プロンプトエンジニアリング#chain of thought#reasoning#problem solving#prompt engineering#chatgpt

Chain-of-Thought Reasoning Prompt

Force step-by-step reasoning before answering to improve accuracy on complex problems.

対応ツール:ChatGPTClaudeGemini
プロンプト全文
Solve the following problem by thinking step-by-step before giving your final answer. Show your reasoning at each stage.

Problem: [describe problem]

Use this structure:
Step 1: [identify what is being asked]
Step 2: [break down the relevant facts or constraints]
Step 3: [apply the reasoning or calculation]
Step 4: [verify the intermediate result]
Final answer: [concise conclusion]
If you are uncertain at any step, state that explicitly.
💡
AIプロンプトライブラリをMarqlyで整理

チャット履歴の中に役立つプロンプトが埋もれてしまうのを防ぎます。Marqly拡張機能を使ってChatGPT、Claude、Geminiから直接保存し、Proプランのセマンティック検索ですぐに見つけられます。

1クリックでプロンプトをクリップ · ライブラリ全体を横断するProセマンティック検索 · AIの対話を保存する方法や、ソース情報と一緒にプロンプトを整理する便利な拡張機能の詳細をご覧ください。

How to use this prompt

Study the structure, then adapt it to your own task. The key is giving the model a clear role, format, and evaluation criteria.

  1. Copy the full prompt above.
  2. Replace the bracketed placeholders with your own details.
  3. Paste it into chatgpt, claude, gemini (or your preferred AI tool).
  4. Iterate on the output: add constraints, ask follow-ups, or combine multiple results.

Why this prompt works

It gives the AI a clear role, specific inputs, and an output format. That structure reduces vague responses and gives you a draft you can refine in minutes instead of hours.

よくある質問

When should I use chain-of-thought?

Use it for math, logic, multi-step decisions, or whenever accuracy matters more than speed.

Does it increase response length?

Yes. The trade-off is better reasoning and easier verification of the answer.

Last updated:

ホーム · Marqly