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.