teach

Create interactive HTML lessons and track learning progress in a structured teaching workspace.

Updated Jun 26, 2026
One-click install
npx skills add https://github.com/dulltackle/kangkang-skills --skill teach-dulltackle
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: teach
Source: https://github.com/dulltackle/kangkang-skills/tree/main/teach
Command: npx skills add https://github.com/dulltackle/kangkang-skills --skill teach-dulltackle

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Learning a new topic over multiple sessions loses continuity: prior knowledge gets re-taught, goals drift, and nothing persists between conversations. This Skill turns a directory into a stateful teaching workspace that tracks your mission, learning records, glossary, and resources so every session builds on the last. ## Core Features & Use Cases - Stateful Learning Workspace: Maintains MISSION.md, RESOURCES.md, GLOSSARY.md, and numbered learning records to capture what you know and why you are learning it. - Interactive HTML Lessons: Generates short, self-contained lessons in ./lessons/ with quizzes, feedback loops, citations, and links to reusable components in ./assets/. - Zone of Proximal Development Targeting: Reads your learning records to pick the next lesson that challenges you just enough, using retrieval practice, spacing, and interleaving. - Use Case: You want to learn strength training over several weeks. The Skill interviews you to define a concrete mission, curates trusted resources, then produces a sequence of printable lessons and reference sheets that adapt as your understanding deepens. ## Quick Start Ask the agent to teach you a topic, for example: teach me the basics 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 learn a new topic across multiple sessions with an AI?

Use a teaching workspace that persists state between sessions. The Skill stores your mission, learning records, glossary, and resources as Markdown files, so each new session reads your history and teaches the next concept in your zone of proximal development instead of starting over.

How are the lessons in this teaching workspace structured?

Each lesson is a single self-contained HTML file saved to ./lessons/ with an incrementing number. It teaches one tightly-scoped concept, includes interactive quizzes with immediate feedback, cites trusted sources, links to other lessons and reference documents, and recommends a primary source to read.

What files does the teaching workspace create and maintain?

The workspace maintains MISSION.md for your learning goal, RESOURCES.md for curated trusted sources, GLOSSARY.md for compressed term definitions, NOTES.md for preferences, numbered learning records in ./learning-records/, lessons in ./lessons/, and reusable components in ./assets/.

How does the Skill decide what to teach next?

It reads your learning records to find your zone of proximal development, then picks the most relevant concept tied to your mission. Learning records are only written when you demonstrate genuine understanding, disclose prior knowledge, or correct a misconception.

When should I not use a stateful teaching workspace?

Avoid it for one-off factual questions or quick lookups where a single answer suffices. The workspace is designed for multi-session skill building; its overhead of missions, records, and lesson files only pays off when learning spans many sessions.