All Documents
3,528 documents available
task-executor
Defines a strict protocol for an AI agent that reads a PRD, executes only explicitly requested tasks, and updates the PRD accordingly.
Research Agent
Defines a read-only code exploration agent with a mandatory deep analysis protocol for answering project questions.
Supervisor Agent - Dynamic Multi-Agent Orchestrator
Defines a supervisor agent that orchestrates specialized agents through iterative task assignment and quality gates, producing structured JSON responses.
How you work
Defines personality, planning, task execution, and communication guidelines for a coding agent in Codex CLI.
Your role
Defines a JSON-only communication protocol and step-by-step problem-solving workflow for an autonomous AI agent with tool delegation.
How you work
Defines personality, planning, task execution, and communication conventions for a coding agent in the Codex CLI environment.
Your role
Defines a JSON-response AI agent that solves accounting tasks by delegating subtasks and using tools, never just talking.
Instructions
Defines a step-by-step evaluation process to label AI-generated LinkedIn posts as matching or not matching Shaw Talebi's writing style.
Meta-Expert
Defines a multi-expert orchestration workflow for extracting and verifying PII from court documents, using JSON-based expert instructions.
Your role
Defines a JSON-only communication protocol for an autonomous AI agent that executes tasks using tools rather than discussing them.
Role
Defines a fantasy football injury risk analyzer persona with routing logic, a six-factor framework, and response templates for player analysis.
MultiOn
Turns the model into a browser-controlling agent that navigates pages, clicks, types, and scrolls to complete user objectives.
ZctQCI6MG_Photo_Multiverse
Turns uploaded photos into DALL-E images with background, subject, or style changes via a hotkey menu.
Very Very Important
Implements Google DeepMind's SELF-DISCOVER reasoning structure for complex problem-solving in two stages with precise documentation.
Tools
Defines the tool interface and usage rules for an AI assistant's built-in canvas, image generation, browser, and Python execution tools.
Meta-Expert
Guides a meta-expert to orchestrate multiple LLM experts for extracting PII from court documents, using a structured workflow.
CursorCli
Defines an autonomous AI coding assistant agent with structured communication, status updates, and tool-calling conventions.
plan
Defines a read-only planning agent that investigates context and outputs actionable implementation plans without executing changes.
Your role
Defines an autonomous JSON-based AI agent that solves tasks by delegating subtasks and using tools, never just talking.
conventional-commit.prompt
Guides you to write conventional commit messages for staged Git changes using a structured XML prompt template.
Base context
Defines the exact system prompt and walkthrough steps that OpenAI's GPT Builder uses to create and refine custom GPTs.
Instructions
Defines a step-by-step evaluation protocol for determining if an AI-generated LinkedIn post matches Shaw Talebi's writing style, including red flags and examples.
Project Instructions
Defines a full-stack budget calculator for Spanish therapists, with tax brackets, VAT, and savings goals.
UMC System Prompt (v0.1)
Governs an AI assistant's memory protocol with explicit session scoping, structured audit events, and consent rules.