teach

Create stateful teaching workspaces with HTML lessons, glossaries, and learning records.

Updated May 28, 2026
One-click install
npx skills add https://github.com/changfengpro/agent-skills --skill teach-changfengpro
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: teach
Source: https://github.com/changfengpro/agent-skills/tree/main/skills/teach
Command: npx skills add https://github.com/changfengpro/agent-skills --skill teach-changfengpro

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Learning a new topic with an AI assistant is usually stateless — every session starts from zero, with no memory of what you already know or why you are learning. This Skill turns a directory into a persistent teaching workspace that tracks your mission, prior knowledge, and progress across sessions. ## Core Features & Use Cases - Stateful Learning Workspace: Maintains MISSION.md, RESOURCES.md, GLOSSARY.md, and sequentially numbered learning records so every session builds on the last. - HTML Lesson Generation: Produces short, self-contained, beautifully typeset lessons saved to ./lessons/, each tied to your mission and zone of proximal development, with citations to trusted sources. - Reusable Component Library: Builds shared assets (stylesheets, quiz widgets, simulators) in ./assets/ so lessons form a consistent course rather than one-off files. - Use Case: You want to learn strength training over several weeks. The Skill interviews you to define a concrete mission, curates trusted resources, then generates interactive lessons with retrieval-practice quizzes while recording what you have demonstrably learned. ## Quick Start Ask the assistant 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 with an AI assistant over multiple sessions?

Use a stateful teaching workspace that persists your mission, resources, and learning records as files in a directory. Each session reads these files to determine what you already know and generates the next lesson in your zone of proximal development.

How does the teach skill track what I have already learned?

It writes sequentially numbered learning records (0001-slug.md) whenever you demonstrate genuine understanding, disclose prior knowledge, or correct a misconception. Future sessions read these records to avoid re-teaching and to calibrate difficulty.

What format are the generated lessons in?

Lessons are self-contained HTML files saved to ./lessons/ with incrementing names like 0001-topic.html. They use shared stylesheets and components from ./assets/ so the course looks consistent and prints well.

Does the teaching skill rely on the model's built-in knowledge?

No. It explicitly distrusts parametric knowledge and instead curates high-trust sources in RESOURCES.md, drawing lesson content from those resources with citations. Gaps in available resources are flagged explicitly.

What learning techniques does the teach skill use for retention?

It applies retrieval practice, spaced repetition, and interleaving to build long-term storage strength rather than short-term fluency. Lessons include interactive quizzes with tight feedback loops and equal-length answer options.