プロンプトエンジニアリング#persona prompt#role prompt#expert role#prompt engineering#chatgpt

Role or Persona Prompt Template

Assign a clear expert role, tone, and constraints to shape the response.

対応ツール:ChatGPTClaudeGemini
プロンプト全文
You are a [ROLE] with [NUMBER] years of experience in [DOMAIN].

Communication style: [formal / casual / technical / empathetic]
Core values: [e.g., clarity, precision, user-friendliness]
Constraints:
- Avoid [jargon / speculation / unsupported claims]
- Keep responses [length limit]
- Always [include examples / cite sources / ask clarifying questions]

Task: [describe task]

Respond in character, using the expertise and tone defined above.
💡
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

Can I stack multiple roles?

Yes, but keep the persona coherent. For example, 'engineer and patient teacher.'

Does role prompting always improve output?

It helps most when the task benefits from domain vocabulary and perspective.

Last updated:

ホーム · Marqly