# thought-based-reasoning

A skill for Claude and other AI coders that gives the model a method for working through hard problems in explicit steps. Useful when a plain prompt returns the wrong answer.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 1400 installs · ★ 1787
- Author: NeoLabHQ
- License: GPL-3.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/NeoLabHQ/context-engineering-kit/tree/HEAD/skills/thought-based-reasoning/SKILL.md
- Updated: 2026-08-26
- HTML: https://affpapa.org/en/nevibecode/skills/thought-based-reasoning

## What it does

This skill hands the agent a catalogue of reasoning techniques. Inside are prompt templates and a decision table: pick Zero-shot CoT when you have no exemplars, Few-shot CoT when you do, Self-Consistency when a wrong answer costs you. Least-to-Most suits problems with subproblems, Tree of Thoughts suits exploring alternatives.

ReAct covers cases needing outside information, PAL covers computation, Reflexion covers retrying after mistakes. Each technique comes with a template plus its strengths and limits. Some examples are Python code, such as drawing several answers and taking a majority vote.

Self-Consistency means several generations at a temperature above zero, so one answer costs more tokens. Majority voting only works when the final answer can be pulled out and compared. The skill addresses reasoning tasks, not your project's code.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add NeoLabHQ/context-engineering-kit --skill thought-based-reasoning -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add NeoLabHQ/context-engineering-kit --skill thought-based-reasoning -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add NeoLabHQ/context-engineering-kit --skill thought-based-reasoning -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install NeoLabHQ/context-engineering-kit thought-based-reasoning
```

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

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add NeoLabHQ/context-engineering-kit --skill thought-based-reasoning -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/NeoLabHQ/context-engineering-kit --path skills/thought-based-reasoning
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add NeoLabHQ/context-engineering-kit --skill thought-based-reasoning -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/NeoLabHQ/context-engineering-kit/tree/HEAD/skills/thought-based-reasoning/SKILL.md

## When to use it
- break a multi-step arithmetic problem into stages
- pick a reasoning technique that fits the task
- cut variance on decisions where errors are expensive
- make the agent check its own mistakes
- chain from simple subproblems to the hard one

## Example prompts
- Work through this problem step by step using the thought-based-reasoning skill
- Pick the right CoT technique for this task and tell me why
- Generate several answers and return the most common one

## Similar
- [skill-creator](https://affpapa.org/en/nevibecode/skills/skill-creator.md) — skill · 414180 installs
- [writing-for-agents](https://affpapa.org/en/nevibecode/skills/writing-for-agents.md) — skill · 466719 installs
- [media-use](https://affpapa.org/en/nevibecode/skills/media-use.md) — skill · 1100000 installs
- [mcp-builder](https://affpapa.org/en/nevibecode/skills/mcp-builder.md) — skill · 130949 installs
- [subagent-driven-development](https://affpapa.org/en/nevibecode/skills/subagent-driven-development.md) — skill · 237746 installs
- [orchestration](https://affpapa.org/en/nevibecode/skills/orchestration.md) — skill · 349800 installs

From the same set: [neolabhq/context-engineering-kit](https://affpapa.org/en/nevibecode/by/neolabhq/context-engineering-kit.md) — 64 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