teach

Creates interactive HTML lessons and learning records in a persistent teaching workspace.

Updated Sep 13, 2026
One-click install
npx skills add https://github.com/petemcw/farseer --skill teach-petemcw
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: teach
Source: https://github.com/petemcw/farseer/tree/main/skills/teach
Command: npx skills add https://github.com/petemcw/farseer --skill teach-petemcw

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Learning a new topic with an AI assistant is usually ephemeral: each session starts from zero, lessons are unstructured chat text, and there is no record of what you already know. This Skill turns a directory into a persistent teaching workspace that tracks your mission, resources, and learning progress across sessions. ## Core Features & Use Cases - Stateful Learning Workspace: Maintains MISSION.md, RESOURCES.md, NOTES.md, and numbered learning records to ground every lesson in your goals and prior knowledge. - Interactive HTML Lessons: Generates self-contained, beautifully typeset lessons with quizzes and feedback loops, saved to ./lessons/ and built from reusable components in ./assets/. - Reference Documents: Produces printable cheat sheets, glossaries, and quick-reference HTML files that compress lesson knowledge for long-term review. - Use Case: You want to learn strength training over several weeks. The Skill interviews you to define a mission, curates trusted resources, then delivers short interactive lessons calibrated to your zone of proximal development, recording each milestone so future sessions build on it. ## Quick Start Ask the assistant to teach you a topic, for example: "Teach me the fundamentals of strength training so I can run my first program."

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 stores your mission, resources, and learning records as files in the current directory. Each session reads these files to determine what you already know and generates the next lesson in your zone of proximal development.

How are the lessons delivered and formatted?▼

Each lesson is a single self-contained HTML file saved to ./lessons/ with sequential numbering like 0001-topic-name.html. Lessons include interactive quizzes, feedback loops, citations to trusted sources, and links to related lessons and reference documents.

What files does the teaching workspace create?▼

The workspace maintains MISSION.md for your learning goal, RESOURCES.md for curated trusted sources, NOTES.md for preferences, numbered learning records in ./learning-records/, HTML lessons in ./lessons/, reference documents in ./reference/, and reusable components in ./assets/.

How does the skill decide what to teach next?▼

It reads your learning records to calculate your zone of proximal development, then selects the most relevant topic tied to your mission. If your mission is unclear, it interviews you first before producing any lessons.

Can I use this for skill-based topics like fitness or yoga?▼

Yes, the Skill supports both knowledge-based and skill-based topics. For skills, it designs interactive lessons with tight feedback loops, retrieval practice, spacing, and interleaving to build long-term retention rather than temporary fluency.