This is a full implementation of Bloom's 2-sigma mastery learning as a tutoring system. It never gives you answers directly, only Socratic questions and minimal hints until you hit ~80% understanding before moving forward. Starts by diagnosing what you already know, builds a concept dependency roadmap, then works through it with spaced repetition and misconception tracking. The output is serious: persistent learner profiles across topics, HTML dashboards, Excalidraw concept maps, detailed session logs with mastery scores. The workflow is rigid by design, one or two questions per round, no exceptions. If you want an AI that actually makes you work for understanding instead of spoon-feeding explanations, this is that. Best for topics where you need deep retention, not quick answers.
npx -y skills add sanyuan0704/sanyuan-skills --skill sigma --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
juliusbrussee/caveman
mattpocock/skills
shadcn/improve
obra/superpowers
forrestchang/andrej-karpathy-skills
vercel-labs/skills