teach

Creates stateful multi-session teaching workspaces with HTML lessons, glossaries, and learning records.

Updated Jun 30, 2026
One-click install
npx skills add https://github.com/santoshkal/chezmoi --skill teach-santoshkal
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: teach
Source: https://github.com/santoshkal/chezmoi/tree/main/private_dot_config/opencode/skills/teach
Command: npx skills add https://github.com/santoshkal/chezmoi --skill teach-santoshkal

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, why you are learning, or what to tackle next. This Skill turns a directory into a persistent teaching workspace that tracks your mission, knowledge, and progress across sessions. ## Core Features & Use Cases - Stateful Learning Workspace: Maintains MISSION.md, RESOURCES.md, GLOSSARY.md, NOTES.md, and numbered learning records so every session builds on prior understanding. - HTML Lesson Generation: Produces short, self-contained, beautifully typeset lessons in ./lessons/ with quizzes, feedback loops, citations, and links to reference documents. - Zone of Proximal Development Targeting: Reads learning records to pick the next concept that challenges you just enough, applying 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 define a concrete mission, curates trusted resources, generates interactive HTML lessons, and records each insight so future sessions never re-teach what you already know. ## 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 and state what you want to learn. It creates a persistent workspace with a mission file, resources, lessons, and learning records so each session builds on what you already demonstrated you know.

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 selects the most relevant concept that challenges you just enough. If the mission is unclear, it interviews you first before teaching anything.

What files does the teaching workspace create?▼

It maintains MISSION.md, RESOURCES.md, GLOSSARY.md, and NOTES.md at the root, plus numbered learning records in ./learning-records/, HTML lessons in ./lessons/, and reference documents in ./reference/. Directories are created lazily when first needed.

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

No. It explicitly distrusts parametric knowledge and grounds lessons in high-trust sources curated in RESOURCES.md, with citations throughout each lesson. Wisdom-oriented questions are delegated to real communities rather than answered from memory.

When is a learning record written versus a glossary entry?▼

A learning record captures decision-grade insights: demonstrated understanding, disclosed prior knowledge, corrected misconceptions, or mission shifts. A glossary entry is added only when you can use a term correctly, compressing it into a tight definition reused across lessons.