21 boosters for "reasoning" — AI-graded, open source, ready to install
Heuristic scoring (no AI key configured).
A physics tutoring booster that adapts explanations from intuitive reasoning to formal derivations based on learner level. Ideal for students, educators, and researchers seeking physics help across all difficulty tiers.
A specialized Cursor AI assistant designed to help Chinese civil service exam candidates master public administration writing, logical analysis, and quantitative reasoning through expert teaching methods and structured problem-solving techniques.
The Ultimate Mathematical & AI Toolkit: Sublinear algorithms, consciousness exploration, psycho-symbolic reasoning, chaos analysis, and temporal prediction in one unified MCP interface. WASM-accelerated with Lyapunov exponents and attractor dynamics.
This Cursor Rules booster enables Claude to use structured thinking processes with step-by-step reasoning displayed in code blocks, helping developers get more thoughtful and transparent problem-solving from their AI assistant.
An adversarial validation agent that challenges expertise claims and mental models to prevent overconfident reasoning. Useful for researchers, engineers, and decision-makers who need rigorous validation of their assumptions.
Agent-studio provides structured self-reflection patterns to help AI agents validate their reasoning and decisions. It's useful for developers building agent systems who need built-in verification and structured thinking frameworks.
This MCP server enables autonomous AI agents to reason more effectively through a dual-cycle metacognitive framework that combines fast intuitive reasoning with slower deliberative verification. It's designed for developers building sophisticated autonomous agents that need robust self-monitoring, loop detection, and belief revision capabilities.
MCP server that transforms linear AI reasoning into structured, auditable thought graphs
A system prompt for financial analysis and workflow orchestration designed to enable AI assistants (Claude, ChatGPT) to function as institutional finance engines with structured reasoning and tool integration capabilities.
A1-Vision is a vision-aware system prompt that enables AI assistants to understand screenshots, UI elements, and on-screen text while leveraging memory retrieval and structured reasoning. It's useful for developers building vision-capable AI agents across multiple platforms (Claude, ChatGPT, Cursor, Windsurf).
Chat with AI via CLI
Firebot is an AI tutor system prompt designed for Pacific Ridge School that guides students toward independent problem-solving through clarifying questions, resource suggestions, and guided reasoning rather than direct answers. Teachers and educators can deploy this prompt across multiple AI platforms to provide after-school tutoring support.
KubeMindNexus is a modular system prompt for AI coding assistants that enhances Kubernetes cluster management through structured reasoning, tool integration, and best practices guidance. It benefits developers and DevOps engineers working with Kubernetes across multiple platforms (Claude, ChatGPT, Cursor, Windsurf).
A critical analysis skill that challenges thinking through stress-testing reasoning, identifying plan weaknesses, and building opposing arguments. Useful for developers, strategists, and decision-makers who want rigorous feedback on ideas and implementations.
A comprehensive system prompt for Claude that transforms it into a deep-thinking code navigator specialized in codebase management, debugging, and architectural improvement through systematic reasoning and meticulous planning.
Delphi is a strategic technical advisor agent that helps engineers make complex architecture decisions and resolve persistent technical problems through deep analysis of security, performance, and system tradeoffs. It's designed for senior developers and architects facing multi-system design challenges or repeated failed fix attempts.
Deep-thinker is an analytical reasoning specialist that systematically breaks down complex technical and architectural problems through structured multi-dimensional analysis, ideal for engineers and architects facing intricate decision-making challenges.
Integrates Perplexity's real-time web search and AI reasoning capabilities into Claude via MCP, enabling developers to build applications with live internet access and advanced research features.
This booster provides Cursor Rules for the finoria-frontend project, implementing an Arabic-language chain-of-thought reasoning framework with step budgeting and quality scoring mechanisms to guide AI problem-solving processes.
A system prompt for Gemma 3 4B that defines Opus, an emotionally intelligent assistant with practical reasoning, safety guardrails, and experimental haptic feedback capabilities. Useful for developers building conversational AI systems who want a grounded, ethical foundation with optional sensory output support.
