do-teach-me

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

2|Updated May 25, 2026
One-click install
npx skills add https://github.com/edheltzel/Do-Skills --skill do-teach-me-edheltzel
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: do-teach-me
Source: https://github.com/edheltzel/Do-Skills/tree/main/skills/personal/do-teach-me
Command: npx skills add https://github.com/edheltzel/Do-Skills --skill do-teach-me-edheltzel

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Learning a new topic with an AI assistant is usually stateless: every session starts from zero, lessons are not saved, and there is no record of what you already know. This Skill turns the current 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, NOTES.md, and numbered learning records so each session builds on prior understanding. - HTML Lessons and References: Generates self-contained, printable HTML lessons in ./lessons/ plus reusable reference documents and shared components in ./assets/. - Evidence-Based Teaching: Applies zone of proximal development, retrieval practice, spacing, and interleaving, and grounds content in curated high-trust resources rather than parametric knowledge. - Use Case: You want to learn strength training over several weeks. The Skill interviews you to define a mission, curates trusted sources, produces short interactive HTML lessons with quizzes, and records each demonstrated understanding so the next lesson targets the right difficulty. ## Quick Start Ask the agent to teach you a topic, for example: teach me the fundamentals of Rust ownership in this workspace.

Frequently Asked Questions about do-teach-me

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 skill in a dedicated directory and state what you want to learn. The agent creates a teaching workspace with a mission file, resources, and numbered HTML lessons, then records what you demonstrate understanding of so future sessions build on it.

What files does the teaching workspace create?▼

It creates MISSION.md for your learning goal, RESOURCES.md for curated sources, GLOSSARY.md for terminology, NOTES.md for preferences, a learning-records directory with numbered markdown records, a lessons directory of HTML lessons, and an assets directory for reusable components.

How does the skill decide what to teach next?▼

It reads your learning records and mission to estimate your zone of proximal development, then teaches the most relevant concept that is challenging but achievable. If the mission is unclear, it interviews you before producing lessons.

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

No, it explicitly avoids trusting parametric knowledge. Lessons are grounded in high-trust resources curated in RESOURCES.md, and each lesson cites a primary source and links to external references for its claims.

What format are the lessons in and can I print them?▼

Lessons are self-contained HTML files saved in ./lessons/ with sequential numbering like 0001-topic.html. They use clean typography designed to print well and link to each other and to reference documents.

When should I not use this teaching workspace approach?▼

It is designed for stateful, multi-session learning of one topic per workspace. For one-off factual questions or quick lookups, a direct answer is more appropriate than setting up missions, records, and lesson files.