[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-82916":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":25,"hasPages":23,"topics":26,"createdAt":10,"pushedAt":10,"updatedAt":36,"readmeContent":37,"aiSummary":38,"trendingCount":16,"starSnapshotCount":16,"syncStatus":39,"lastSyncTime":40,"discoverSource":41},82916,"learn-anything","ChenChenyaqi\u002Flearn-anything","ChenChenyaqi","AI-powered recursive learning system — Socratic deep-dives and TDD-style exercises integrated directly into your coding assistant.","",null,"TypeScript",165,14,52,1,0,11,74,112,54,93.53,"MIT License",false,"main",true,[27,28,29,30,31,32,33,34,35],"ai","claude-code","cli","codex","learning","skills","socratic-method","spaced-repetition","tdd","2026-06-12 04:01:39","# Learn Anything\n\n[English](.\u002FREADME.md) | [中文](.\u002FREADME.zh-CN.md)\n\nAI-powered recursive learning system — turns your AI coding assistant into an interactive tutor using the Socratic method and TDD-style exercises.\n\nGenerate skill and command files for **30+ AI tools** (Claude Code, Cursor, Gemini CLI, Codex, Copilot, Windsurf, etc.), then use slash commands to systematically master any technical topic.\n\n## Quick Start\n\n```bash\n# Initialize in your project (interactive — select your AI tools)\nnpx learn-anything-cli init\n\n# Or specify tools directly\nnpx learn-anything-cli init --tools claude\n\n# Chinese terminal output\nnpx learn-anything-cli init --lang zh-CN\n\n# Or install globally\nnpm install -g learn-anything-cli\nlearn-anything init\n```\n\nAfter init, your AI assistant gains five learning commands:\n\n| Command                          | What it does                                                 |\n| -------------------------------- | ------------------------------------------------------------ |\n| `\u002Flearn:topic \u003Ctopic-name>`      | Initialize a topic, generate a knowledge map, track progress |\n| `\u002Flearn:explain \u003Cconcept-name>`  | Recursive Socratic deep-dive into a concept                  |\n| `\u002Flearn:practice \u003Cconcept-name>` | TDD-style coding exercises with Socratic feedback            |\n| `\u002Flearn:review [topic-name]`     | Review progress, spaced repetition recommendations           |\n| `\u002Flearn:status [topic-name]`     | Visualize learning state as a knowledge map heatmap          |\n\n## Learning Workflows\n\n### `\u002Flearn:topic \u003Ctopic-name>` — Initialize a Topic\n\nThe AI generates a hierarchical knowledge map (`.learn\u002Ftopics\u002F\u003Ctopic>\u002Fknowledge-map.md`), creates a learning state tracker (`state.yaml`), and presents the landscape for you to choose your own path.\n\n### `\u002Flearn:explain \u003Cconcept-name>` — Recursive Deep Dive\n\nThe AI assesses your level (beginner → advanced), explains the concept with analogies and code examples, identifies deeper sub-topics, and lets you choose how deep to go. Every session is recorded for spaced repetition.\n\n### `\u002Flearn:practice \u003Cconcept-name>` — TDD-Style Exercises\n\nThe AI generates a test-driven exercise at the right difficulty (beginner \u002F intermediate \u002F challenge), provides structured Socratic feedback, and updates your mastery status. Edge cases, security, and code quality are all covered.\n\n### `\u002Flearn:review [topic-name]` — Progress Review\n\nAnalyzes your learning data: mastery heatmap, spaced repetition priority scoring, concept relationship analysis (blocking \u002F orphan concepts). Generates a personalized next-step plan.\n\n### `\u002Flearn:status [topic-name]` — Visualize State\n\nRenders a knowledge map heatmap with status icons, practice counts, and confidence scores for every concept.\n\n## Supported AI Tools\n\nManage, Amazon Q Developer, Antigravity, Auggie, Bob Shell, Claude Code, Cline, Codex, ForgeCode, CodeBuddy Code, Continue, CoStrict, Crush, Cursor, Factory Droid, Gemini CLI, GitHub Copilot, iFlow, Junie, Kilo Code, Kiro, OpenCode, Pi, Qoder, Lingma, Qwen Code, RooCode, Trae, Windsurf, and AGENTS.md-compatible assistants.\n\n```bash\n# Update skill files to latest version (detects existing tools automatically)\nnpx learn-anything-cli update\n```\n\n## How It Works\n\n```\nYour Project\u002F\n├── .claude\u002Fcommands\u002Flearn\u002F    # Slash commands (learn:topic, learn:explain, ...)\n├── .claude\u002Fskills\u002F            # Skill files with full workflow instructions\n├── .cursor\u002Fcommands\u002F          # Cursor-specific command format\n├── .gemini\u002Fcommands\u002Flearn\u002F    # Gemini TOML-format commands\n├── .learn\u002F                    # Your learning data (knowledge maps, progress)\n│   └── topics\u002F\n│       └── javascript\u002F\n│           ├── knowledge-map.md\n│           ├── state.yaml\n│           └── sessions\u002F\n└── ...\n```\n\nEach AI tool gets tool-appropriate file formats (YAML frontmatter for Claude, TOML for Gemini, etc.) via an adapter pattern.\n\n## Development\n\n```bash\npnpm install\npnpm build        # Compile TypeScript\npnpm test         # Run tests\npnpm dev          # Watch mode\npnpm dev:cli      # Build and run CLI locally\n```\n\n## License\n\nMIT\n","Learn Anything 是一个基于AI的递归学习系统，将你的AI编码助手转变为使用苏格拉底式教学法和测试驱动开发风格练习的互动导师。项目支持超过30种AI工具，如Claude Code、Cursor、Gemini CLI等，用户可以通过命令行初始化，并选择适合自己的AI工具进行技术主题的学习。核心功能包括创建话题知识地图、概念深度解析、编程实践练习、学习进度回顾及状态可视化展示。特别适用于希望系统性地掌握复杂技术概念和技术栈的开发者或学生，在日常学习或工作中通过与AI交互来提升技能水平。",2,"2026-06-11 04:09:38","CREATED_QUERY"]