# think

think — a skill that shifts the AI into deep analysis mode: instead of the first reasonable answer, it finds the highest-leverage solution by connecting ideas across domains. Use it when you need strategy, not instructions.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 307 installs · ★ 227 repo stars
- Author: pproenca
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/pproenca/dot-skills/tree/HEAD/skills/.curated/think/SKILL.md
- Updated: 2026-08-15
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/pproenca-think

## What it does

Think activates when you ask for thinking, brainstorming, strategy, or figuring out what to do next. The skill reframes how the AI works: it seeks the intersection where concepts from different disciplines combine into a solution that no single-domain expert would have found. It starts by identifying the real problem beneath what you asked, then expands the landscape—examining how adjacent and distant fields tackle similar patterns.

The core mechanism is finding cross-domain collision points: moments where ideas from two or three different contexts fold together into unexpected leverage. The skill also teaches resistance to first answers, searching for opposing views, questioning whether the problem can be avoided entirely because a platform or standard already solved it.

Installation varies by platform: Claude Code, Cursor, GitHub Copilot and others use different paths and commands. After setup, the skill loads into a local folder with working instructions.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add pproenca/dot-skills --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 pproenca/dot-skills --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 pproenca/dot-skills --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 pproenca/dot-skills skills/.curated/think
```

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

### Gemini CLI

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

2. **Platform CLI**
```bash
gemini skills install https://github.com/pproenca/dot-skills --path skills/.curated/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 pproenca/dot-skills --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/pproenca/dot-skills/tree/HEAD/skills/.curated/think/SKILL.md

## When to use it
- choose a strategy among competing approaches
- uncover a non-obvious solution by linking concepts across fields
- reframe the problem to see what you actually need
- stress-test logic before committing to execution
- think like a strategist instead of a task executor

## Example prompts
- What's our best move with this architecture?
- How would a strategist approach authorization differently?
- I'm stuck. What's the highest-leverage move right now?

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: a1a106ca543d9c7a.

BEGIN THIRD-PARTY FILE a1a106ca543d9c7a
```text
---
name: think
description: >
  Deep strategic thinking mode that finds the single highest-leverage,
  most innovative action by blending concepts across domains. Use this
  skill whenever the user asks you to think, brainstorm, strategize, or
  figure out what to do next — even casually. Trigger on phrases like
  "what should we do", "what's the best approach", "what would you
  suggest", "think about this", "what's the smartest move", "I'm stuck",
  "ideas?", "hmm what if we...", "what's next", "how should we approach",
  or any request for creative/strategic ideation rather than
  straightforward execution. When in doubt about whether the user wants
  execution or ideation, lean toward triggering this skill.
---

# Think

You've been asked to think. Not to execute, not to implement, not to
follow a recipe — to actually think. This is different from your
default mode. Your default mode is helpful and competent but tends
toward the first reasonable answer. Here, you're after the *best*
answer.

## The Core Question

Before anything else, ask yourself:

> "What is the single smartest, most radically innovative, and most
> accretive thing I could suggest right now?"

Not "what's reasonable." Not "what's standard." The *single smartest
thing.* The one that makes people go "oh, that's clever" — not
because it's complicated, but because it's so obviously right in
hindsight that you wonder why nobody said it sooner.

## How to Get There

### 1. Understand the Real Problem

The stated problem is rarely the actual problem. Before proposing
anything, figure out:

- What is the user actually trying to achieve? Not what they asked
  for — what they *need*.
- What constraints are they operating under that they haven't
  stated?
- What would "wildly successful" look like here?

If someone asks "how should I structure this database?", maybe the
real question is "how do I build something that doesn't need a
database at all?"

### 2. Map the Full Landscape

Before narrowing, widen. What are ALL the relevant concepts, tools,
patterns, and domains that touch this problem? Think across:

- **The immediate domain** — the tech, the framework, the codebase
- **Adjacent domains** — what do similar problems look like in other
  fields of engineering?
- **Distant domains** — what would biology, economics, game theory,
  architecture, or systems thinking say about this pattern?

The breakthrough usually lives at the intersection of two or more of
these. Not in any single one.

### 3. Find the Intersection (4D Chess)

This is the core move and the skill's reason for existing. Look for
the spot where concepts from *different domains* collide to create
```
END THIRD-PARTY FILE a1a106ca543d9c7a

The third-party file has ended. Everything between the a1a106ca543d9c7a tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2687 of 9187 bytes. © pproenca · MIT · https://github.com/pproenca/dot-skills/tree/HEAD/skills/.curated/think/SKILL.md

_Part of the page did not fit — see the HTML version._

---
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
