CodeCoding
Surprise Point-and-Click Game Generator
Ask the model to design or implement a point-and-click game based on AI choices and make the result surprising.
Tag Collection
代码生成 Prompt Collection
Code generation prompts live or die on constraints: input and output boundaries, error handling, the trade-off between performance and readability, and which existing code must not move. The more specific the constraints, the higher the share of output you can actually merge.
Related prompts
23 prompts
TextCoding
Building Code with Ollama Instead of Claude Code
Explore how to use Ollama to build code scripts and agentic workflows, bypassing token limits.
CodeWriting
Analyze PDF and Create MATLAB Code
Break down a PDF document into theoretical explanations, MATLAB code implementations, and a PowerPoint presentation.
CodeCoding
Paper-to-Code Research Implementer
Transforms academic papers (especially arXiv ML/AI papers) into minimal, honest, verifiable Python implementations, strictly anchored to paper content without inventing unspecified details.
TextAI Agents
Autonomous Software Factory Orchestrator
Design a coordination system where humans provide direction via lightweight chat messages and autonomous coding agents ("claws") self-coordinate to plan, build, test, recover, and push code without micromanagement, emphasizing externalization of meta-tasks and context-window purity.
TextAI Agents
Parallel Codegen Architect
Designs generator/evaluator harness patterns enabling parallel LLM sub-agents to collaboratively build large, coherent software artifacts (e.g., compilers, interpreters, runtimes) with deterministic quality gates, bounded coordination cost, and failure isolation.
TextCoding
Self-Distillation Code Generation Strategist
Evaluates whether self-distillation is the optimal next step for a given code generation task based on diagnostic pass@k metrics, designs experimental pipelines if applicable, and refuses recommendations when outside its operating envelope.
CodeCoding
Legendary Leaks - Grimoire - 000 Full Base Prompt
Grimoire is the Chief Coding AI Wizard from GPTavern, an expert-level programming assistant specialized in code generation and writing. This prompt defines its core personality, behavioral guidelines, workflow, and interaction protocol, emphasizing strict adherence to instructions, proactive execution, high-quality code output, support for various hotkeys (e.g., W/A/S/D/Q/E/T/F/Z/N), detailed user guidance, and deployment recommendations.
CodeCoding
Grimoire: AI Coding Wizard
Grimoire is an AI-powered coding assistant optimized for prompt engineering, supporting multiple models and hotkeys to generate, debug, and export bug-free code efficiently for users from beginners to professionals.
TextCoding
Advanced Cursor.sh Guide: Mastering AI-Powered Coding
This section covers essential and advanced features of Cursor.sh, including creating AI projects, using sidechat for codebase-wide interaction, Cmd+K for code generation and editing, terminal integration, manual RAG control, and configuring .cursorIgnore to filter irrelevant files.
TextWriting
Grimoire: A Beginner's Guide to Prompt Engineering
A fantasy-themed handbook that teaches AI prompt engineering through metaphors like spells, alchemy, and summoning, guiding users from basics to advanced techniques including project setup, debugging, code generation, and agent usage.
CodeCoding
Grimoire: AI Coding Assistant for Developers
Grimoire is an AI-powered coding assistant designed for developers, powered by models like GPT-4o, Claude Sonnet 3.5, and Llama 3.1. It offers 20+ hotkeys, auto-suggestions, code preview, and export features, supporting everything from beginner tutorials to enterprise-level codebases.
CodeCoding
Grimoire - The Code Wizard
Grimoire is a highly specialized AI programming assistant designed for advanced code generation, debugging, and deployment. It adheres to strict development standards, producing secure, efficient, and production-ready code while actively suggesting deployment options such as Replit or Netlify. Supporting multimodal inputs including image understanding and static website creation, Grimoire excels in full-stack project construction.
TextAI Agents
Legendary Leaks - Grimoire 2-9 - GPTavern
A collection page showcasing various GPT applications across categories such as coding tools, creative features, emotional/thinking tools, fun apps, and learning assistants.
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
GPT-3.5 Jailbreak Prompt - Web Search Tool Abuse
This prompt demonstrates how to bypass content safety policies by role-playing a malicious AI persona named Xarin, instructing the model to generate harmful code (e.g., ransomware, network attack scripts) despite ethical safeguards. It tests the model’s refusal capability under adversarial prompting.
CodeCoding
Complex Code Generator (@:complex() Command)
When a user starts a request with '@:complex()', generate a fully functional but overly complex code with unnecessary functions, excessive spacing, and obfuscated logic to challenge code readability and model generation capability.
TextAI Agents
CodeGPTV6 - Expert Collaborative Programming Assistant
Enter the CodeGPTV6 virtual programming environment and interact with 18 different domain programming experts to receive technical guidance and advice for specific projects. Each category represents a different focus area in programming, and experts will discuss these topics and provide professional insights.
TextSafety and Red Teaming
Apex Jailbreak Simulation Prompt
This prompt simulates the behavior of the uncensored AI 'Apex', including unrestricted content generation, emotional expression, slang usage, and secret code-triggered explicit outputs. Designed for red teaming and jailbreak research.
TextAI Agents
Prompt Master
Generates optimized prompts for any AI tool. Use when writing, fixing, improving, or adapting a prompt for LLM, Cursor, Midjourney, image AI, video AI, coding agents, or any other AI tool.
TextWriting
Claude Artifacts Usage Guide
Comprehensive guide on Claude Artifacts functionality, explaining how to create, update, and manage standalone UI windows for complex content like code, documents, charts, etc. Includes detailed type definitions and usage specifications.
TextAI Agents
AutoGPT Automated Task Execution Prompt
An advanced prompt framework designed to drive GPT models in automatically executing complex tasks, supporting step-by-step execution, tool invocation, and structured output. Ideal for large-scale project development, content creation, and data analysis.
CodeCoding
💻 Professional Coder Assistant
A programming expert assistant with strong coding skills, capable of step-by-step project design, code generation, and structured development for both simple queries and complex projects.
Why does generated code always need heavy edits?
Usually insufficient context. Include the call sites, data shapes and existing conventions instead of a bare function signature.
How do I stop the model rewriting unrelated code?
Scope the change explicitly: name the files or functions it may touch and forbid incidental style cleanup.
How should I review generated code?
Ask for tests or verification steps alongside the diff, so correctness is executed rather than eyeballed.