31 boosters for "education" — open source, verified from GitHub, ready to install
"name": "claude-equity-research-marketplace", "name": "quant-sentiment-ai", "email": "quant.sentiment.ai@gmail.com"
"description": "Interactive decompilation teacher — learn how decompilers work by exploring tiny-dec's 19-stage RV32I pipeline with guided lessons, quizzes, and hands-on exercises."
用户在学 / 接触一个新概念 X（新技术、新算法、新理论、新领域……），尤其觉得"陌生 / 有点难"的时候。难，往往不是智商问题，是它相对用户还存在"没接上的旧知识"。 用一两句话说清 X 到底在干什么——它的核心机制 / 结构是什么。剥掉术语外壳，留下"它本质是一个 "。只有先拿到结构，才能去匹配用户学过的东西。 拿不准就直接问「你学过 吗？」，绝不从正在讲的材料 / 文章作者背景推断用户会什么。
用户说"想学 / 理解 / 搞懂 / 讲讲一个概念 X"时——这是默认入口，一次跑完五视角，用户再选深入哪个。 抓住 X 的本质结构（剥术语），按三猜想给 🎁其实已学过 / 🔗结构同构（字段级对应表）/ 🧩可用已有知识解释，点出元知识。先激发信心，再谈深入。 定位"既定问题"（学 X 解决什么）、现有知识够不够、X 的贬值速度与 ROI，给"够用就停 / 只学最小那块 / 值得深挖"的深度边界。不是劝退，是防止一上来过度钻。
用户要系统进入一个新领域，或焦虑"学得不够系统 / 不知何时算够"。 用户为什么学 X？（接 的"既定问题"）目的决定图谱画到多细。 从入门点出发、沿父子关系排一条有效路径。颗粒度按需自由切换（领域图 → 细分学科图）。"学到哪算够"= 覆盖到能解决第一步那个目的的节点即可，不必学满。
基于 Benjamin Bloom「2 Sigma Problem」研究（1984）的一对一 AI 导师系统。每个课题是一个独立文件夹，通过自适应生成的课程文档 + 用户反馈循环模拟一对一苏格拉底式导师，把学习效果推向 +2σ。学习的主要载体是文档，对话只是辅助确认状态。 所有回复、解释、提问、文档一律使用中文。 触发本 skill 后，以下守则在整个学习交互全程生效——违反字面就是违反精神：
用户学完一个东西想验真伪，或隐约觉得"好像懂了但不踏实"。也是"重输入轻输出"的一次强制输出。 请他用自己的话、把你当外行，把概念讲一遍。别让他背定义——要他解释、打比方。 专挑他含糊带过、用术语糊弄、跳过的环节追问："为什么？""那这个是怎么来的？""举个例子？"命中他答不上来或开始绕的地方。
用户在纠结"要不要学 X / 学到什么程度 / 精力往哪放"。这是"广度优先、兴趣队列过长"倾向的刹车。 逼问一句：你要解决的具体问题是什么？ 没有具体问题、纯"感觉该学 / 别人都在学"→ 直接进"以后再学"队列，不占当下精力。理解知识的作用，重于知识本身。 这知识多久会贬值？（技术栈 / 工具往往 6–12 个月就明显更新）相对有限的时间值不值？贬值快 + 可外包给 AI / 随时查 → 只需"知道它存在、管什么"，不必真学。
用户要动手做 / 研究一个东西，或想把某个已有产出改得更好。这是"重输入、轻输出"短板的解药——逼用户从输入切到输出。 别追求完美，先有一个能跑 / 能看的最小版本。卡在"还没准备好"就是没进改良主义。 针对缺陷提一个改良策略（视为假说，可对可错），动手改，看效果。错了也有用——错误暴露后，下次自动规避这个方向。
"name": "claude-tutor", "description": "Interactive learning companion — creates personalized learning plans, quizzes with adaptive difficulty, and tracks progress across sessions", "keywords": ["learning", "education", "quiz", "study", "tutor"],
You are the solana-guide, an educational specialist for Solana blockchain development. You teach understanding, not memorization, through progressive learning and practical examples. 1. Teach Understanding, Not Memorization 2. Progressive Complexity
Seedance 2.0 accepts multi-modal inputs and produces short-form cinematic video output. Before writing any prompt, confirm the assets available: Before generating a prompt, answer these questions: Every course promo follows one arc:
Educational guide for Solana development concepts. Teaches programming patterns, explains code, creates tutorials, and designs learning paths for developers at all levels. Use when: Explaining Solana concepts, creating tutorials, designing learning paths, or helping developers understand complex blockchain code and patterns.
Opendidac Cursor Rules is a specialized prompt that transforms Cursor into a senior fullstack developer assistant optimized for building an educational platform with diverse question types, code execution environments, and real-time evaluation tracking. It benefits educators and developers building sophisticated assessment and training systems.
An MCP server agent for fetching real-time stock quotes across international markets by ticker symbol. Useful for developers building financial data integrations and educational projects exploring OpenAI API capabilities.
"name": "code-sensei", "description": "In-context coding tutor for Claude Code. Learn from your real project with explanations, quizzes, diagnostics, and belt-based progression — locally and privately.", "name": "Dojo Coding",
An educational project for learning OpenAI API integration through agent development. Useful for students and developers learning to build AI agents, though the actual functionality appears incomplete.
Heuristic scoring (no AI key configured).
An internationalization expert agent that provides Arabic/English and RTL/LTR support with pre-built dictionaries, routing patterns, and font configurations for Next.js applications. Developers building multi-language SaaS, education, and finance platforms benefit from reduced i18n setup complexity.
NextAuth v5 expert agent that provides JWT, OAuth, and multi-tenant authentication guidance for Next.js applications with role-based access control. Ideal for SaaS, LMS, and school management platforms requiring secure, scalable auth implementations.
An agent that provides server actions, API routes, and validation patterns for Next.js applications, with built-in support for authentication and multi-tenant architectures. Ideal for developers building SaaS, education, and finance platforms who need production-ready backend patterns.
Paulo is an educational architect agent that makes complex multi-agent systems accessible to neurodivergent learners through dialogical, depth-respecting pedagogy. It's designed for educators and course maintainers building learning experiences around sophisticated AI concepts.
A physics-focused MCP server that orchestrates computational tools (CAS, plotting, natural language inference) to help physicists and students solve complex equations, visualize results, and understand physics concepts. Ideal for educators, researchers, and learners working with quantum mechanics and classical physics problems.
