Agent skill

Learning to Learn (OpenMAIC)

by THU-MAIC in THU-MAIC/OpenMAIC

A Chinese-language skill that embeds learning strategies like retrieval practice and self-explanation as a parallel goal inside an OpenMAIC subject lesson, without making study skills the topic.

MITAuto-check passedEducation

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

Install Learning to Learn (OpenMAIC)

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

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

GitHub CLI
$ gh skill install THU-MAIC/OpenMAIC learning-to-learn --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/learning-to-learn .claude/skills/learning-to-learn && 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
learning-to-learn
GitHub stars
40k
Token cost
~502 tokens
SKILL.md length
63 words
Files
1
Skills in repo
25
Repo updated
First seen
Licence
MIT

At a glance

A Chinese-language skill that embeds learning strategies like retrieval practice and self-explanation as a parallel goal inside an OpenMAIC subject lesson, without making study skills the topic.

  • Works in 2 steps: 概念目标:学生最终要理解、解释或迁移什么; → 学会学习目标:学生要练习哪一种学习动作,以及什么行为能证明它发生了。
  • Adding retrieval practice or self-explanation into a subject lesson without making it the lesson's topic
  • SKILL.md covers 先声明平行目标, 两条内容红线, 四个嵌入点 and 多智能体的作用, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

The skill requires stating two goals before planning any page: a concept goal, what students should ultimately understand or transfer, and a learning-to-learn goal, which specific learning action students should practice and what observable behavior proves it happened. Each embedded strategy must be traceable back to the concept it serves, and strategies that cannot answer that are removed; the guidance favors one or two well-fitted strategies per lesson rather than listing the whole vocabulary of learning science.

Two content rules keep this invisible to students: internal planning labels such as learning seam or metacognition never appear as visible headings or body text, and teacher or student-agent dialogue stays in narration and actions, while static pages carry only concept points, questions, tasks and prompts phrased as concrete actions, such as writing an answer before checking it rather than naming retrieval practice.

Four embedding points structure where this happens: an opener that asks students to recall or predict before formal explanation, concept-building where a student explains the conclusion in their own words, hands-on interactive tasks where predicting or answering comes before feedback and mistakes lead to a retry path rather than a dead end, and a closing that covers what was understood, how it was learned, what remains uncertain and when to review again. A teacher agent models thinking before answering and a student agent models a realistic incomplete or wrong understanding for the learner to correct.

When your agent uses it

  • Adding retrieval practice or self-explanation into a subject lesson without making it the lesson's topic
  • Designing a lesson where students predict before seeing feedback
  • Building a closing sequence that covers both concept understanding and how it was learned

Example prompts

  • “帮我在这节光合作用课中加入检索练习和自我解释环节。”
  • “Design a predict-then-check interactive task for the Newton's laws lesson.”
  • “Write the lesson closing so students review both the concept and how they learned it.”

Requirements

  • The OpenMAIC stage-design classroom workflow

Workflow steps

2 steps, taken from the first numbered list in SKILL.md.

  1. 概念目标:学生最终要理解、解释或迁移什么;
  2. 学会学习目标:学生要练习哪一种学习动作,以及什么行为能证明它发生了。

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

Learning to Learn (OpenMAIC) loads about 502 tokens when it runs. Until then it costs about 109 tokens; SKILL.md has 63 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~109
When it runs · the whole SKILL.md, loaded when a task matches
~502

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). 63 words, ~502 tokens.

Download SKILL.mdSave it as .claude/skills/learning-to-learn/SKILL.md (or your agent's skills folder).
name
learning-to-learn
description
Infuse learning strategies and metacognition into a concept-centered OpenMAIC classroom as a parallel goal. Use when the user wants students to learn how to learn while studying a subject: retrieval practice, self-explanation, prediction before feedback, monitoring understanding, deliberate review, or productive failure. Do not use when learning science or study skills should be the standalone subject of the lesson.
title
学会学习(Learning to Learn)

学会学习(Learning to Learn)

把学习策略与元认知作为平行目标嵌入概念主课:不替换学科概念主线,而是改变学生如何经历、检查和巩固这些概念。

stage-design 仍然约束课堂的创建和持久化流程。如果同时使用 /understanding-by-design,先确定大概念、基本问题与表现性任务,再嵌入学习策略;如果同时使用 /social-emotional-learning,让两类平行目标服务同一概念任务,不要各自另起一条课程主线。

先声明平行目标

在页面计划前分别声明:

  1. 概念目标:学生最终要理解、解释或迁移什么;
  2. 学会学习目标:学生要练习哪一种学习动作,以及什么行为能证明它发生了。

每一个学习策略都要能回答“它在服务哪个概念理解”;答不出的嵌入删除。优先选择最贴合任务的 1–2 种策略,不要在一节课里罗列整套学习科学术语。

两条内容红线

  1. 规划标签不进页面:学习缝、元认知、教学意图、平行目标 等内部框架词只用于规划与 brief,不作为学生可见的标题、正文或栏目标签。
  2. 角色台词只走旁白:老师与学生代理的口述、示范和讨论发言放进 narration / actions;静态页面只承载概念要点、问题、任务与提示,不写“老师说”或“学生说”。

页面使用学生能立即执行的动作语言,而不是技术术语:

  • 检索练习:写成“别急着翻,先把答案写出来”;
  • 自我解释:写成“用自己的话给结论一个理由”;
  • 先预测后验证:写成“先猜一下,再看对不对”;
  • 间隔复习:写成“过几天再回来默一次”;
  • 监控理解:写成“你是真的懂,还是只是感觉懂了?”

只有当用户明确要求讲授某种学习方法本身时,才把对应术语作为学生要学的内容。

四个嵌入点

这些是页面规划锚点,不是页面标题,也不要求各自新增一页:

  1. 开场:正式讲解前,让学生先调取已有知识、做出初步判断或写下预测。
  2. 概念建立:得出结论后,让学生用自己的话解释一次,并追问“为什么”。学生代理可以示范不完整解释,再邀请学习者补充或质疑。
  3. 亲手做:在 interactive 中先预测或作答,再给反馈;错误要进入检查、补漏和重试路径,不能成为死路。
  4. 收束:同时收住“我理解了什么”“我是怎样学会的”“哪里还不确定”以及“之后如何再检索一次”。

多智能体的作用

  • 老师:示范先想再答、检查理解与定位缺口;认可“我卡住了”,再引导补漏。
  • 学生代理:呈现“感觉懂了但默不出来”、预测错误或解释不完整的真实状态,并邀请学习者判断、修正和迁移。

围绕方法和理解讨论,不评价人;老师及时把对话带回概念主线。

质量关口

  • 概念目标与学会学习目标分开声明。
  • 每个嵌入点都标明它服务的概念与可观察的学习动作。
  • 至少让学生实际经历一次主动回忆、自我解释或先预测后验证,而不是只听学习方法介绍。
  • 受挫与错误后保留反馈、补漏和重试路径。
  • 收束同时包含概念理解、学习过程反思与后续复习动作。
  • 逐页检查所有静态文字,不得出现内部规划标签或角色口述台词。
  • 不承诺“万能学习法”;需要比较研究证据时先核实来源。

边界

本 Skill 用于把学习策略嵌入学科概念课,不用于以学习方法或学习科学本身为内容主线的独立课程。若用户要把学习法做成第二条完整课程主线,先用 ask_user 确认范围。

© 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/learning-to-learn of THU-MAIC/OpenMAIC.

Open the folder on GitHubat commit 32f5923

Compare with similar skills

Learning to Learn (OpenMAIC) 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.

Learning to Learn (OpenMAIC) compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Learning to Learn (OpenMAIC) this skillTHU-MAIC/OpenMAIC40k—~502Automated safety check: PassMIT
Learndair-ai/dair-academy-plugins6142 repos~1.3kAutomated safety check: PassMIT
Matlab Plan Tutor Adoptionmatlab/agent-skills-playground181—~867Automated safety check: PassCustom licence
DeepTutor CLIHKUDS/DeepTutor41k—~2.8kAutomated safety check: PassApache-2.0
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

Similar skills

  • 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
  • Matlab Plan Tutor Adoption

    matlab/agent-skills-playground

    A skill your agent uses when an instructor asks for a MATLAB AI tutor setup guide, adoption guide, pilot plan, course-specific rollout, or recommended tutor configuration based on a learning…

    181 GitHub stars~867 tokensUpdated 28 days ago
    EducationAuto-check passed
  • DeepTutor CLI

    HKUDS/DeepTutor

    Teaches the agent to set up and run DeepTutor from the command line: chat and capabilities, knowledge bases, partners, memory, sessions, notebooks and the server or Web app.

    41k GitHub stars~2.8k tokensUpdated yesterday
    EducationAuto-check passed
  • 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
  • Claude Certification Tutor

    rohitg00/ai-engineering-from-scratch

    Guides a learner through one of four independent Claude certification tracks with onboarding, lessons, practice labs, mock exams and remediation.

    66k GitHub stars~3k 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 yesterday
    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 yesterday
    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 yesterday
    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 yesterday
    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 yesterday
    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 yesterday
    Auto-check passed

Categories

Questions about Learning to Learn (OpenMAIC)

What does Learning to Learn (OpenMAIC) do?

A Chinese-language skill that embeds learning strategies like retrieval practice and self-explanation as a parallel goal inside an OpenMAIC subject lesson, without making study skills the topic. The skill requires stating two goals before planning any page: a concept goal, what students should ultimately understand or transfer, and a learning-to-learn goal, which specific learning action students should practice and what observable behavior proves it happened. Each embedded strategy must be traceable back to the concept it serves, and strategies that cannot answer that are removed; the guidance favors one or two well-fitted strategies per lesson rather than listing the whole vocabulary of learning science.

When should I use Learning to Learn (OpenMAIC)?

Learning to Learn (OpenMAIC) fits situations like: adding retrieval practice or self-explanation into a subject lesson without making it the lesson's topic; designing a lesson where students predict before seeing feedback; building a closing sequence that covers both concept understanding and how it was learned.

How do I install Learning to Learn (OpenMAIC) in Claude Code?

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

How do I install Learning to Learn (OpenMAIC) in Codex?

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

Can I use Learning to Learn (OpenMAIC) 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 learning-to-learn -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/learning-to-learn, .gemini/skills/learning-to-learn, .github/skills/learning-to-learn and .opencode/skills/learning-to-learn in your project.

What does Learning to Learn (OpenMAIC) need to run?

SKILL.md names no scripts, command-line tools or credentials: Learning to Learn (OpenMAIC) is instructions for the agent only. Our summary lists: The OpenMAIC stage-design classroom workflow.

Does Learning to Learn (OpenMAIC) 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 Learning to Learn (OpenMAIC) 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 Learning to Learn (OpenMAIC) use?

Learning to Learn (OpenMAIC) 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 Learning to Learn (OpenMAIC) use?

About 502 tokens (SKILL.md is roughly 2k 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 Learning to Learn (OpenMAIC)?

Skills that share tags, products or a category with Learning to Learn (OpenMAIC): Learn (dair-ai/dair-academy-plugins, 614 stars), Matlab Plan Tutor Adoption (matlab/agent-skills-playground, 181 stars), DeepTutor CLI (HKUDS/DeepTutor, 41k stars) and AI Engineering Project Tutor (rohitg00/ai-engineering-from-scratch, 66k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Learning to Learn (OpenMAIC)?

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.