165 evidence-grounded AI skills for teachers, school leaders and EdTech builders—pedagogy, learning science, curriculum, assessment and regeneration. Claude, Codex and Hermes.
-
Updated
Aug 28, 2026 - TypeScript
165 evidence-grounded AI skills for teachers, school leaders and EdTech builders—pedagogy, learning science, curriculum, assessment and regeneration. Claude, Codex and Hermes.
Build with Claude Code without your brain going numb — a plugin that quizzes you on the code it just wrote and gates the session until you pass.
Universal AI agent skill that turns any material into learning-science-based self-study courses with retrieval practice, spaced repetition, and tutor mode.
Cognitive science AI tutor skill for Claude Code — teaching loop, FSRS spaced repetition, zero-hint quizzes, concept-level mastery tracking
RSVP speed reader for Obsidian with retrieval practice, streaks, and AI study integration. Part of the Study Framework.
Evidence-driven Agent Skill for systematic learning: retrieval, discrimination, transfer, performance, and long-term continuity.
Agent Skill that quizzes you on its own answers — one multiple-choice question after each substantive reply, graded and explained. Ambient retrieval practice against AI deskilling. Instruction-only: no scripts, no network, no data sent. MIT.
Turn any study material into a spaced-repetition mastery loop: AI-generated active-recall items plus a real FSRS scheduler, in a portable Claude/Codex/Cowork skill.
Brief, situated comprehension checks for AI-assisted changes in Claude Code.
A browser extension that develops human intellectual independence.
One teaching system that works in any AI harness — opencode, Claude Code, Codex, Cursor, pi, plain chat. Teach skill reads a learner profile every session, probes before explaining, spaces review across sessions. Install via npx teacher-sab.
Turn your own material into a runnable course: FSRS spaced repetition, retrieval practice, real grading, zero dependencies. Halts hard at every graded step, so the machine never takes the test for you; every graded step leaves a re-verifiable receipt.
Understand it. Retrieve it. Use it. A research-grounded teaching skill with course-aware practice and optional accessibility preferences.
An AI tutor that is not allowed to explain first — an evidence-based, guarded tutoring loop for pi. · 一个不允许先讲解的 AI 导师:基于实证、带护栏的一对一学习循环。
Generate quiz questions from any source material: plausible distractors from misconception banks, per-option explanations, configurable difficulty bands.
Microlearning App: AI-powered Android app that transforms doomscrolling into context-aware 3-15 minute learning sessions with adaptive practice, spaced retention, and privacy-first design.
Open-source study system built on learning science: AI weekly plan, focus mode, closed-book tests and a degree record. PT/EN · npx estudar
KI-Lern-Coach für Eltern: hilft DIR, dein Kind in kurzen, spielerischen Lerneinheiten zu begleiten und Arbeitsmaterial (inkl. druckbarer A4-Blätter) zu erstellen. Fundiert auf Lernforschung, fach-agnostisch. Fördert Lernkompetenz statt Noten. Kein Tool fürs Kind selbst, keine Hausaufgabenhilfe.
Instead of writing comments, your coding agent asks you to explain the code it just wrote, then grades the answer and awards XP. Retrieval practice for AI-assisted development.
From documents to deliberate learning: parallel extraction, evidence-preserving merges, retrieval practice, cases, and printable study systems.
To associate your repository with the retrieval-practice topic, visit your repo's landing page and select "manage topics."