teach

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

Updated Jul 30, 2026
One-click install
npx skills add https://github.com/j172/bid --skill teach-j172
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: teach
Source: https://github.com/j172/bid/tree/main/agent/skills/teach
Command: npx skills add https://github.com/j172/bid --skill teach-j172

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 - Mission-Grounded Teaching: Captures your concrete learning goal in MISSION.md so every lesson ties back to a real-world outcome. - Progressive HTML Lessons: Generates short, self-contained, beautifully typeset lessons in ./lessons/ targeted at your zone of proximal development, with quizzes and feedback loops for retention. - Learning Records & Glossary: Tracks demonstrated understanding in numbered learning records and maintains a canonical glossary, so future sessions never re-teach what you know. - Curated Resources: Builds RESOURCES.md with high-trust knowledge sources and communities instead of relying on parametric guesses. - Use Case: You want to learn strength training over several weeks. The Skill interviews you about your goal, writes a mission file, curates trusted sources, then produces a sequence of interactive HTML lessons that build on each other as your learning records grow. ## Quick Start Ask the agent to teach you a topic, for example: "Teach me the basics of Rust ownership over the next few sessions."

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 over multiple sessions?

Use a stateful teaching workspace that stores your mission, learning records, and resources 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.

What files does the teaching workspace create?

The workspace contains MISSION.md for your learning goal, RESOURCES.md for curated sources, GLOSSARY.md for terminology, numbered learning records in ./learning-records/, HTML lessons in ./lessons/, reusable components in ./assets/, and NOTES.md for preferences.

How are lessons designed for long-term retention?

Lessons use retrieval practice, spacing, and interleaving to build storage strength rather than short-term fluency. Each lesson is short, interactive, includes quizzes with immediate feedback, and targets one tightly-scoped skill tied to your mission.

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

No, it explicitly avoids parametric knowledge. Teaching content is grounded in high-trust sources curated in RESOURCES.md, and lessons include citations to external primary resources for every claim.

What happens when my learning goal changes mid-way?

The mission file is updated after confirming with you, and a learning record is written to capture the shift. Future lessons are then re-planned around the revised mission rather than the stale one.