A proper Socratic tutor that refuses to give you answers. It diagnoses your current level first, breaks topics into atomic concepts, then gates your progress at 80% mastery before moving forward. The whole thing runs on Bloom's 2-Sigma method with spaced repetition baked in. It generates HTML roadmaps, Excalidraw concept maps, and tracks misconceptions across sessions in a persistent learner profile. Invoke it with /sigma followed by any topic, or just say you want to learn something. The core promise is genuine: it will ask questions and wait for you to work things out, not hand you explanations. If you've ever wished for a patient tutor who actually makes you think instead of just explaining, this is that.

install copies · 90 days. Times the install command was copied on this site in the last 90 days, bots filtered.
8
skills.sh installs
1.1K
GitHub stars
3.8K
last updated
Jul 14, 2026

Install

$ npx -y skills add sanyuan0704/code-review-expert --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

ArgumentDescription
<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)
--resumeResume previous session from sigma/{topic-slug}/
--visualForce rich visual output every round

Core Rules (NON-NEGOTIABLE)

Sponsors

Details

Repository
github.com/sanyuan0704/code-review-expert
Categories
Git & Pull Requests, Code Review & Quality
First seen
May 16, 2026

More from sanyuan0704/code-review-expert

All 5
1github avatararize-ai-provider-integrationgithub/awesome-copilotCreates, reads, updates, and deletes Arize AI integrations that store LLM provider credentials used by evaluators and other Arize features. Supports any LLM pro1.1Kskills.sh installs
2github avatararize-evaluatorgithub/awesome-copilotHandles LLM-as-judge evaluation workflows on Arize including creating/updating evaluators, running evaluations on spans or experiments, managing tasks, trigger-1.1Kskills.sh installs
3github avatarreact19-concurrent-patternsgithub/awesome-copilotPreserve React 18 concurrent patterns and adopt React 19 APIs (useTransition, useDeferredValue, Suspense, use(), useOptimistic, Actions) during migration.1.1Kskills.sh installs
4github avatararize-datasetgithub/awesome-copilotCreates, manages, and queries Arize datasets and examples. Covers dataset CRUD, appending examples, exporting data, and file-based dataset creation using the ax1.1Kskills.sh installs
5github avatararize-instrumentationgithub/awesome-copilotAdds Arize AX tracing to an LLM application for the first time. Follows a two-phase agent-assisted flow to analyze the codebase then implement instrumentation a1.1Kskills.sh installs
6github avatarintegrate-context-maticgithub/awesome-copilotDiscovers and integrates third-party APIs using the context-matic MCP server. Uses `fetch_api` to find available API SDKs, `ask` for integration guidance, `mode1.1Kskills.sh installs