by IssacW228
📚 Student LLM Wiki — AI-compiled knowledge base for university students. Drop course slides, get a persistent interlinked wiki. Feynman review, exam prep, confidence decay, cross-course connections. Based on Karpathy's LLM Wiki pattern. Works with Claude Cowork / Claude Code / Claudian + Obsidian.学生大语言模型维基百科——专为大学生打造的AI编译知识库。
# Add to your Claude Code skills
git clone https://github.com/IssacW228/student-llm-wikiGuides for using ide extensions skills like student-llm-wiki.
student-llm-wiki is an open-source ide extensions skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by IssacW228. 📚 Student LLM Wiki — AI-compiled knowledge base for university students. Drop course slides, get a persistent interlinked wiki. Feynman review, exam prep, confidence decay, cross-course connections. Based on Karpathy's LLM Wiki pattern. Works with Claude Cowork / Claude Code / Claudian + Obsidian.学生大语言模型维基百科——专为大学生打造的AI编译知识库。. It has 178 GitHub stars.
student-llm-wiki's catalog security scan is still queued. You can run an instant dependency and prompt-injection check now with the "Scan for vulnerabilities" button above.
Clone the repository with "git clone https://github.com/IssacW228/student-llm-wiki" and add it to your Claude Code skills directory (see the Installation section above).
Yes. SkillsLLM lists many other IDE Extensions skills you can browse and compare side by side. Open the IDE Extensions category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh student-llm-wiki against similar tools.
No comments yet. Be the first to share your thoughts!
Top skills in this category by stars
Unlocks once the catalog security scan passes (runs nightly).
The deep catalog scan for this skill is still queued. Run an instant dependency check now instead.
用 AI 把课件变成你自己的知识库 Turn your course slides into a personal wiki with AI
你把课件 PDF 丢进 raw/ 文件夹,AI 自动帮你整理成结构化的 wiki 笔记,存在 wiki/ 里。你用 Obsidian 浏览这些笔记,用 AI 工具来复习、出题、检查薄弱环节。你不需要手写任何笔记。
基于 Andrej Karpathy 的 LLM Wiki 模式。
1. Obsidian(用来浏览笔记)
2. 选一个 AI 工具(任选其一即可)
| 工具 | 适合人群 | 获取方式 |
|---|---|---|
| Claude Code CLI | 熟悉命令行 | 安装说明 |
| Claude Code Web | 不想装任何东西 | claude.ai/code |
| Cursor | 喜欢 IDE 界面 | cursor.com |
| Trae | 国内用户 | trae.ai |
| Cowork | 团队协作 | 参考 Cowork 文档 |
| GitHub Copilot | 已有订阅 | VS Code 插件市场 |
3. 你的课件(PDF 或其他文本格式)
git clone https://github.com/IssacW228/student-llm-wiki.git
cd student-llm-wiki
然后打开 Obsidian → 「打开本地仓库」→ 选择 student-llm-wiki 文件夹。
必须安装 Dataview 插件:Obsidian 设置 → 社区插件 → 浏览 → 搜索
Dataview→ 安装并启用。
claude
.claude/)会自动加载,无需额外设置.claude/)自动识别,直接使用student-llm-wiki 文件夹.cursor/rules/wiki.mdc,自动生效student-llm-wiki 文件夹.trae/skills/,自动识别student-llm-wiki 文件夹COWORK-INSTRUCTIONS.md 会自动加载AGENTS.md 会被自动读取raw/ 下新建文件夹,用你的课程代号命名(如 raw/MATH1001/)ingest raw/MATH1001/L1.pdf
Home.md 查看结果同一份文件不会被重复导入(通过文件 hash 去重)。
| 命令 | 作用 |
|---|---|
ingest raw/XXXX/L1.pdf |
导入课件,自动生成笔记、课程总览、跨课连接记录 |
lint |
检查笔记健康度:断链、孤立页、过期概念、缺失总览、术语表补全 |
review XXXX |
费曼复习模式:AI 提问,你来回答 |
exam-prep XXXX |
根据薄弱概念自动出练习题 |
diagram ConceptName |
为某个概念页添加 Mermaid 图解(流程图/架构图/时序图等) |
也可以用自然语言,比如「帮我复习这门课」或「把这个文件导入知识库」。
raw/ 下创建对应课程文件夹(如 raw/PHYS1001/)ingest,课程总览页会自动创建Home.md 首页会动态显示新课程,无需手动修改student-llm-wiki/
├── raw/ ← 放课件(只读,AI 不会修改这里)
│ └── XXXX/ ← 按课程分文件夹
├── wiki/ ← AI 生成的笔记(自动维护)
│ ├── concepts/ ← 概念页(每概念一页,含图解)
│ ├── courses/ ← 课程总览(ingest 时自动创建)
│ ├── sources/ ← 课件摘要
│ ├── exam-prep/ ← 练习题
│ ├── connections-log.md ← 跨课程连接发现记录
│ ├── contradictions.md ← 矛盾与张力追踪
│ ├── glossary.md ← 中英术语表(自动填充)
│ ├── overview.md ← 跨课程综述(自动更新)
│ ├── index.md ← 总目录
│ └── hot.md ← AI 上下文缓存(每次 session 首读)
├── Home.md ← Obsidian 首页仪表盘
│
│ 以下为 AI 工具配置文件,无需修改:
├── .claude/ ← Claude Code 配置
├── .cursor/ ← Cursor 配置
├── .trae/ ← Trae 配置
├── AGENTS.md ← Copilot/Codex 配置
└── COWORK-INSTRUCTIONS.md ← Cowork 配置
MIT
You drop course PDF slides into the raw/ folder. The AI automatically organizes them into structured wiki notes in wiki/. You browse the notes with Obsidian, and use AI tools to review, generate practice questions, and surface weak spots. You never write notes yourself.
Based on Andrej Karpathy's LLM Wiki pattern.
1. Obsidian (for browsing your notes)
2. An AI tool (pick just one)
| Tool | Best for | Get it |
|---|---|---|
| Claude Code CLI | Terminal users | Install guide |
| Claude Code Web | No install needed | claude.ai/code |
| Cursor | IDE-style interface | cursor.com |
| Trae | — | trae.ai |
| Cowork | Team use | See Cowork docs |
| GitHub Copilot | Existing subscribers | VS Code marketplace |
3. Your course slides (PDF or other text formats)
git clone https://github.com/IssacW228/student-llm-wiki.git
cd student-llm-wiki
Open Obsidian → "Open folder as vault" → select the student-llm-wiki folder.
Install the Dataview plugin: Obsidian Settings → Community plugins → Browse → search
Dataview→ Install and enable.
claude
.claude/) is auto-detected — no extra setup needed.claude/ config is auto-detected — start typing commands directlystudent-llm-wiki folder in Cursor.cursor/rules/wiki.mdc — auto-appliedstudent-llm-wiki folder in Trae.trae/skills/ — auto-detectedstudent-llm-wiki folderCOWORK-INSTRUCTIONS.md loads automaticallyAGENTS.md is read automaticallyraw/ named after your course (e.g. raw/MATH1001/)ingest raw/MATH1001/L1.pdf
Home.md to see your new notesThe same file won't be ingested twice — files are tracked by hash.
| Command | What it does |
|---|---|
ingest raw/XXXX/L1.pdf |
Import a slide deck — generates notes, course overview, and cross-course link records |
lint |
Check wiki health: broken links, orphan pages, stale concepts, missing overviews, glossary gaps |
review XXXX |
Feynman review mode: AI quizzes you |
exam-prep XXXX |
Auto-generate practice questions from weak concepts |
diagram ConceptName |
Add a Mermaid diagram to a concept page (flowchart / architecture / sequence / etc.) |
You can also use plain English: "quiz me on this course" or "import this file into the wiki".
raw/ for the course (e.g. raw/PHYS1001/)ingest — a course overview page is created automaticallyHome.md dashboard updates dynamically — no manual edits neededstudent-llm-wiki/
├── raw/ ← Your slides (read-only — AI never modifies this)
│ └── XXXX/ ← One folder per course
├── wiki/ ← AI-generated notes (auto-maintained)
│ ├── concepts/ ← Concept pages (one per concept, with diagrams)
│ ├── courses/ ← Course overviews (auto-created on ingest)
│ ├── sources/ ← Slide summaries
│ ├── exam-prep/ ← Practice questions
│ ├── connections-log.md ← Cross-course link discovery log
│ ├── contradictions.md ← Contradiction & tension tracker
│ ├── glossary.md ← Bilingual term index (auto-populated)
│ ├── overview.md ← Cross-course synthesis (auto-updated)
│ ├── index.md ← Master catalog
│ └── hot.md ← AI context cache (read first each session)
├── Home.md ← Obsidian dashboard
│
│ AI tool config — no need to touch these:
├── .claude/ ← Claude Code config
├── .cursor/ ← Cursor config
├── .trae/ ← Trae config
├── AGENTS.md ← Copilot/Codex config
└── COWORK-INSTRUCTIONS.md ← Cowork config