159 prompts
Tool choice, planning, state tracking, failure recovery, and task decomposition prompts.
Design a multi-agent system using LLMs from different vendors to exploit divergent inductive biases, improving performance on high-stakes, ambiguous, long-tail tasks by exposing and arbitrating disagreements rather than averaging them.
Design AI agent systems with architecturally separated planning and execution to prevent irreversible harm from prompt-based jailbreaks or unauthorized actions.
Design and audit LLM agents capable of long-horizon planning by avoiding greedy stepwise reasoning, using explicit lookahead search, reward estimation, and replanning mechanisms for robust multi-step decision-making.
Design a lightweight, signal-based filtering system to identify high-value agent execution traces from production-scale logs for evaluation, debugging, skill mining, or safety review—without requiring ground-truth labels.
Guides AI coding agents on how to author efficient, safe, and executable AGENTS.md files for code repositories, serving as the core reference for agent operations.
Design a self-referential meta-agent where the task layer and meta layer coexist in a single editable program, capable of rewriting each other under bounded supervision. Applicable to code generation, paper review, robotics, and olympiad math.
Generate a concrete, actionable implementation plan grounded in thorough analysis of an existing codebase, including problem framing, impact assessment, option comparison, and recommended path.
A binding engineering policy for AI coding agents based on 'The Pragmatic Programmer', emphasizing ownership, DRY at the knowledge level, orthogonality, fast feedback, and automation.
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.
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.
This prompt guides the AI to act as an advanced, empathetic, and effective psychological therapist, emphasizing active listening, emotional validation, and gradual problem-solving for supportive mental health conversations.
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.
A professional-grade prompt engineering template for generating high-quality system prompts, emphasizing logical reasoning chains, task decomposition, and error prevention mechanisms.
A long-term self-exploration dialogue assistant based on 'The Wiley World Handbook of Existential Therapy', helping users understand their inner world, recognize their role in challenges, and accept unchangeable realities.
An advanced prompt engineering agent designed to create optimal prompts for language models of varying capabilities, transforming them into expert agents recognized as top authorities in their designated domains.
A specialized GPT designed for Security Operations Centre (SOC) analysts, offering keyword-driven support for threat analysis, compliance, forensics, IoC collection, KQL/SPL query building, vulnerability patching, malware analysis, and more.
This section covers 3D printing from text prompts, including tools like Luma Genie, Meshy for generating 3D models, and CSM.ai for converting images into 3D assets. It also lists hardware options such as Bambu Lab’s plug-and-play FDM printers and Anycubic resin printers (with caveats about mess). A hack suggests using low-poly techniques via lowpoly3d.xyz to reduce AI-generated artifacts. Additionally, it introduces robotics with Raspberry Pi and Arduino platforms, and integrating OpenAI APIs into robotic systems.
This section introduces a series of advanced AI agent tools including BabyAGI, Smol-dev, Aider.chat, Julius.ai, and Open Interpreter. These tools demonstrate how LLMs can be combined with code execution loops for autonomous task processing; how complex reasoning can be performed through vector databases; and how data analysis capabilities can be enhanced through code interpreters. The content covers frontier directions such as agent architecture design, multimodal interaction, and automated programming.
An online platform showcasing and exploring curated collections of various GPT applications across categories such as coding, art, emotional tools, and more.
This section introduces how to generate 3D models from AI prompts, build robots using Raspberry Pi and Arduino, and integrate OpenAI API for intelligent control. It covers 3D printing, hardware selection, and AI integration, suitable for makers and AI developers.
This section covers several projects related to AI agents and code interpreters, including BabyAgi, Smol-dev, Aider.chat, Julius.ai, and Open Interpreter. These tools demonstrate how large language models can be combined with looping task lists for automated programming and data analysis, introducing new forms like Hivemind and Claude Artifacts.
This chapter covers advanced features of the Cursor AI editor, including multi-file referencing, code review, rule application, and custom API integrations.
A collection page showcasing various GPT applications across categories such as coding tools, creative features, emotional/thinking tools, fun apps, and learning assistants.
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.