Bhala-Srinivash/agent-tutor-skill

learn

When your agent uses it

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 triggers on "let's study", "drill me on", "what's due for review", requests for structured learning with progress tracking, or any context where the user wants to actually understand (not just read about) a topic.

What it loads into context

Token counts are estimates. Scripts run separately; they are not counted as reference context.

# 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.