Video

Learn anything with the /teach skill

Matt Pocock, YouTube · 2026-06-08.June 8, 2026
Watch: full video.

This short walkthrough shows how a /teach skill can turn an AI agent into a more structured learning partner, not just a chatbot that explains things on demand. The useful idea is that the skill does not simply answer questions; it creates lessons, checks understanding, tracks progress, and tries to teach at the learner’s next reachable level. For knowledge workers, the value is a clearer way to use AI for learning: not asking for generic explanations, but designing a guided path that stretches without overwhelming.

Official video embed

Matt Pocock, YouTube · 2026-06-08

Matt Pocock, YouTube · 2026-06-08

This video is hosted by a third-party provider. It will load only after you choose to press Play.

This video can load through the original platform's official player where available.

Open original source
  • A /teach skill turns learning into a repeatable workflow: choose a topic, assess what the learner already understands, create a lesson, check comprehension, and adapt the next step.
  • The important teaching idea is the “zone of proximal development”: the lesson should be just beyond the learner’s current ability, difficult enough to stretch them but not so hard that they get lost.
  • Good AI teaching is not just explanation; it needs feedback loops, examples, questions, progress tracking, and ways to notice when the learner is confused.
  • For knowledge workers, the practical lesson is to use AI as a structured tutor for difficult topics, not just as a search box for quick answers.