Agent skill

Feynman Learning Cycle Classroom

by THU-MAIC in THU-MAIC/OpenMAIC

Turns a concept or lesson material into a Feynman-style classroom where learners explain first, find their smallest gap, rebuild the idea and apply it somewhere new.

MITAuto-check passedEducation

SKILL.md written in Chinese; this summary is our English description.

Install Feynman Learning Cycle Classroom

skills CLI
$ npx skills add THU-MAIC/OpenMAIC --skill feynman-learning -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install THU-MAIC/OpenMAIC feynman-learning --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/THU-MAIC/OpenMAIC.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/agent-runtime/feynman-learning .claude/skills/feynman-learning && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
feynman-learning
GitHub stars
40k
Token cost
~955 tokens
SKILL.md length
201 words
Files
1
Skills in repo
25
Repo updated
First seen
Licence
MIT

At a glance

Turns a concept or lesson material into a Feynman-style classroom where learners explain first, find their smallest gap, rebuild the idea and apply it somewhere new.

  • Works in 8 steps: 先讲给外行听(interactive) → 找到最小卡点(interactive 或 slide) → 用问题把因果链补出来(interactive,或以 discussion… → …
  • Designing a lesson where students explain a concept before being taught it
  • SKILL.md covers 适用范围, 核心原则, 页面内容红线 and 先确定三个约束, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Written in Chinese, this skill restructures any subject into one full Feynman learning cycle built around the learner's own explanation instead of the textbook. The learner explains first, the smallest gap is located, questions rebuild the cause-and-effect chain, the explanation is repeated, jargon is stripped out, an analogy is stress-tested, and the idea is moved into an unfamiliar situation. The run ends with a Feynman learning record and goals for the next round. It loads /stage-design first and adds only the teaching method, page briefs and interaction rhythm on top of it.

The rules include collecting the learner's explanation before showing any standard definition, fixing only one or two gaps at a time, asking before telling, and using teacher-uploaded material as a fact source rather than a first-page answer key. The cycle maps onto seven to nine pages, mostly interactive tasks, and student-facing titles are phrased as actions rather than method names. A concept boundary, an audience and the teacher's constraints are settled before planning. It is not meant for lessons about the Feynman technique itself, and /learning-to-learn, /style-clone and /pptx-import cover neighboring cases.

When your agent uses it

  • Designing a lesson where students explain a concept before being taught it
  • Converting a slide deck or lesson plan into a teach-back activity
  • Walking a learner through gap-finding, analogy testing and transfer to a new case

Example prompts

  • “Build a Feynman-style class on how vaccines train the immune system for middle school students.”
  • “Turn my photosynthesis slide deck into a teach-back lesson.”
  • “Make a classroom where learners explain recursion, then drop the jargon and try again.”

Requirements

  • The /stage-design skill, which this skill loads first

Workflow steps

8 steps, taken from the step headings in SKILL.md.

  1. 先讲给外行听(interactive)
  2. 找到最小卡点(interactive 或 slide)
  3. 用问题把因果链补出来(interactive,或以 discussion action 收尾的 slide)
  4. 再讲一遍(interactive)
  5. 去掉刚才用过的术语(interactive)
  6. 拆穿自己的类比(interactive)
  7. 换一个陌生情境(interactive 或 quiz)
  8. 合成费曼学习记录(slide 或 interactive)

What it can do on your machine

Read from SKILL.md and the folder at commit 32f5923. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Feynman Learning Cycle Classroom loads about 955 tokens when it runs. Until then it costs about 127 tokens; SKILL.md has 201 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~127
When it runs · the whole SKILL.md, loaded when a task matches
~955

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from THU-MAIC/OpenMAIC at commit 32f5923, republished under its MIT licence (© THU-MAIC). 201 words, ~955 tokens.

Download SKILL.mdSave it as .claude/skills/feynman-learning/SKILL.md (or your agent's skills folder).
name
feynman-learning
description
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.
title
费曼学习法

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 或 /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-back、Jargon Challenge、Transfer、v1/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

按 /stage-design 的顺序创建课堂:create_stage → set_roster → 按批准计划逐页 generate_scene → list_scenes → read_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。

© THU-MAIC, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/agent-runtime/feynman-learning of THU-MAIC/OpenMAIC.

Open the folder on GitHubat commit 32f5923

Compare with similar skills

Feynman Learning Cycle Classroom next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Feynman Learning Cycle Classroom compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Feynman Learning Cycle Classroom this skillTHU-MAIC/OpenMAIC40k—~955Automated safety check: PassMIT
AI Engineering Project Tutorrohitg00/ai-engineering-from-scratch66k—~1.6kAutomated safety check: PassMIT
Hung-Yi Lee Teaching Stylevoidful/hung-yi-lee-skill1.3k—~13kAutomated safety check: PassNone
AI Engineering Course Guiderohitg00/ai-engineering-from-scratch66k—~1.7kAutomated safety check: PassMIT
Claude Academy Guideanthropics/skills180k3 repos~1.9kAutomated safety check: PassApache-2.0
Learndair-ai/dair-academy-plugins6142 repos~1.3kAutomated safety check: PassMIT

Similar skills

  • AI Engineering Project Tutor

    rohitg00/ai-engineering-from-scratch

    Tutors a learner through one stage of a hands-on AI engineering project per session: lesson, prediction, code, grader run and reflection, with hints but never full solutions.

    66k GitHub stars~1.6k tokensUpdated 2 days ago
    EducationAuto-check passed
  • Hung-Yi Lee Teaching Style

    voidful/hung-yi-lee-skill

    Explains machine learning, LLMs, AI agents and speech modeling in a Hung-Yi Lee-inspired teaching style, drawing on a knowledge base built from his lectures and research references.

    1.3k GitHub stars~13k tokensUpdated 1 mo ago
    EducationAuto-check passed
  • AI Engineering Course Guide

    rohitg00/ai-engineering-from-scratch

    Routes a topic, question or bug to the exact lessons in the AI Engineering from Scratch curriculum and suggests the next command to run.

    66k GitHub stars~1.7k tokensUpdated 2 days ago
    EducationAuto-check passed
  • Claude Academy Guide

    anthropics/skills

    Official

    Adds a matching Claude Academy course, tutorial or use case to the end of an answer about learning to use Claude, but only when the match is strong.

    180k GitHub starsUsed in 3 repos~1.9k tokens
    EducationAuto-check passed
  • Learn

    dair-ai/dair-academy-plugins

    Help a user learn a topic through adaptive tutoring, lesson planning, practice, retrieval checks, explanations, study guides, or exercises.

    614 GitHub starsUsed in 2 repos~1.3k tokens
    EducationAuto-check passed
  • Explains a concept, formula or mechanism in plain Chinese so the reader can recognize it, follow the reasoning, adjust it when conditions change and apply it to new cases.

    7.5k GitHub stars~632 tokensUpdated 2 days ago
    EducationAuto-check passed

More from THU-MAIC/OpenMAIC

All 25 skills in this repo
  • Guides setup, classroom generation and secondary development for OpenMAIC, the multi-agent interactive classroom, one confirmed phase at a time.

    40k GitHub stars~1.7k tokensUpdated today
    Auto-check: notes
  • Designs a Chinese K-12 classroom for one OpenMAIC stage around the core-literacy model, using authentic tasks, performance assessment and observable evidence.

    40k GitHub stars~2.4k tokensUpdated today
    Auto-check passed
  • Maps the structure of an OpenMAIC stage document so an agent can find the right path, read it and patch quizzes, widgets, actions and project pages without guessing.

    40k GitHub stars~2.4k tokensUpdated today
    Auto-check passed
  • Designs a review-and-practice lesson around an independent first attempt, targeted feedback, supported practice, a fresh independent check and a next step.

    40k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Derives a reusable personal skill for course-making from a representative sample of the user's own past classrooms and chat history, confirmed with them before saving.

    40k GitHub stars~678 tokensUpdated today
    Auto-check passed
  • Curriculum Planner

    THU-MAIC/OpenMAIC

    Plans a multi-classroom series such as a seven-day course, clarifies the brief in rounds, gets sign-off on the full lesson list, then builds each stage in a shared folder.

    40k GitHub stars~2.8k tokensUpdated today
    Auto-check passed

Categories

Questions about Feynman Learning Cycle Classroom

What does Feynman Learning Cycle Classroom do?

Turns a concept or lesson material into a Feynman-style classroom where learners explain first, find their smallest gap, rebuild the idea and apply it somewhere new. Written in Chinese, this skill restructures any subject into one full Feynman learning cycle built around the learner's own explanation instead of the textbook. The learner explains first, the smallest gap is located, questions rebuild the cause-and-effect chain, the explanation is repeated, jargon is stripped out, an analogy is stress-tested, and the idea is moved into an unfamiliar situation.

When should I use Feynman Learning Cycle Classroom?

Feynman Learning Cycle Classroom fits situations like: designing a lesson where students explain a concept before being taught it; converting a slide deck or lesson plan into a teach-back activity; walking a learner through gap-finding, analogy testing and transfer to a new case.

How do I install Feynman Learning Cycle Classroom in Claude Code?

Run `npx skills add THU-MAIC/OpenMAIC --skill feynman-learning -a claude-code`. Or copy the skill folder (skills/agent-runtime/feynman-learning in THU-MAIC/OpenMAIC) into .claude/skills/feynman-learning in your project. Claude Code loads it when a task matches its description.

How do I install Feynman Learning Cycle Classroom in Codex?

Run `npx skills add THU-MAIC/OpenMAIC --skill feynman-learning -a codex`. Or copy the skill folder (skills/agent-runtime/feynman-learning in THU-MAIC/OpenMAIC) into .agents/skills/feynman-learning in your project. Codex loads it when a task matches its description.

Can I use Feynman Learning Cycle Classroom in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add THU-MAIC/OpenMAIC --skill feynman-learning -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/feynman-learning, .gemini/skills/feynman-learning, .github/skills/feynman-learning and .opencode/skills/feynman-learning in your project.

What does Feynman Learning Cycle Classroom need to run?

SKILL.md names no scripts, command-line tools or credentials: Feynman Learning Cycle Classroom is instructions for the agent only. Our summary lists: The /stage-design skill, which this skill loads first.

Does Feynman Learning Cycle Classroom access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Feynman Learning Cycle Classroom safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Feynman Learning Cycle Classroom use?

Feynman Learning Cycle Classroom is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Feynman Learning Cycle Classroom use?

About 955 tokens (SKILL.md is roughly 3.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Feynman Learning Cycle Classroom?

Skills that share tags, products or a category with Feynman Learning Cycle Classroom: AI Engineering Project Tutor (rohitg00/ai-engineering-from-scratch, 66k stars), Hung-Yi Lee Teaching Style (voidful/hung-yi-lee-skill, 1.3k stars), AI Engineering Course Guide (rohitg00/ai-engineering-from-scratch, 66k stars) and Claude Academy Guide (anthropics/skills, 180k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Feynman Learning Cycle Classroom?

THU-MAIC (a GitHub organization) maintains it in THU-MAIC/OpenMAIC, which has 40,120 GitHub stars. The repository holds 25 skills in this directory. The repository was last updated on October 8, 2026.

Source: THU-MAIC/OpenMAIC on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.