What problem does it solve? Explaining a topic once rarely makes it stick; facts get memorized, then forgotten. This Skill turns any explanation into a structured teaching session that builds genuine understanding by connecting new facts to foundations the learner already accepts, and it grounds every claim in the project's .vault/ knowledge base before falling back to the web. ## Core Features & Use Cases - Probe-Plan-Teach workflow: Maps the learner's current level with graded quiz questions, presents a dependency-graph lesson plan as a mermaid diagram for approval, then teaches node by node with quiz-checks after each concept. - Vault-first grounding: Dispatches a read-only research agent that searches the vault's summaries, maps, and raw sources before using web search, so lessons build on material already collected. - Durable trace: Writes a lesson transcript to wiki/lessons/ and updates a mastery map in wiki/maps/ tracking which strands are solid, fuzzy, or missing. - Use Case: A student asks to finally understand eigenvalues before an exam. The Skill probes their linear algebra foundations, finds past exams in the vault to calibrate against, teaches via motivated discovery steps, and leaves a lesson log plus an updated mastery map for future sessions. ## Quick Start Ask the assistant to teach you a topic, for example: teach me how Bayesian updating works using my vault, starting from what I already know.
