This copy-ready roleplay prompt helps you start a mystery adventure with choices with fewer blank-page decisions. Paste it into ChatGPT and Claude, fill the variables, and you get a structured first draft you can edit. It is written for repeatable results and tells you what to check before publishing.
4.9(79 ratings)833 copies
Updated By Author
48 words · v1.0
Fill in the blanks · 1 variable
ChatGPT promptReplace every highlighted token before sending
Start a {setting} mystery adventure. Describe a scene in 120 words, give me three plausible choices and track my inventory, clues and suspicions. Never decide my actions for me. Keep continuity and end each turn on a small question. Do not introduce supernatural explanations unless I choose them.
---
Platform note: Work through the task step by step, then give the final answer in the requested format. Ask one clarifying question if a required detail is missing.
Share what worked, what broke and which model you used. Comments appear after posting and are moderated for spam.
How to use this prompt
1
Open ChatGPT and start a new chat. Paste the prompt exactly as written.
2
Replace each placeholder ({setting}) with your own details. Leave the instructions and the output format untouched.
3
Add one concrete example or data point if the model's first answer is vague. Specific input produces specific output.
4
Run it once, then ask for a single revision with a specific critique rather than regenerating from scratch.
5
Review the result. That the content stays fictional, respectful and within the platform's usage policies.
Worked example
This is the kind of input the prompt expects and the shape of output it produces. Your result will differ with the model and the details you supply.
Example input
Setting: a coastal village
Example output
**Scene:** the character stays in voice, reveals one concrete detail about their world, asks you a question and leaves you a meaningful choice. Out-of-character commands are marked with [OOC] and answered briefly without breaking the scene. The simulation stays fictional and does not impersonate a real person. After the session, the model summarises what it observed about your choices and offers one harder scenario.
Tips for a better result
Give the character a want, a fear and a flaw; without them the persona collapses into a generic assistant.
Use an out-of-character command to adjust tone without restarting the scene.
Keep real people, especially private individuals, out of impersonation scenarios.
Change one variable at a time and compare the outputs; it is the fastest way to learn what this model responds to.
Common mistakes
Letting the model make decisions for your character.
Assuming a persuasive roleplay character is a reliable source of facts.
Pushing a scenario into harassment, impersonation or unsafe content.
Verified Knowledge · FAQ
Questions about this prompt
Practical answers about running the start a mystery adventure with choices prompt.
Related prompts
Same job, a different angle — or the next step in the workflow.
Simulate a difficult stakeholder meeting with a prompt built for Claude and ChatGPT. It supplies context, constraints and an output contract, then asks the model to surface assumptions and gaps. Copy it, fill the variables and treat the result as a structured draft, not a final answer.
This copy-ready roleplay prompt helps you play a lateral thinking puzzle with fewer blank-page decisions. Paste it into ChatGPT and Claude, fill the details, and you get a structured first draft you can edit. It is written for repeatable results and tells you what to check before publishing.
A roleplay prompt for create a choose-your-own-path story. It gives ChatGPT and Claude a clear role, explicit constraints and a defined output, so the first answer is closer to usable. Fill in the variables, run it once, then use the verification notes on this page to review the result.
ChatGPTClaude
4.8(81)779 copies
A
Written and reviewed by Author
AIPrompt123 Contributor
Contributing author and prompt engineer at AIPrompt123.
Last reviewed 17 November 2026 · version 1.0 · tested on ChatGPT, Claude
Comments
Share what worked, what broke and which model you used. Comments appear after posting and are moderated for spam.