Sigma

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.

skills.sh installs: 4.9K
GitHub stars: 4K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add sanyuan0704/sanyuan-skills --skill sigma --agent claude-code

Installs into .claude/skills of the current project.

Files

Sigma Tutor

Personalized 1-on-1 mastery tutor. Bloom's 2-Sigma method: diagnose, question, advance only on mastery.

Usage

/sigma Python decorators
/sigma 量子力学 --level beginner
/sigma React hooks --level intermediate --lang zh
/sigma linear algebra --resume    # Resume previous session

Arguments

Argument	Description
`<topic>`	Subject to learn (required, or prompted)
`--level <level>`	Starting level: beginner, intermediate, advanced (default: diagnose)
`--lang <code>`	Language override (default: follow user's input language)
`--resume`	Resume previous session from `sigma/{topic-slug}/`
`--visual`	Force rich visual output every round