Feynman Learning logo

Feynman Learning

OrganizationPopular
THU-MAIC
feynman-learning

Turn any concept, lesson, slide deck, or source material into a Feynman learning cycle in which learners explain first, expose the smallest gap, rebuild the explanation through Socratic prompts, strip jargon, stress-test analogies, and transfer the idea to a new context. Use when the user asks for teach-back, learning by explaining, or a Feynman-style classroom. Do not use when the Feynman technique itself is merely the lesson topic or when study strategy should remain a parallel goal.

Overview

PublisherTHU-MAIC
RepositoryOpenMAIC
Skill namefeynman-learning
Stars
37.6K
Forks
5.9K
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by THU-MAIC on GitHub. Read the source before you install it.

Installation

Install the Feynman Learning AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/THU-MAIC/OpenMAIC.git /tmp/OpenMAIC
mkdir -p .claude/skills
cp -r /tmp/OpenMAIC/skills/agent-runtime/feynman-learning .claude/skills/feynman-learning
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Feynman Learning in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Feynman Learning on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Feynman Learning is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

费曼学习法

把任何学科内容重构为一轮完整的费曼学习循环。核心对象不是教材,而是学习者当前的解释。学习者必须经历“先解释、暴露缺口、自己重建、换种说法、迁移应用”,最终留下《费曼学习记录》和下一轮目标。

先加载 /stage-design,遵循它的新课堂创建、roster、逐页持久化和音频验收流程。本 Skill 只规定教学法、页面 brief 和互动节奏。

适用范围

用于以下请求:

  • 用费曼法学习或教授某个具体概念;
  • 把课件、教案、视频或材料改造成费曼式学习活动;
  • 设计一节以 teach-back、自我解释、追问和迁移为核心的课堂。

不要用于:

  • 以“费曼学习法是什么”为知识主线的科普课;
  • 只想把学习策略作为概念课的平行目标,此时使用 /learning-to-learn
  • 品牌风格复制或 PPT 原样导入,此时使用 /style-clone/pptx-import。导入材料仍可作为本 Skill 的事实来源。

核心原则

  1. 学习者先讲,AI 后介入。 在展示权威定义、教材解释或标准流程之前,先收集学习者自己的解释。没有初始解释,就没有费曼循环。
  2. 一次只修最小缺口。 从解释中找出当前最关键的 1–2 个断点,不把整本教材一次性砸给学习者。
  3. 追问优先于代答。 先用最少的问题帮助学习者自己补全因果链。只有多次追问仍卡住且用户允许时,才提供必要事实或支架。
  4. 理解必须经得住改写和迁移。 能背术语不等于理解;学习者要能去掉术语、说明类比边界,并在陌生情境中重新解释。
  5. 材料只提供事实,不抢占初始解释。 教师上传的材料用于确定概念边界和校验事实,不作为第一页直接展示的标准答案。

页面内容红线

以下词属于规划语言,只能写在对话、brief 或 roster 设计中,不得作为学生可见的标题、标签或栏目:Teach-backJargon ChallengeTransferv1/v2/v3概念定界缺口诊断类比破坏测试费曼循环概念变化轨迹

学生可见标题要写成可执行动作,例如:

  • “先把它讲给一个没学过的人听”;
  • “你讲到哪一步卡住了?”;
  • “换掉这几个词,再讲一遍”;
  • “这个类比会在哪里失效?”;
  • “到一个新情境里试试”。

老师和学生代理的口述、追问与讨论放进 narration / actions,不写成“老师说”“小白说”的静态页面正文。

先确定三个约束

页面计划前明确:

  1. concept boundary:本轮只解释哪个可学习的核心概念,明确不覆盖什么;
  2. audience:学习者要讲给谁听,例如没学过该概念的初中生或外行;
  3. teacher constraints:学习深度,以及追问失败后是否允许 AI 给出答案。

只有请求不足以确定这些约束时,才用 ask_user 补齐。

费曼循环与页面映射

循环可以落在 7–9 页中。不要机械追求页数,但以下证据链不能缺失。第一页应把概念边界和第一次讲解合并成一个 interactive 任务,避免在初始解释前泄露标准内容。

1. 先讲给外行听(interactive)

  • 简短说明本轮概念边界和目标听众,不给标准定义;
  • 要求学习者不查资料,用自己的话完成第一次解释;
  • 优先提供文本或语音输入。若组件无法保存自由输入,要求学习者先写下或说出自己的版本,并让老师旁白提醒其保留,供后续对照。

2. 找到最小卡点(interactive 或 slide)

  • 把初始解释拆成必要概念要素;
  • 只定位 1–2 个最关键的跳步、术语替代、错误因果或遗漏;
  • 让学习者自己判断“我卡在哪里”,不要只展示 AI 评分。

概念检查表写进 brief,并转成学生能回答的问题,不要渲染“缺口 1”“缺口 2”等内部标签。

3. 用问题把因果链补出来(interactive,或以 discussion action 收尾的 slide)

  • 每个问题只针对一个已定位缺口;
  • 小白代理持续追问“为什么”“如果条件改变会怎样”;
  • brief 写明该问题针对什么、出现什么理解证据后停止;
  • 未满足 teacher constraints 前不要直接给答案。

4. 再讲一遍(interactive)

  • 给出少量结构提示,要求学习者生成第二版解释;
  • 提示必须指向因果结构,不复述标准答案;
  • 保留第一版与第二版的可比较差异,供最终学习记录使用。

5. 去掉刚才用过的术语(interactive)

  • 从学习者第二版解释中选择其真正使用过的术语;
  • 要求不用这些词再解释一次,或给出能拆穿机械背诵的反例;
  • 不要预先展示一张与学习者表达无关的术语黑名单。

6. 拆穿自己的类比(interactive)

  • 让学习者提出一个类比,再分别说明“哪里像”“哪里不像”;
  • 至少逼出一个类比失效点;
  • 页面不预先给出全部失效点,由代理追问帮助学习者发现。

7. 换一个陌生情境(interactive 或 quiz)

  • 把概念迁移到没有在前面使用过的新情境;
  • 可限制使用概念名称,迫使学习者依靠机制解释;
  • 最好加入一个反例、边界条件或假设改变,检验其是否真的掌握结构。

8. 合成费曼学习记录(slide 或 interactive)

最终记录使用学习者自己的话,至少包含:

  1. 我现在能解释什么;
  2. 我一开始怎样理解;
  3. 我发现自己卡在哪里;
  4. 我的新版解释;
  5. 我的类比及其失效点;
  6. 我能解决的新问题;
  7. 我仍然不能解释什么,以及下一轮学习目标。

它不是“你学会了”的庆祝页,而是下一轮循环的起点。

Roster

  • 老师 / 教练:守住先解释后反馈的顺序,决定何时提供支架,把讨论拉回核心概念。
  • 小白 / 初学者代理:作为解释对象,真实地表示听不懂并追问因果,是主要的缺口探测器。
  • 可选的错误概念代理:呈现一个常见但错误的解释,帮助学习者辨析;不要让它提前说出标准答案。

搭建与验收

/stage-design 的顺序创建课堂:create_stageset_roster → 按批准计划逐页 generate_scenelist_scenesread_stage 验收。页面需要补写或重建旁白时使用 generate_actions,并确保最终 speech actions 都有音频;修改旁白文字后调用 generate_tts

完成前逐页检查:

  • 初始解释发生在任何标准内容之前;
  • 每页能说明它外化了什么、暴露了什么或重建了什么;
  • 诊断只聚焦 1–2 个最小缺口;
  • 追问没有偷换成直接代答;
  • 术语剥离针对学习者自己使用过的词;
  • 类比测试至少产生一个失效点;
  • 迁移离开原始案例并包含边界或反例;
  • 静态页面没有规划标签、教学法黑话或角色台词;
  • 最终记录同时包含已理解内容、仍有缺口和下一轮目标。

能力边界

生成式页面无法对学习者实时输入的每一句话动态诊断。要如实使用三条路径:

  1. interactive 收集解释,并用检查点支持学习者自检;
  2. roster 代理与老师旁白模拟苏格拉底追问;
  3. 真正需要逐句诊断与持续保存解释版本时,在工作台对话中运行循环,以课堂页面作为活动骨架。

不要把静态或预生成页面描述成能够实时判分。

Frequently asked questions

What does the Feynman Learning AI skill do?

Turn any concept, lesson, slide deck, or source material into a Feynman learning cycle in which learners explain first, expose the smallest gap, rebuild the explanation through Socratic prompts, strip jargon, stress-test analogies, and transfer the idea to a new context. Use when the user asks for teach-back, learning by explaining, or a Feynman-style classroom. Do not use when the Feynman technique itself is merely the lesson topic or when study strategy should remain a parallel goal.

Why use Feynman Learning on TypingMind?

Because you install it once and use it with any model. Feynman Learning is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Feynman Learning in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/THU-MAIC/OpenMAIC/tree/main/skills/agent-runtime/feynman-learning. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Feynman Learning?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Feynman Learning?

As many as you like. As long as a model supports skills, you can use Feynman Learning with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Feynman Learning AI skill free?

Yes. It is published on GitHub by THU-MAIC under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇