@li-evan

learn-feynman applies feynman technique to validate conceptual understanding. user explains a topic in plain language while the skill probes ambiguities, identifies knowledge gaps, and determines whether understanding is closed-loop or needs prerequisite work.

learn-occam helps users decide whether to learn something new by validating concrete problems against existing knowledge, assessing knowledge decay and roi, then recommending study, skip, or minimal viable learning.

learn-prototype guides users through iterative prototyping by forcing a minimal working version first, then coaching them to identify flaws, hypothesize improvements, test, and extract method patterns. core loop is self-directed problem discovery over coached solutions.

learn-deep sequences five learning perspectives (crossover, occam, graph, prototype, feynman) to give users a full-pass introduction to any concept, then guides them toward deeper specialization based on their context and goals.

Use when 用户想以一对一苏格拉底导师的方式系统学习一个课题——开一门新课、推进课题的下一篇、提交学习反馈或说「我读完了」、或整理/查看学习日志。基于 Bloom 2 Sigma 的交互式学习系统。触发词：开个文件夹学X、我想学X、帮我学X、继续、下一篇、我读完了、整理学习、查看学习日志、interacti...

当用户学习或接触一个新概念/新技术/新算法/新领域时使用（尤其感到陌生或有点难时）。用「跨界原则」拿用户已掌握的知识快速撬动新知识——指出他其实已经学过的同一个东西（换了名字）、结构同构的旧知识、能解释新知识的已有知识，并点出新概念体现的跨领域元知识模式。让「学新东西」变成「发现你已经会了一半」。触发场景：学 X...

当用户要系统学一个新领域、不知道从哪入手、或担心「学得不够系统」时使用。用「知识图谱学习法」和用户一起构建该领域的概念/用途/父子节点图谱（自己建图的过程本身就是学习），标出复用价值最高的节点和「从常识就能入门的点」，给出有效学习路径并回答「学到哪算够」。触发场景：系统学 X 领域、从哪开始学、学得不系统、想要...

A-Share Multi-Dimensional Quantitative Analysis MCP Server - broker research reports, AI news analysis, and stock comprehensive analysis

A-Share Multi-Dimensional Quantitative Analysis MCP Server - broker research reports, AI news analysis, and stock comprehensive analysis