Learn
Cognitive science-based AI tutor that won't let you fake understanding. Implements a full teaching loop (Explain→Example→Check→Evaluate→Practice), concept-level mastery tracking with FSRS spaced repetition, learning profile diagnostics, and zero-hint quizzes. Reads source material (PDFs, docs, code, URLs) to teach from specific content, or teaches from AI knowledge. Use this skill when the user says /learn, "teach me X", "quiz me", "review my concepts", "what should I study", "test my knowledge", "learning dashboard", "how well do I know X", or wants to systematically learn any topic. Also tri
Install
npx skills add Bhala-Srinivash/agent-tutor-skill --skill learngit clone --depth 1 https://github.com/Bhala-Srinivash/agent-tutor-skill.git /tmp/agent-tutor-skill
mkdir -p ~/.claude/skills
cp -r /tmp/agent-tutor-skill/. ~/.claude/skills/learnPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Agent Tutor Skill — Cognitive Science Learning Companion
A learning companion that produces actual understanding — not just answers. It tracks what you know and don't know at the **concept level**, teaches using cognitive science principles, and schedules reviews using the FSRS algorithm so you never forget.
## Why This Exists
AI makes learning feel easy. That's the problem. Mia Kiraki identified 4 cognitive traps:
1. **Fluency Illusion** — Clear explanations feel like comprehension, but aren't
2. **Zero Retrieval Practice** — AI answers remove the need to pull from your own memory
3. **No Desirable Difficulty** — AI removes the struggle that forces deeper processing
4. **Forgetting Architecture** — Every conversation starts fresh, no persistent memory
This skill fixes all four: enforces retrieval practice, tracks knowledge persistently, requires you to *prove* understanding, and schedules spaced reviews.
## Storage (Hybrid Model)
```
~/.learn/
├── profile.md ← Global: your learning preferences
└── topics/
├── {topic-slug}/
│ ├── knowledge-base.md ← Concept map + FSRS scheduling + session log
│ └── concepts/
│ └── {area}.md ← Per-area tracking with error notes
└── ...
```
- **Profile** is global — your learning style doesn't change per topic
- **Knowledge base** is per-topic — separate concept tracking for each subject
- **Concept files** track individual concepts within areas with FSRS parametersDetails
- Skill name
learn- Repository
- Bhala-Srinivash/agent-tutor-skill
- License
- MIT
- Repo updated
- 1 March 2026
FAQ
What does the Learn skill do?
Cognitive science-based AI tutor that won't let you fake understanding. Implements a full teaching loop (Explain→Example→Check→Evaluate→Practice), concept-level mastery tracking with FSRS spaced repetition, learning profile diagnostics, and zero-hint quizzes. Reads source material (PDFs, docs, code, URLs) to teach from specific content, or teaches from AI knowledge. Use this skill when the user says /learn, "teach me X", "quiz me", "review my concepts", "what should I study", "test my knowledge", "learning dashboard", "how well do I know X", or wants to systematically learn any topic. Also tri
How do I install the Learn skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add Bhala-Srinivash/agent-tutor-skill --skill learn. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Learn popular?
It lives in Bhala-Srinivash/agent-tutor-skill, which has 13 GitHub stars and 1 forks.
Related skills
Book Learning Tutor
12fangyuan-3149/book-learning-tutor
把书课程化并作为「专业教师」逐课带人类学完：课前备课→详尽费曼教学→练习闸门→间隔复习→背诵作业→自进化。处理使用者已提供的本地书（PDF/EPUB/DJVU/MOBI/AZW/DOCX/TXT/MD/CBZ）或已落在 参考/<书名>/ 的书；**本技能不联网、不搜索、不下载 —— 找书请用 book-finder 技能**。当用户说「学这本书 <本地路径> / 把这本 PDF 课程化 / 教我这本书 / 继续学 <书> / 复习 <书> / 考考我 <书> / 帮我学 X」时调用。教学引擎已单包自包含，无需再加载其他技能。
Generating Stem Flashcards
15jalliet/flashcards
Generates atomic flashcards from technical/STEM source material. Supports three output modes: (1) interactive React artifacts with client-side KaTeX rendering, (2) Anki-ready TSV export with MathJax-compatible LaTeX, or (3) direct push to Anki via MCP Server (no export/import step). Use when users request flashcards, study cards, revision cards, Anki cards, quiz materials, or spaced repetition content from lecture notes, textbooks, or worksheets containing mathematical notation.
Course Helper
13xxxhhhccc458/course-helper
课程学习资料整理与习题解答方法：把讲义、课件、PDF 整理成复习大纲，解答习题，生成公式速查表与易错辨析；并维护跨会话的教学交接文档（学习进度）、管理项目提示词库、按模块拆分项目资料档案（B 层）。当用户在课程学习类项目中要求整理讲义或课件、编写或续写复习大纲、讲解课程概念、解答作业题（HW／习题）、续写学习进度或教学交接文档、登记常用提示词时使用。不适用于纯代码工程项目。
Doceo
16eugeniughelbur/doceo
Turn anything the user wants to learn into a short, visual, plain-language teachable artifact (one HTML lesson page + a markdown lesson note), calibrated to what they already know and improving with every use. Use when the user runs /doceo, says "teach me X", "I don't understand X", "explain this simply", "make this teachable", or is clearly drowning in a too-technical explanation.
Think Like Me
13kakha13/think-like-me
Personal engineering rules and reasoning patterns the user has curated over time. Consult BEFORE writing, modifying, debugging, or designing any technical feature — rules often cover domain-specific gotchas (e.g., mobile audio timers need background mode) that generic answers miss. Also triggers on `/learn-this`, "learn this", "remember this", or `/new-rule` to capture new rules, and on detected corrections to previously proposed code.
Autonomous Learning Os
15gquthier/autonomous-learning-os
Construit à l'utilisateur son propre dashboard d'apprentissage sur mesure — entretien de setup, deep research multi-agents sur son sujet, génération du curriculum, app Next.js au design BizOS, brief Telegram optionnel. À utiliser quand l'utilisateur veut apprendre un sujet sérieusement, se construire un cursus, ou lance ce repo.
Browse the most popular Claude skills, all learning & education skills, or write your own with the skills generator.