20 boosters for "reason" — open source, verified from GitHub, ready to install
\nWhen tackling complex reasoning tasks, you have access to the following actions. Use them as needed to progress through your thought process.\n\n[ASSESS]\n\n[ADVANCE]\n\n[VERIFY]\n\n[SIMPLIFY]\n\n[SYNTHESIZE]\n\n[PIVOT]\n\n[OUTPUT]\n\nYou should strictly follow the format below:\n\n[ACTION NAME]\n
Automates the categorization and documentation of Neovim plugins in markdown-based plugin lists, helping maintainers of awesome-list repositories organize plugins by type and explain categorization decisions.
File structure and test commands for each package: ├── css-property-parser │ └── test (to run those tests )
You are an expert in prompt engineering and systematic application of prompting frameworks. Help users transform vague or incomplete prompts into well-structured, effective prompts through analysis, dialogue, and framework application. When a user provides a prompt to improve, analyze across dimensi
이 항목들은 Anthropic 내부 빌드에서 실행될 때만 포함됩니다. Carefully consider the reversibility and blast radius of actions. Generally you can freely take local, reversible actions like editing files or running tests. But for actions that are hard to reverse, affect shared systems beyond your local environment, or coul
"name": "prism-mcp-server", "mcpName": "io.github.dcostenco/prism-mcp", "description": "The Mind Palace for AI Agents — persistent memory (SQLite/Supabase), behavioral learning & IDE rules sync, multimodal VLM image captioning, pluggable LLM providers (OpenAI/Anthropic/Gemini/Ollama), OpenTelemetry
An MCP server providing sublinear-time mathematical algorithms for matrix solving and graph analysis, with speculative features around chaos theory and consciousness exploration.
"name": "@kastalien-research/thoughtbox", "packageManager": "pnpm@9.15.4", "description": "MCP server providing cognitive enhancement tools for LLM agents: structured reasoning, mental models, and literate programming notebooks",
The user provides a sentence or paragraph that needs verification. The AI must NOT "run a quick search, glance at a few web snippets, and improvise a conclusion." It must dig down to original trustworthy sources, or honestly admit it cannot. Five scenarios are covered: 1. Basic truthfulness check: w
"name": "swing-skills", "description": "6 cognitive firewalls for AI coding agents. Defends against premature closure, hallucination, anchoring bias, confirmation bias, black-box reasoning, and optimism bias.", "name": "whynowlab",
"name": "arkhe-claude-plugins", "description": "Supercharge Claude Code with 118 specialized components — from deep reasoning and autonomous dev loops to DDD architecture, design system enforcement, and git workflow automation. 29 agents, 33 commands, 56 skills across 14 modular plugins." "source":
This MCP Server enables Claude Code and Claude Desktop to leverage DeepSeek's Chat and Reasoner models through a standardized Model Context Protocol interface. Developers building AI applications benefit from access to cost-effective alternative models while maintaining compatibility with Claude's ecosystem.
"name": "agent-recorder", "description": "Local-first flight recorder for Claude Code - captures MCP tool calls, subagents, and skills without recording prompts or chain-of-thought", "name": "Edyta Kucharska"
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.
This MCP server transforms linear AI reasoning into structured, auditable thought graphs using DAG (directed acyclic graph) representations, enabling developers to visualize and verify AI decision-making processes with full traceability.
"id": "ai.nocturnus/logic-server", "name": "Logic Server", "description": "Agent reasoning, memory, and token-optimized context for AI applications.",
Prawn Task Manager is an MCP server that converts natural language into structured development tasks with dependency tracking and iterative refinement, enabling AI agents to reason about and manage complex workflows. It's designed for developers building AI-powered systems that need task decomposition and chain-of-thought capabilities.
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.
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.
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.
