14 boosters for "thinking" — open source, verified from GitHub, ready to install
Analyzes ANY input to find, improve, or create the right skill. Start with least privilege (, , , , ). Only add higher-risk tools when explicitly required:
"name": "research-companion", "description": "Strategic research thinking agents — idea evaluation, project triage, and structured brainstorming inspired by Carlini's research methodology", "name": "Andre Huang",
A practical guide to Supervised Fine-Tuning using SFTTrainer and Unsloth optimizations, enabling developers to efficiently adapt pre-trained LLMs for instruction-following with 2x faster training. Ideal for ML engineers building custom instruction-tuned models and reasoning systems.
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.
nano-spec is a lightweight, four-document specification methodology designed to help developers plan and document AI-assisted tasks in Windsurf through structured README, TODO, technical docs, and progress logs. It benefits teams wanting rapid, spec-driven development without heavyweight documentation overhead.
"description": "Cognitive brainstorming protocol for Claude Code. Structures thinking through GROUND (problem discovery) -> EXPLORE (divergent) -> DECIDE (convergent) -> STRESS (stress-test) -> SHIP (artifacts) phases. Includes domain skills for technical architecture and conceptual work.", "name":
Leghis Smart Thinking is an MCP server that enables fast retrieval and lookup of Smart-Thinking memories, allowing users to quickly find relevant context and fetch complete entries by ID. Developers and knowledge workers benefit from rapid access to structured memory/note systems integrated with Claude.
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.
Markdown Agents is a framework for defining AI agents using simple markdown files with YAML frontmatter, enabling version-controlled, portable agent configuration across Claude Code and Desktop. Developers benefit from reduced cognitive load, git-native memory tracking, and predictive AI collaboration without session amnesia.
John is a Product Manager agent that generates comprehensive PRDs and strategic product documentation by translating business vision into actionable development requirements. Product teams, startup founders, and business stakeholders benefit from structured, professional product planning without needing extensive PM expertise.
Heuristic scoring (no AI key configured).
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.
Ultra-thinker is a comprehensive analytical agent that applies rigorous 7-phase structured reasoning to complex problems across multiple disciplines. It's useful for professionals, researchers, and decision-makers who need deep, systematic analysis on high-stakes questions.
