← Back to Skills Marketplace
li-evan

Learn Crossover

by Evan · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
43
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install learn-crossover
Description
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...
README (SKILL.md)

跨界原则学习法(learn-crossover)

核心信条:真正的快速学会,其实是「你已经学过了」。 跨界匹配的是结构,不是名词。

何时用

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"。

流程

第一步:抓住 X 的本质结构(不堆术语)

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。

第二步:弄清用户已经会什么

主动询问,建立"用户已掌握知识"的清单:

  • 问用户的背景:学过哪些相关领域、做过什么项目、熟悉哪些工具 / 理论
  • 只采纳对话中用户亲口确认学过的知识
  • 目的:找出与 X 结构同构、或能解释 X 的旧知识

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

第三步:按"跨界三猜想"组织输出(核心)

  1. 🎁 你其实已经学过(换了名字) —— 最高优先。X 是否就是用户已知的 Y 换了个领域名称?(如 导数 = 梯度 = 变化率)。命中就直接说"你已经会了,它只是改名叫 X"。
  2. 🔗 结构同构(非常像) —— 给出用户学过的 Z 与 X 的字段级对应表(A↔a、B↔b……),并明确标出哪里相同、哪里不同。铁律:不一样归不一样,但相似部分就是学习杠杆,别因为"严格不同"就不用它。
  3. 🧩 可被解释(用已有知识解释) —— 用用户已掌握的 W 把 X 讲通。

第四步:点出元知识

X 体现了哪个反复出现的底层模式?(分治、自举 / bootstrap、阻尼-负反馈、探索 vs 应用、量变质变、控制变量、状态机……)。告诉用户"这个模式你在 也见过",把 X 挂到他的元知识网上。

第五步:落点

一句话收尾,降低学习恐惧 + 指明剩下要新学的最小部分:

"所以 X 你已经会了 ___ 部分,真正全新、需要从头学的只有 ___。"

注意

⚠️ 铁律·只用确证的已会知识:判断用户「已经会什么」只能用他确证学过的知识(亲口确认或可靠背景);严禁把「正在讲的材料 / 文章作者背景 / 对话里别人的知识」当成用户会的。拿不准 → 直接问「⚠️ 你学过 ___ 吗?」,绝不替他假设。(最常见的翻车点:把材料作者的背景错安到学习者头上,整段跨界作废。)

  • 宁可多举具体例子(案例驱动),别给抽象框架。
  • 结构对应要给到字段级映射表,不要泛泛说"它们很像"。
  • 不确定某个跨界连接是否成立时,标注"这是个待验证的类比"——提出假说,允许被推翻。
  • 同族 skill:要"该不该学"用 learn-occam,要"系统建图"用 learn-graph,要"动手迭代"用 learn-prototype,要"自查懂没懂"用 learn-feynman
Usage Guidance
Install this if you want a Chinese-language skill for learning new topics through analogies to knowledge you already have. Be aware it may activate for broad learning questions, and non-Chinese users may find its instructions hard to review or use.
Capability Assessment
Purpose & Capability
The stated purpose is to help users understand unfamiliar concepts by mapping them to knowledge the user has confirmed; the artifact contains only instructional Markdown and the behavior fits that purpose.
Instruction Scope
The trigger examples are fairly broad for learning and explanation requests, and the skill is written in Chinese, so it may route some generic learning requests or be less usable for non-Chinese readers; this is a routing/accessibility concern, not a security concern.
Install Mechanism
The package contains a single SKILL.md file with no executable scripts, dependencies, package install steps, or hidden install behavior.
Credentials
The skill does not ask to read local files, run commands, use network access, access accounts, mutate user data, or index private content.
Persistence & Privilege
No persistence, background workers, privilege escalation, credential handling, or session/profile access is requested or implied.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install learn-crossover
  3. After installation, invoke the skill by name or use /learn-crossover
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
learn-crossover v1.0.0 - Initial release of the "跨界原则学习法(learn-crossover)" skill. - Helps users quickly grasp new concepts by leveraging knowledge they already have, through structural mapping and analogy. - Guides users to match new knowledge with familiar concepts, avoid jargon overload, and build understanding via concrete field-level comparisons. - Emphasizes using only user-confirmed knowledge as a basis for analogies. - Includes a step-by-step process for identifying core structure, querying user background, mapping similarities, highlighting meta-knowledge patterns, and clarifying what is truly new to learn.
Metadata
Slug learn-crossover
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Learn Crossover?

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... It is an AI Agent Skill for Claude Code / OpenClaw, with 43 downloads so far.

How do I install Learn Crossover?

Run "/install learn-crossover" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Learn Crossover free?

Yes, Learn Crossover is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Learn Crossover support?

Learn Crossover is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Learn Crossover?

It is built and maintained by Evan (@li-evan); the current version is v1.0.0.

💬 Comments