7 ready-made prompts
ChatGPT Prompts
Prompts for ChatGPT, Claude and Gemini: summarising, research, translation, personas, reasoning.
These prompts are written for the model's actual failure modes, not for a demo. Each one forces a specific output shape, so the result is usable without a second round of editing.
ChatGPT Prompt for Summarising Long Documents (3 Layers)
Turn a 30-page report into something readable in ten minutes: one-sentence core, an executive summary and a bulleted detail layer.
Beginner ChatGPTClaudeChatGPT Idea Generation Prompt: 30 Ideas, 5 Angles
Ends the "nothing comes to mind" loop: multiplies one topic across five angles and scores every idea for feasibility.
Beginner ChatGPTClaudeChatGPT Persona Prompt: Expert Role Template
Instead of a shallow answer to the same question, get an expert's view: identity, experience, bias, boundaries and output rules.
Beginner ChatGPTClaudeTranslation Prompt That Keeps Tone and Terminology
Instead of a literal translation, keep meaning, tone and technical terms — and make the model check its own work at the end.
Intermediate ChatGPTClaudeResearch Prompt: Balanced Brief With Counter-Arguments
A research prompt that produces a quick but balanced picture: you define the scope, the model must include opposing views.
Intermediate ClaudeClaude Prompts: Long-Context and Analysis Templates
XML-tagged prompt skeletons built for Claude's long context and its strength at following structured instructions.
Intermediate GeminiGemini Prompts: Short, Direct Templates for Google AI
Built for Gemini's preference for short, direct instructions, including prompts that work alongside Search and Workspace.
BeginnerFrequently asked
About ChatGPT Prompts
Do these prompts work on models other than ChatGPT?
Yes. Text prompts are model-agnostic: the same instruction works on Claude, Gemini, Copilot and Grok. Output style differs slightly, but the structure holds.
Why do the prompts contain square brackets?
Those are the fields you fill in: your product, audience, data. Leaving them empty produces generic output; filling them is what makes the result specific.
Other categories