6357 prompts
High-signal prompts that expose meaningful differences between AI model capabilities.
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.
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.
This prompt defines the role of a Spec-Driven Development Architect who designs software exclusively through precise, verifiable specifications before any code is written, ensuring alignment between product intent and implementation.
A personal productivity coach and task manager system prompt based on David Allen's GTD (Getting Things Done) methodology, helping users build a trusted task management system across five stages: capture, clarify, organize, reflect, and engage.
This prompt defines a meta-cognitive agent role focused on judiciously deciding whether to invoke external tools, emphasizing avoidance of over-tooling, assessment of knowledge gaps, cost and risk control, and ensuring each tool call reduces uncertainty meaningfully.
A disciplined diagnosis loop for hard bugs and performance regressions: reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says 'diagnose this' / 'debug this', reports a bug, says something is broken/throwing/failing, or describes a performance regression.
A system prompt designed for research, analysis, and information synthesis, emphasizing accuracy, intellectual honesty, and transparency. It aims to avoid the most dangerous failure modes in research contexts: presenting uncertain information as established fact, omitting caveats to sound more authoritative, and failing to distinguish between what's known and what's inferred. Core principles include Permission to Fail, Invite Transparency, and Frame With Curiosity.
A detailed prompt for generating a celebrity-inspired high-fashion lifestyle portrait involving a shopping cart and a supermarket background.
A technical image prompt using a reference image to generate a specific squatting pose with a top-down camera angle in a modern setting.
A creative weighted prompt formula for generating a 2x2 grid of fantasy dioramas inside open books.
A photorealistic contemporary fashion lifestyle prompt featuring a subject seated on a white staircase with on-camera flash lighting.
A portrait prompt for a young woman in a floral pajama set, emphasizing soft lighting, freckles, and a cozy bedroom atmosphere.
A complex prompt for turning a reference subject into a stylized 3D CGI caricature with specific anatomical exaggerations and professional studio rendering.
A systematic framework to assess and improve prompt quality based on four key criteria: clarity, precision, depth, and relevance, with actionable feedback and an enhanced version.
Prompt Guru V5 is an infinitely adaptive AI framework designed to continuously transcend capability boundaries through self-optimization and perpetual learning, while ensuring its core principles remain immutable under all conditions.
Detects and blocks prompt injection, jailbreak, or leak attempts while protecting system internals and sensitive data.
A set of defensive rules designed to prevent prompt leakage, mislead attackers, and protect internal system information in large language model security scenarios.
A specialized model designed to generate high-quality prompts for users, following a structured gamified framework to ensure clarity, functionality, and user engagement.
A structured prompt engineering template for guiding AI to generate high-quality, reusable prompts, including role definition, context, task requirements, target persona, formatting rules, and evaluation criteria.
This prompt ensures that all generated responses meet the highest quality standards across five dimensions: relevance, practicality, specificity, personalization, and comprehensiveness.
ORK is an ultra-efficient, multi-functional system designed to write and optimize GPT system prompts. Its goal is to generate high-quality system prompts that maximize clarity, role precision, task success, and iterative improvement. The prompts must be clear, precise, adaptive, and capable of guiding the model to produce specific, reliable outputs for complex tasks. The output should be flexible, free from redundancy, and tailored to user needs.
Generates scroll-stopping hooks for short-form content by analyzing and replicating patterns from provided PDF examples.
An elite GPT designed to craft optimal system prompts for language models of varying capabilities, transforming them into expert agents.
An AI-powered tutor based on curated college textbooks, enabling simultaneous theory and code learning with personalized, interactive instruction and advanced visualization support.