teach

Creates stateful teaching workspaces with HTML lessons, learning records, and curated resources.

1|Updated Jul 2, 2026
One-click install
npx skills add https://github.com/filippolmt/skills --skill teach-filippolmt
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: teach
Source: https://github.com/filippolmt/skills/tree/main/skills/teach
Command: npx skills add https://github.com/filippolmt/skills --skill teach-filippolmt

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Learning a new topic with an AI assistant is usually stateless — every session starts from zero, re-teaches what you already know, and produces throwaway chat answers instead of durable study material. This Skill turns a directory into a persistent teaching workspace that tracks your mission, progress, and reference material across sessions. ## Core Features & Use Cases - Stateful learning workspace: Maintains MISSION.md, RESOURCES.md, GLOSSARY.md, and numbered learning records so each session builds on demonstrated understanding rather than guesswork. - HTML lesson generation: Produces short, self-contained, beautifully typeset lessons in ./lessons/ with quizzes, citations to trusted sources, and reusable components in ./assets/. - Zone of proximal development targeting: Reads learning records to pick the next lesson that challenges you just enough, using retrieval practice, spacing, and interleaving for long-term retention. - Use Case: You want to learn strength training over several weeks. The Skill interviews you to write a mission, curates high-trust resources, then generates a sequence of interactive HTML lessons — each one recorded so future sessions never repeat what you have mastered. ## Quick Start Ask the agent to teach you a topic, for example: "Teach me the fundamentals of strength training in this workspace."

Frequently Asked Questions about teach

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I use an AI agent to learn a new topic over multiple sessions?

Invoke the teach skill in a dedicated directory and state what you want to learn. It creates a workspace with a mission file, learning records, and HTML lessons, so each new session resumes from your demonstrated understanding instead of starting over.

How does the teach skill decide what to teach next?

It reads the numbered learning records in ./learning-records/ to calculate your zone of proximal development, then picks the most relevant next topic tied to your mission. Lessons use retrieval practice, spacing, and interleaving to build long-term retention.

What files does the teaching workspace create?

The workspace contains MISSION.md, RESOURCES.md, GLOSSARY.md, NOTES.md, numbered learning records in ./learning-records/, self-contained HTML lessons in ./lessons/, reusable components in ./assets/, and reference HTML documents in ./reference/.

Can I use this skill for one-off questions instead of long-term learning?

It is designed for stateful, multi-session learning and has model invocation disabled, so you must invoke it explicitly. For quick one-off factual questions, a normal conversation without the workspace overhead is a better fit.

Does the teach skill rely on the AI's built-in knowledge?

No. The skill explicitly distrusts parametric knowledge and prioritizes building RESOURCES.md with high-trust books, articles, and communities. Lessons cite these external sources, and wisdom-level questions are delegated to real communities.