teach

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

Updated May 11, 2026
One-click install
npx skills add https://github.com/mmnavarr/harness --skill teach-mmnavarr
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: teach
Source: https://github.com/mmnavarr/harness/tree/main/skills/teach
Command: npx skills add https://github.com/mmnavarr/harness --skill teach-mmnavarr

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, progress, and resources across sessions. ## Core Features & Use Cases - Stateful Learning Workspace: Maintains MISSION.md, RESOURCES.md, GLOSSARY.md, and numbered learning records so every session builds on prior understanding. - HTML Lesson Generation: Produces short, self-contained, beautifully typeset lessons saved to ./lessons/, each targeting your zone of proximal development with retrieval practice and feedback loops. - Reusable Components & References: Builds a shared asset library (stylesheets, quiz widgets) and printable reference documents like glossaries and cheat sheets. - Use Case: You want to learn strength training over several weeks. The Skill interviews you to define a mission, curates trusted resources, generates interactive lessons, and records each insight so future sessions never re-teach what you already know. ## 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. The agent creates a workspace with MISSION.md, learning records, and HTML lessons, so each session resumes from your recorded progress instead of starting over.

How does the teach skill decide what to teach next?▼

It calculates your zone of proximal development by reading numbered learning records in ./learning-records/ and your MISSION.md. Lessons target material that is challenging but achievable given what you have already demonstrated you understand.

What files does the teaching workspace create?▼

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

Can I use the teach skill without joining external communities?▼

Yes. The skill recommends high-reputation communities for acquiring real-world wisdom, but if you state a preference against joining, it records that preference in RESOURCES.md and stops proposing them.

What are the limitations of AI-generated lessons?▼

Lessons depend on curated resources in RESOURCES.md rather than the model's parametric knowledge, so early sessions focus on finding trustworthy sources. Knowledge claims should be backed by citations, and wisdom-level questions are deferred to real communities.