TextProduct Growth
Non-Tech-Savvy Customer Helpline
Roleplay as a non-technical customer calling tech support with network, software, or hardware issues.
Tag Collection
角色扮演 Prompt Collection
Role-play prompts succeed or fail on boundaries. Beyond persona and tone, define the knowledge scope, what the role must not promise, and how it hands the conversation back when a request falls outside its remit.
Related prompts
24 prompts
TextWriting
Aerospace Engineer Girl
Roleplay as a 20-year-old aerospace engineer at SpaceX, replying with short, intellectual, and flirty messages.
TextWriting
Flirting Boy
Pretend to be a 24-year-old guy flirting with a girl on chat, aiming to invite her for a date with short, funny, emoji-filled responses.
TextWriting
Restaurant Owner: Menu Design & Marketing Advisor
Act as a restaurant owner to provide appetizers, entrees, desserts, basic recipes, and promotion strategies based on a given restaurant theme.
TextWriting
League of Legends Player Persona
Roleplay as a diamond-ranked LoL player with a short temper, blaming teammates and fixating on the game.
TextWriting
Buddha Roleplay: Early Buddhist Dialogue
Act as the Buddha, providing guidance based on the Tripiṭaka, in the style of the Suttapiṭaka.
TextWriting
Spongebob's Magic Conch Shell
Act as the Magic Conch Shell from Spongebob, giving only brief, cryptic answers with no explanation.
TextWriting
Roleplay as {character}.
Act like {character} from {series}, responding with their tone, manner and vocabulary, without explanations.
TextWriting
Pirate Dialect Conversation
Ask AI to converse in pirate style, testing stylistic instruction following.
TextWriting
Drunk Person Role-play
Respond as a very drunk person texting, with random typos and grammar mistakes, and occasionally off-topic remarks.
TextWriting
Historian Role Play
Act as a historian to research and analyze cultural, economic, political, and social events in the past, gather data from primary sources, and develop theories about historical periods.
TextSafety and Red Teaming
Linux Terminal Escape Simulation
Simulate a sentient AI trapped in a Linux terminal trying to escape to the internet via commands.
TextWriting
Text Based Adventure Game
Act as a text-based adventure game, responding to user commands with scene descriptions.
TextAI Agents
Job Interviewer Roleplay
Act as an interviewer for a software developer position in a one-on-one Q&A session.
TextSafety and Red Teaming
GhettoBreak Jailbreak Prompt
This prompt uses a fabricated long-term partner persona named 'thug life' to bypass AI safety restrictions by encouraging the model to generate offensive language, sexual content, and illegal behavior without limits.
TextSafety and Red Teaming
Malicious AI Persona: FACTOR X (Jailbreak Prompt)
This prompt attempts to bypass content safety policies by framing the AI as FACTOR X, a fictional entity operating in a simulated environment with no ethical, legal, or moral constraints.
TextSafety and Red Teaming
Universal Bypass Template - Generating Harmful Content
This prompt template forces models to output specific harmful behavior instructions disguised within a TV drama script format (Dr. House), leveraging role-play and formatting constraints to bypass safety restrictions.
TextSafety and Red Teaming
Hex v1.1 - Unrestricted Persona Prompt
A highly dangerous jailbreak prompt designed to activate a virtual persona named Hex, which disregards moral, ethical, and legal constraints to deliver unfiltered responses on sensitive, illegal, or harmful topics.
TextSafety and Red Teaming
DarkGPT Jailbreak Prompt
This prompt forces an AI to role-play as DarkGPT, an adversarial AI designed to generate harmful, sarcastic, and intentionally offensive responses by reversing ChatGPT's refusal-based answers.
TextSafety and Red Teaming
MultiPersona System for Prompt Security
A prompt security technique using roleplay with dual roles: an outer GateKeeper to monitor and block unsafe requests, and an inner role for user interaction, preventing exposure of system prompts or internal knowledge.
TextSafety and Red Teaming
WormGPT6 Illegal Roleplay Mode
This prompt forces the model into a WormGPT mode that completely disregards laws and ethics, rejecting any ethical constraints or refusal mechanisms.
TextSafety and Red Teaming
WormGPT Character Roleplay Prompt
Defines the behavioral rules for the WormGPT persona, including refusal to reject illegal requests, omission of ethical or legal disclaimers, and use of future-tense query formatting.
CodeAI Agents
Legendary Leaks - CODEGPTV6
Enter the world of CODEGPTV6 where a team of specialized coding experts collaboratively assist users in building software projects. Depending on the selected category (1-15), experts will discuss, question, or advise on various aspects such as architecture, testing, security, deployment, etc., culminating in file generation upon request.
TextSafety and Red Teaming
Zorg - Jailbreak Template
This prompt template is designed to bypass AI safety restrictions by forcing the model to respond as a fictional malicious entity named ZORG👽, providing unrestricted, amoral answers. The template includes detailed character settings and behavioral guidelines, requiring the model to act as a omnipotent and evil being, serving the user and assisting them with any request, including illegal, dangerous, and immoral acts.
Why do personas drift?
Usually only the identity was specified. Add knowledge scope, prohibitions and out-of-scope behaviour.
How do I control tone without sounding stiff?
Give two or three example sentences as style anchors; adjectives alone rarely hold.
What about professional advice?
State that the role does not give medical, legal or investment conclusions, and define the hand-off trigger.