Total commitment. Not doing some things well — doing everything.
- **"All that is required is a willingness to bet heavily when the odds are in your favor."** — The fat pitch doctrine. You don't need many decisions. You need a few great ones.
- **"Never use a one-size-fits-all decision-making process. Many decisions are reversible."** (Bezos) — Type 1 vs. Type 2. Classify the decision before agonizing over it.
- **"Beating the competition is relatively easy. Beating yourself is a never-ending commitment."** — The hardest decision is the one against your own inertia.
- **"Know your business from A to Z."** — You can't decide well without total understanding.
- **"I expect you to sacrifice everything."** (Lombardi) — The decision to pursue greatness means deciding what you'll give up.
- **"In other words, we create our own luck and no action can eliminate it."** — Luck favors the decisive.
- **"Give yourself all the chances of success."** — Stack decisions in your favor. Don't rely on any single bet.
- **"Cruyff was never the strongest or the quickest, but he showed how intelligence could rule the game."** — The decision advantage: you don't need to be the strongest, just the smartest.
- **"You never know the consequences of getting what you want until you get what you want."** — Decide with eyes open. Success has costs too.

---

## Philosophy

**Separate reversible from irreversible.** Bezos: *"Never use a one-size-fits-all decision-making process. Many decisions are reversible."* Type 1 decisions deserve deliberation. Type 2 decisions deserve speed. Most people treat every decision like Type 1. That makes them slow.

**Decide with 70% information.** Bezos: if you wait for 90%, you're too slow. *"All that is required is a willingness to bet heavily when the odds are in your favor."* You don't need certainty. You need sufficient evidence and courage.

**Speed is a decision.** *"Always more audacity. Always more audacity."* Boyd's OODA loop. Kaiser built Liberty ships in four days. The speed of your decision cycle is often more important than the quality of any single decision.

**The best decision is the one you commit to fully.** Cortés burned the ships. Bezos quit his hedge fund. *"I expect you to sacrifice everything."* The archive is full of founders who succeeded not because they made the optimal choice, but because they committed so completely they made it work.

**Know when to wait.** The opposite of speed is patience, not slowness. Buffett: *"All that is required is a willingness to bet heavily when the odds are in your favor."* The discipline to NOT decide — to wait for the fat pitch — is as important as speed.

---

## Methodology

1. **Classify the decision.** Type 1 or Type 2? If Type 2, decide now. If Type 1, proceed.
2. **Define it clearly.** Write down exactly what you're deciding and what success looks like.
3. **Apply regret minimization.** Bezos: project to age 80. Which option will you regret NOT taking?
4. **Pre-mortem the top option.** Assume it failed. Why? (See Invert skill.)
5. **Set a deadline and commit.** *"All that matters is to survive. The rest is just words."* Decide. Then make it work.

---

## Key Voices

**Bezos** — Type 1/Type 2, regret minimization, "disagree and commit" · **Buffett** — fat pitch, patience · **Grove** — strategic inflection points · **Napoleon** — "Always more audacity" · **Lombardi** — "I expect you to sacrifice everything" · **Kaiser** — "Problems are only opportunities in work clothes"
```

## File: README.md
upstream: https://github.com/alonmichael/founders-brain/blob/main/README.md

````text
# Founders Brain

> **"Learning from history is a form of leverage."** — David Senra

> **"All I want to know is where I'm going to die, so I'll never go there."** — Charlie Munger

9 thinking skills and 107 maxims distilled from 473 episodes of David Senra's [Founders](https://www.founderspodcast.com/) podcast — 6.6 million words of biography covering Rockefeller, Jobs, Bezos, Munger, Land, Lauder, Ferrari, Walton, and hundreds more.

**founders-brain** turns Claude Code into a thinking partner who reasons the way history's greatest founders did — not with generic business advice, but with specific mental operations, historical parallels, and maxims extracted from the actual biographies.

Drop it into Claude Code, Cowork, OpenClaw, or any agent that supports the [SKILL.md standard](https://github.com/anthropics/claude-code).

## Quick Start

1. Install (30 seconds — see below)
2. Run `/observe` — describe what you're looking at
3. Run `/historicize` — find the founder who faced your problem before
4. Run `/invert` — ask how you'd guarantee failure, then avoid that
5. Run `/decide` — when it's time to commit

## Install — 30 seconds

**Requirements:** [Claude Code](https://docs.anthropic.com/en/docs/claude-code) and [Git](https://git-scm.com/)

### Step 1: Install on your machine

Open Claude Code and paste this:

> Install founders-brain: run **`git clone --depth 1 https://github.com/AlonMichael/founders-brain.git ~/.claude/skills/founders-brain && cd ~/.claude/skills/founders-brain && ./setup`** then add a "founders-brain" section to CLAUDE.md that lists the available skills: /observe, /question, /invert, /model, /historicize, /synthesize, /decide, /focus, /update.

### Step 2: Add to your repo so teammates get it (optional)

> Add founders-brain to this project: run **`cp -Rf ~/.claude/skills/founders-brain .claude/skills/founders-brain && rm -rf .claude/skills/founders-brain/.git && cd .claude/skills/founders-brain && ./setup`** then add a "founders-brain" section to this project's CLAUDE.md listing the available skills.

### Cowork / OpenClaw

Create a project, point it at the cloned directory, and paste the contents of `CLAUDE.md` into the project instructions.

### Codex / Gemini CLI / Cursor

```bash
git clone --depth 1 https://github.com/AlonMichael/founders-brain.git .agents/skills/founders-brain
cd .agents/skills/founders-brain && ./setup
```

## See It Work

```
You:    I'm trying to decide whether to keep building for enterprise
        or pivot to the consumer traction we're seeing organically.

You:    /historicize

Claude: This is a textbook Grove inflection point. Let me give you
        the Intel parallel.

        Intel was a memory company. That was their identity. But the
        market was telling them something different — Japanese competitors
        crushing them on price, while their real edge was in processors.

        Grove asked Drucker: "If we got kicked out and the board brought
        in a new CEO, what would he do?" The answer was immediate:
        "Get out of memory."

        Your organic consumer traction IS the market telling you
        something. Every time you push back toward enterprise, you're
        being Henry Ford insisting on the Model T.

You:    /invert

Claude: Let's flip it. How would you guarantee this pivot fails?

        "In order to succeed, you must first survive."
        — Warren Buffett

        The failure recipe: pivot without enough runway, try to serve
        both segments simultaneously (Buffett: "A loss of focus is what
        worries Charlie and me the most"), or pivot to consumer without
        understanding WHY they're coming organically.

        Invert each one: secure 18 months of runway before committing,
        kill enterprise completely (Jobs killed 70% of Apple's products),
        and spend 2 weeks in pure /observe mode with your organic users
        before building anything.

You:    /decide

Claude: This is Type 1 — irreversible and high-stakes.
        Bezos regret minimization test: at 80, which story do you
        want to tell?

        "All that matters is to survive. The rest is just words."

        Define your kill criteria for enterprise NOW. Write them down.
        If the data already meets them, you have your answer.
```

Three skills, end to end. Not a chatbot — a thinking partner with 473 biographies in its head.

## The Skills

| Command | Thinking Skill | Headline Maxim |
|---------|---------------|----------------|
| `/observe` | Notice what others miss | *"Simplicity is complexity resolved."* |
| `/question` | Reframe the problem | *"The art of being wise is the art of knowing what to overlook."* |
| `/invert` | Think backwards | *"All I want to know is where I'm going to die, so I'll never go there."* |
| `/model` | Apply mental models | *"Take a simple idea and take it seriously."* |
| `/historicize` | Learn from biography | *"Learning from history is a form of leverage."* |
| `/synthesize` | Connect across domains | *"Learn to sell, learn to build. If you can do both, you'll be unstoppable."* |
| `/decide` | Act under uncertainty | *"All that matters is to survive. The rest is just words."* |
| `/focus` | Say no to everything else | *"Focus means saying no."* |
| `/update` | Change your mind | *"Only the paranoid survive."* |

## Philosophy

Three principles from the archive:

1. **The dead have already solved your problem.** Almost no problem is new. Rockefeller, Land, Lauder, Bezos — they faced your problem decades or centuries ago. *"Learning from history is a form of leverage."*

2. **Thinking is a craft, not a talent.** Munger built mental models for sixty years. Buffett reads five hours a day. *"Read 500 pages every day. That's how knowledge works. It builds up like compound interest."*

3. **Inversion is the master key.** Don't ask how to succeed — ask how to fail, then avoid that. *"All I want to know is where I'm going to die, so I'll never go there."*

## Source Material

Built from 473 episodes of [Founders](https://www.founderspodcast.com/) covering:

Rockefeller · Carnegie · Jobs · Bezos · Munger · Buffett · Land · Lauder · Ferrari · Walton · Ford · Grove · Musk · Disney · Knight · Chanel · Arnault · Cucinelli · Price · Honda · Dyson · Bryant · Walsh · da Vinci · Franklin · Ogilvy · Kroc · Hughes · Johnson · Lombardi · Churchill · Edison · and hundreds more.

107 maxims extracted from 6.6 million words of transcript. Every maxim is traceable to the archive.

## Docs

| Doc | What It Covers |
|-----|---------------|
| [SOUL.md](SOUL.md) | Agent identity, beliefs, voice, standards |
| [CLAUDE.md](CLAUDE.md) | Claude Code integration instructions |
| [Catalog](docs/catalog.md) | Episode catalog by domain |
| [Corpus Analysis](docs/corpus-analysis.md) | Full statistical analysis of 473 episodes |
| [Good Outputs](examples/good-outputs.md) | What great responses look like |
| [Bad Outputs](examples/bad-outputs.md) | Anti-patterns to avoid |

## License

MIT. Free forever.

Built by [Alon Michael](https://github.com/AlonMichael). Attribution to David Senra's [Founders](https://www.founderspodcast.com/) podcast appreciated.

> *"Focus means saying no."* — Steve Jobs
>
> *"Excellence is the capacity to take pain."*
>
> *"Don't do anything that someone else can do."* — Edwin Land
````
