Learn Anything is an AI-powered recursive learning system — Socratic deep-dives and TDD-style exercises integrated directly into your coding assistant.

Hire a private AI tutor for anything — it reads how you actually learn and teaches the next lesson just for you. Bloom's 2-Sigma research as a Claude Code skill + self-hostable web app · 中文优先 苏格拉底式 AI 家教

三位老师，一段故事，零个标准答案。——当苏格拉底教学法遇上轻小说叙事，学习便不再孤独。

Die sokratische Methode als Claude Skill.md

The Dataset and Official Implementation for <Discursive Socratic Questioning: Evaluating the Faithfulness of Language Models’ Understanding of Discourse Relations> @ ACL 2024

The Architecture of Thought: The Dialectical Cognition Framework - A Treatise on Human-AI Collaboration

A Socratic dialogue engine for AI agents.

Master AI Agent Assistant in 3 Days. A guided study plan using nanobot (~3k lines of Python) and your own AI Socratic Tutor. Learn Architecture, Skills, and Deployment.

Every solution is a thesis. Defend it. — A framework that challenges technical & AI implementations before they ship.

MindWiki — 10 顶级专家组团的决策追问系统 Skills（张小龙、乔布斯、马斯克、张一鸣、芒格、王兴、雷军、梁宁、Naval、毛泽东）。带工具调用和自我验证测试。

Three-layer memory architecture for long-term AI learning with Claude

Open-source pipeline for generating & evaluating Socratic dialogues with LLMs. Includes expert-labeled data and a calibrated judge model.

The AI that refuses to think for you. Open-source anti-deskilling framework implementing human-AI collaboration protocols from the Cabitza lab (Milano-Bicocca). Four modes: Forge, Anvil, Crucible, Executor.

让想法，落地 — 给想得多、做得少的人。Socratic AI · Ink design · BYOK · self-hosted.

An AI skill that interrogates you — with your consent — until the story you tell yourself gives way to what's actually true. Claude Code plugin / Agent Skill.

Socratic AI agent prompting skill

A Socratic tutor that refuses to hand you the answer — until you can prove you actually understand. 一个拒绝直接给答案的导师，直到你能证明自己真的懂了。

Local-first desktop app: 16 AI agents from 8 LLM providers debate any topic — with live argument mapping, fact-check badges, and conflict detection.

Quorum: orchestrate a swarm of AI experts on any question. Specialists debate, research, and validate — then a polymath supervisor delivers the verdict. One command, multiple minds, stress-tested answers.

Critical thinking plugin for Claude Code. Three specialized agents (advocate, adversary, judge) argue, stress-test, and judge any idea using a shared argument graph, 10 reasoning traditions, and persistent memory.