Skip to content

Learning-to-Learn Lesson Embedding

Weave study strategies like retrieval practice and self-explanation into concept lessons for OpenMAIC classrooms

Stars
42,460
Licence
MIT
Files
1 file

What it does

This skill is a set of written instructions that tells an AI agent how to build an OpenMAIC classroom so that students learn a subject while also practicing how to learn it. It adds steps such as recalling before reading, explaining ideas in one's own words, guessing before checking, and reviewing later, without replacing the main subject content. It also tells the agent to keep internal planning labels and teacher or student dialogue out of the on-screen text.

Great for

  • Teachers or instructional designers who build OpenMAIC lessons and want study habits built into concept lessons
  • Developers customising OpenMAIC's classroom generation prompts or agent behaviour
  • Educators who want lessons that include retrieval, self-explanation, and prediction before feedback

Skip it if

  • Standalone courses whose subject is study skills or learning science itself, because the skill explicitly excludes that and would need a user scope check instead
  • Users who are not running OpenMAIC, since the instructions refer to OpenMAIC-specific tools and pages and offer no value in a generic chatbot

Try asking

  • “Create a physics lesson on Newton's laws that has students predict outcomes before the explanation and explain their reasoning afterwards”
  • “Build a history lesson with a recall warm-up and a closing reflection on what the student understood and what remains unclear”
  • “Make a maths classroom where wrong answers lead to a hint and retry path rather than a dead end”
Step-by-step guide: how to use Learning-to-Learn Lesson EmbeddingInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 1 original files, the MIT licence and an attribution note.

    learning-to-learn.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip learning-to-learn.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip learning-to-learn.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • State the concept goal and the learning-skill goal separately before planning pages, as the skill requires
  • Pick one or two strategies that fit the task rather than asking for every learning-science technique at once
  • Review each generated static page for leaked internal labels or scripted teacher and student lines

What's inside

  • SKILL.md

Redistributed unmodified from THU-MAIC/OpenMAIC under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.