What problem does it solve? One-off explanations fade quickly and chat-based tutoring loses all progress between sessions. This Skill turns the current directory into a persistent teaching workspace so a topic started today resumes weeks later at exactly the right difficulty, with learning grounded in small buildable artifacts rather than passive reading. ## Core Features & Use Cases - Stateful learning workspace: Maintains MISSION.md, GLOSSARY.md, RESOURCES.md, learning-records/, and builds/ directories that persist progress, corrected misconceptions, and demonstrated understanding between sessions. - Build-to-learn loop: Each lesson produces the smallest runnable artifact (React/Next/TypeScript scripts, Vitest/Jest tests, GSAP/Framer motion, Playwright browser behaviors) that exercises one skill in the zone of proximal development. - Storage-strength assessment: Gates progression on from-scratch retrieval and rebuild rather than recognition, citing primary sources instead of teaching from parametric memory. - Use Case: Ask to learn the tool-calling agent loop; over three sessions you build a plain completion, a forced-tool-choice call, and a closed-enum router, with each corrected misconception recorded so the next session builds on it. ## Quick Start Teach me React Server Components over multiple sessions, starting from what I already know and building small runnable examples.
