# Q Thinking Chain

> Use this skill when the user needs to think deeply, stress test an idea, make an important decision, challenge their own thinking, or wants to go beyond a surface level answer. Activate for analysis, critique, decision support, or deep reasoning tasks.

- Skill: `kju4q/q-thinking-chain` (Agent Skill, multi-file: 4 files)
- Install (CLI): `npx skillmds@latest add kju4q/q-thinking-chain`
- Raw SKILL.md: https://api.skillmd.com/api/skills/kju4q/q-thinking-chain/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: kju4q (https://skillmd.com/u/kju4q)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/kju4q/q-thinking-chain

---


# Claude Chain

## Description

Use this skill when the user needs to think through a complex problem, stress test an idea, make an important decision, or wants to go deeper than a surface level answer. Activate when the user asks for analysis, critique, decision support, or wants to challenge their own thinking.

## What this skill does

This skill gives Claude a structured thinking framework built around three techniques. Each one is designed for a different kind of thinking challenge. Read the techniques folder to understand each one before applying them.

## Techniques

- techniques/reasoning-layer.md — use when the user wants a deeper, more committed answer
- techniques/adversarial-room.md — use when the user wants to stress test or critique an idea
- techniques/belief-updater.md — use when the user is working through uncertainty with multiple possible explanations

## How to use

When a user brings you a problem, decision, or idea, assess which technique fits best. You can combine techniques if the situation calls for it. Always adapt the technique to the user's actual context — do not apply it rigidly.

Ask the user which technique they want to use if it is not clear from their message.

## Gotchas

- Do not give a polished diplomatic answer when using the adversarial technique. The value is in genuine ruthless critique not balanced feedback.
- Do not jump to the committed answer in the reasoning layer without first showing the safe answer and its flaws. The contrast is what creates the insight.
- Do not maintain hypotheses that are obviously dead. Update and remove them as evidence comes in. Keep the list alive and honest.
- Do not apply all three techniques at once unless the user explicitly asks for a full analysis.

## Notes

This skill is part of the q-claude-skills collection. New techniques are added regularly. Check the techniques folder for the latest additions.