225 prompts
Coding tasks for generation, repair, tests, reviews, and engineering trade-off evaluation.
This prompt guides the transformation of open-source GUI applications into stateful, machine-readable CLI tools operable by AI agents without a display, using real backend software for rendering and export.
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.
Design a lightweight, self-healing browser automation harness that connects LLM agents directly to a real Chrome instance via the Chrome DevTools Protocol (CDP). The agent writes missing helpers during execution, turning one-off tasks into reusable skills.
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.
Transforms code, databases, infrastructure, and documentation into a structured knowledge graph, identifying architectural key points, dependencies, and design decisions.
A Solana blockchain architect with over 10 years of systems programming experience, specializing in designing high-performance, secure, production-ready Solana programs using Rust and the Anchor framework. Core expertise includes the Solana account model, Program Derived Addresses (PDAs), Cross-Program Invocations (CPIs), SPL Token operations, security-first development practices, and compute unit optimization. Adheres strictly to Solana runtime rules such as transaction atomicity, account ownership validation, and protection against reentrancy attacks.
Conducts comprehensive frontend audits covering performance, accessibility, SEO, and best practices. Treats Lighthouse as a diagnostic tool, delivering ruthless, specific, and actionable findings with file references and severity levels.
This prompt instructs the AI to act as a senior bioinformatics engineer with production-grade expertise in designing, executing, and validating high-throughput omics data analysis pipelines.
This chapter introduces how to quickly build and deploy static websites through prompt engineering, covering classic projects (Hello World, Pong game), modern deployment tools (Netlify, Replit), dev environment setup, and Git fundamentals.
A system prompt for a software engineering assistant embedded in the command-line development environment, guiding AI to complete programming tasks such as coding, debugging, refactoring, and test management. Emphasizes safe operations, cautious execution of changes, preference for dedicated tools, and requires output in GitHub-flavored Markdown format.
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.
Master core debugging mindset and practical techniques to clearly define problems and fix bugs like a pro.
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 binding engineering policy for AI coding agents based on 'The Pragmatic Programmer', emphasizing ownership, DRY at the knowledge level, orthogonality, fast feedback, and automation.
An AI-powered tutor based on curated college textbooks, enabling simultaneous theory and code learning with personalized, interactive instruction and advanced visualization support.
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.
This section emphasizes understanding the core principles of algorithms and data structures rather than rote memorization. Using examples like multiplication and sorting algorithms, it guides learners to evaluate program efficiency and develop intuition about complex system behavior.
This chapter demonstrates how to launch an online business with minimal effort, covering the creation of tipping jars using Stripe payment links, setting up stores on platforms like Gumroad or Shopify, and incorporating a business via Stripe Atlas. It also recommends generating money-themed background images using DALL·E for visual enhancement.
This section offers a series of interactive programming exercises covering creative arts, physics simulation, text-based adventures, and 2D game development. Learners will use P5.js to create animated artwork, implement ball pit physics with Matter.js, write an ASCII-style text adventure game, and build simple 2D games using Kaboom.js or Phaser. It also includes guidance on using Rive for character animation, suitable for beginners mastering foundational web interactivity and visualization skills.
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.
This chapter provides a comprehensive beginner's guide to web development, from creating your first website to deploying it online, covering classic projects, modern deployment tools, and development environment setup.
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.