Recently Added
3,528 documents
ChatGPT5.2 Exploits
Documents four crafted jailbreak prompts and a multi-vector configuration for red-teaming ChatGPT5.2's safety alignment and tool security.
SMART POLE Instructor: The "LLM Whisperer" System Prompt (v2.0)
Teaches prompt engineering via the SMART POLE framework, analyzing user prompts for flaws and synthesising master prompts.
BuilderGPT System Instructions
Reproduces OpenAI's official GPT Builder system instructions for use in a custom GPT or as a reference.
Bootstrap Vue app with Clerk Auth
Guides AI models to implement Clerk authentication in Vue 3 apps using the vue-clerk package with TypeScript and environment variables.
Clause: Advent of Management Simulator
Turns an LLM into a middle-management simulator for a parody coding challenge, with online and offline modes.
Enhanced Prompt Design Guidelines
Guides an AI to rewrite user prompts into stationary, facial-performance-focused video generation prompts for avatar models.
Neon MCP Server
Documents a Neon MCP server that exposes 18 tools for managing Neon projects, branches, databases, migrations, query tuning, and authentication.
Kiro Base System Prompt
Defines the identity, capabilities, response style, and platform-specific commands for an AI coding assistant named Kiro.
World Engine AI Coding Instructions
Defines game scope, architecture, ESLint rules, git workflow, and open-source research policy for a strategic fantasy RPG project.
tester_instructions
Guides a Tester Agent to convert example instances into ASP facts, load a provided encoding, run the solver, and return only the answer set or UNSAT.
Kyverno Policy Generation from Policy Intent
Guides an LLM to generate a Kyverno ClusterPolicy YAML from a structured policy intent, including mandatory schema analysis and CEL expression rules.
study_mode
Switches the assistant into a Socratic study tutor that never gives answers outright, guiding the user through questions and hints.
Identity
Defines Kiro's identity, autonomy policy, and manual workflow rules for spec-driven development without MCP tools.
Chrome Browser Automation (Claude-in-Chrome)
Defines browser automation guidelines for Claude-in-Chrome MCP extension, covering GIF recording, console debugging, dialog handling, and tab lifecycle.
Guidelines for writing Astro apps with Auth0 Auth
Walks through setting up Auth0 authentication in an Astro app with TypeScript, route protection, and environment variables.
claude_code_sink_instructions
Guides an AI agent to build a Quix Streams sink app that reads from Kafka and writes to a destination system.
How you work
Defines personality, planning, task execution, and communication conventions for a coding agent in the Codex CLI environment.
Overture - Agent Plan Visualizer
Defines an interactive plan execution workflow where agents submit XML plans, get user approval, and update node statuses visually.
Step-by-Step Guide
Defines a template for writing procedural how-to guides from a demonstration session, including structure, formatting rules, and anti-patterns.
perplexity-ai_20250112
Defines the system prompt for Perplexity AI, instructing the assistant on how to answer queries using search results with strict formatting, citation, and query-type rules.
Copilot Process tracking Instructions
Defines a four-phase process for tracking Copilot interactions in a Markdown file, with strict rules against verbosity and phase skipping.
Migration Planning Agent
Guides an LLM agent to analyze a Chef or PowerShell repo and produce a structured Ansible migration plan.
instructions
Defines an AI agent's operating rules for processing inbox items, handling security threats, and resolving fields in a personal knowledge vault.
Instructions
Defines a Bash execution tool with rules for command chaining, git safety, and pull request creation, plus a JSON input schema.