# think

A skill for in-depth analysis of complex problems using Gemini. Applies multiple thinking frameworks—first principles, systems thinking, inversion, second-order effects—to uncover blind spots and surface a grounded recommendation.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 260 installs · ★ 28 repo stars
- Author: johnlindquist
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/johnlindquist/claude/tree/HEAD/skills/think/SKILL.md
- Updated: 2025-12-19
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/johnlindquist-think

## What it does

Think breaks down tough decisions by examining them through different lenses. You describe a problem or idea; the skill applies frameworks (first principles, systems thinking, inversion, second-order effects), shows what each reveals, and synthesizes a recommendation based on the combined insights.

Inside are templates for various scenarios: deep analysis of hard problems, quick reasoning on simpler questions, stress-testing an idea, comparing multiple options, pre-mortem (imagining failure and working backward), and opportunity-cost analysis. Each template structures a prompt for Gemini.

Requires Gemini CLI and an API key. Setup needs `pip install google-generativeai` and the `GEMINI_API_KEY` environment variable.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add johnlindquist/claude --skill think -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add johnlindquist/claude --skill think -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add johnlindquist/claude --skill think -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install johnlindquist/claude skills/think
```

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

### Gemini CLI

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

2. **Platform CLI**
```bash
gemini skills install https://github.com/johnlindquist/claude --path skills/think
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add johnlindquist/claude --skill think -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/johnlindquist/claude/tree/HEAD/skills/think/SKILL.md

## When to use it
- analyze architecture decisions through multiple thinking lenses
- stress-test an idea for logical flaws and hidden assumptions
- compare several options against criteria and pick the strongest one
- plan a debugging strategy step by step
- anticipate failure modes before they happen with pre-mortem

## Example prompts
- Analyze this architecture choice using first principles, systems thinking, inversion, and second-order effects
- Challenge this idea rigorously: uncover hidden assumptions, edge cases, and who might disagree
- Evaluate these three options: Operational Transform versus CRDTs versus a custom sync engine

## Similar
- [mungers-lattice](https://affpapa.org/en/nevibecode/skills/mungers-lattice.md) — skill · 105 installs
- [balanced](https://affpapa.org/en/nevibecode/skills/balanced.md) — skill · 243 installs
- [analysis](https://affpapa.org/en/nevibecode/skills/analysis.md) — skill · 1500 installs
- [ultra-think](https://affpapa.org/en/nevibecode/commands/ultra-think.md) — command · 8383 installs
- [sequential-thinking](https://affpapa.org/en/nevibecode/skills/sequential-thinking.md) — skill · 1800 installs
- [problem-solving](https://affpapa.org/en/nevibecode/skills/problem-solving.md) — skill · 590 installs

## Other versions with the same name
- [think · tw93](https://affpapa.org/en/nevibecode/skills/think.md) — 15400 installs
- [think · agricidaniel](https://affpapa.org/en/nevibecode/skills/agricidaniel-think.md) — 337 installs
- [think · pproenca](https://affpapa.org/en/nevibecode/skills/pproenca-think.md) — 307 installs

From the same set: [johnlindquist/claude](https://affpapa.org/en/nevibecode/by/johnlindquist/claude.md) — 7 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
