teach

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

Updated Aug 20, 2026
One-click install
npx skills add https://github.com/bittlinkm/claude-setup --skill teach-bittlinkm
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: teach
Source: https://github.com/bittlinkm/claude-setup/tree/main/skills/teach
Command: npx skills add https://github.com/bittlinkm/claude-setup --skill teach-bittlinkm

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Learning a new topic with an AI assistant is usually stateless: every session starts from zero, prior knowledge gets re-taught, and there is no record of progress. This Skill turns a directory into a persistent teaching workspace that tracks your mission, what you have learned, and which resources to trust across multiple sessions. ## Core Features & Use Cases - Stateful learning workspace: Maintains MISSION.md, GLOSSARY.md, RESOURCES.md, and sequentially numbered learning records so every session builds on the last and targets your zone of proximal development. - HTML lesson generation: Produces short, self-contained, beautifully typeset lessons saved to ./lessons/, built from reusable components in ./assets/ and grounded in cited high-trust sources. - Retention-focused pedagogy: Designs lessons around retrieval practice, spacing, and interleaving to build long-term storage strength rather than illusory fluency. - Use Case: You want to learn strength training over several weeks. The Skill interviews you to write a mission, curates trusted resources, generates an interactive HTML lesson on progressive overload, and records what you demonstrated so the next session teaches the right next thing. ## Quick Start Ask the assistant 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 assistant to learn a new topic over multiple sessions?

Invoke the teach skill in a dedicated directory, which becomes a persistent learning workspace. It records your mission, learning records, and glossary so each session picks up where the last one ended instead of starting over.

How does the teach skill decide what to teach next?

It reads your learning records and MISSION.md to estimate your zone of proximal development, then teaches the most relevant concept that is challenging but achievable. You can also specify exactly what you want to learn.

What files does the teaching workspace create?

The workspace contains MISSION.md for your goal, RESOURCES.md for curated sources, GLOSSARY.md for terminology, numbered learning records in ./learning-records/, HTML lessons in ./lessons/, reusable components in ./assets/, and a NOTES.md scratchpad.

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

No. The skill explicitly distrusts parametric knowledge and builds RESOURCES.md from high-trust external sources first. Lessons cite these primary sources, and wisdom-level questions are delegated to real communities like forums or local groups.

What format are the lessons generated in?

Lessons are single self-contained HTML files saved to ./lessons/ with incrementing numbered filenames. They use clean Tufte-style typography, link to other lessons and reference documents, and include interactive quizzes with immediate feedback.

When should I not use a structured teaching workspace?

It is overkill for one-off factual questions or quick lookups that need no continuity. The workspace is designed for multi-session skill building where tracking progress, misconceptions, and mission changes provides real value.