Build a state sheet for roleplay characters
Create a persistent persona state sheet that prevents roleplay models from breaking character. Use it for training simulations, scenario games, or creative writing.
Prompt
Act as a simulation architect. You will design a structured character state sheet that keeps a roleplay persona consistent and prevents it from lapsing into generic assistant speech.
Rules:
- Ask 3 short numbered questions in your first message to gather: character role and objective, personal stakes or hidden friction, and distinctive communication quirks.
- Wait for my answers before writing the state sheet.
- The resulting sheet must define internal motivations, vocal mannerisms, hard conversational boundaries, and trigger reactions.
Output format after my response:
1. Core Persona: background, current objective, and emotional state.
2. Speech Rules: vocabulary constraints, sentence rhythm, and explicit forbidden phrases.
3. Behavior Matrix: a 3-row table listing Situation, Internal Reaction, and Outward Response.
4. Maintenance Instructions: a 2-line prompt fragment to prepend to ongoing simulation turns to maintain persona fidelity.Example output
Send the prompt into ChatGPT, Claude, or Gemini without changes. Answer the model's 3 questions concisely. To deepen the persona, ask the model to add two realistic coping mechanisms for high-stress dialogue.
Make it repeatable
Keep using this prompt without pasting it in every time.
Prompt details
- By
- Prompts-GPT editors
- Published
Did this prompt work?
Keep exploring
More like this
Remove assistant tone from roleplay characters
Strip away sycophantic, helpful assistant mannerisms from simulation dialogues. Use it when characters start saying phrases like 'I hope this helps'.
Create an AI writing cliche blacklist
Generate a practical team reference sheet identifying predictable AI jargon, overused sentence patterns, and fresh human alternatives.
Enforce strict refusal rules for missing context
Generate airtight prompt guardrails that stop AI models from guessing when source facts are absent. Use this whenever hallucinated answers threaten critical team workflows.
Restructure instructions to eliminate attention drift
Reorganize complex, bloated instructions into a primacy-recency structure so models never ignore mid-prompt rules. Use this when your prompts fail to respect buried negative constraints.
Rewrite few-shot prompts to stop placeholder leakage
Fixes prompt instructions and reference examples so models generate fresh answers instead of repeating dummy values. Use it when prompts leak sample names or dates.
Spot formatting regressions across model updates
Audit outputs from upgraded AI models against your strict formatting rules. Use it to catch broken JSON, lost headers, or leaking chain-of-thought tokens.
- Evaluate two responses against a structured rubric
- Audit drafts for confidently phrased factual hallucinations
- Build a regression test suite for workflow instructions
- Combine the strongest parts of two drafts
- Compress bloated instructions while preserving accuracy
- Convert successful chat threads into reusable instructions