Karpathy Wiki

Use when building or maintaining a personal knowledge base with LLM assistance. Triggers on ingesting sources, compiling wiki articles, querying knowledge, running health checks, deep research, or initializing a new wiki vault. Based on Karpathy's LLM Wiki pattern with Obsidian integration.

117 stars 17 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add SherwinQ/karpathy-wiki --skill karpathy-wiki
Manual install
git clone --depth 1 https://github.com/SherwinQ/karpathy-wiki.git /tmp/karpathy-wiki
mkdir -p ~/.claude/skills
cp -r /tmp/karpathy-wiki/. ~/.claude/skills/karpathy-wiki

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Karpathy Wiki

LLM-driven personal knowledge base that compounds over time. Raw sources in, structured wiki out.

> You never write the wiki. The LLM writes everything. You just steer, and every answer compounds.

## When to Use

- User wants to ingest documents, URLs, or text into a knowledge base
- User wants to query, compile, or maintain wiki articles
- User needs deep research to fill knowledge gaps
- User wants to initialize a new wiki vault

## When NOT to Use

- One-off Q&A without persistent knowledge storage
- Note-taking without cross-referencing or structure
- Non-text content management (images, videos alone)

## Core Principles

1. **raw/ is immutable** — sources are never edited; re-ingest as new version
2. **purpose.md anchors direction** — read on every operation, align output with wiki goals
3. **Classify before extract** — determine entity type during Ingest, choose chapter structure during Compile
4. **Analyze before generate** — two-step Compile: structured analysis → article generation
5. **Backlink audit is mandatory** — bidirectional links are the knowledge graph
6. **Query answers must be archived** — good answers are compounding fuel
7. **Token budget first** — always read index before full articles (L0→L1→L2→L3)
8. **Human verifies, LLM maintains** — LLM writes, user steers

## Pipeline

| Stage | Input | Output |
|-------|-------|--------|
| **Ingest** | URLs, files, text | `raw/` (immutable) + hash cache |
Read the full skill on GitHub

Details

Skill name
karpathy-wiki
Repository
SherwinQ/karpathy-wiki
License
MIT
Repo updated
28 April 2026

FAQ

What does the Karpathy Wiki skill do?

Use when building or maintaining a personal knowledge base with LLM assistance. Triggers on ingesting sources, compiling wiki articles, querying knowledge, running health checks, deep research, or initializing a new wiki vault. Based on Karpathy's LLM Wiki pattern with Obsidian integration.

How do I install the Karpathy Wiki skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add SherwinQ/karpathy-wiki --skill karpathy-wiki. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Karpathy Wiki popular?

It lives in SherwinQ/karpathy-wiki, which has 117 GitHub stars and 17 forks.

Related skills

Mcd Saver

136

yuxinlaile/McD-saver

麦麦省钱助手——基于麦当劳中国官方 MCP Server 的省钱点餐技能。当用户提到麦当劳、麦乐送、麦麦、点麦当劳、想省钱/薅羊毛/领券/优惠、查优惠怎么用、积分兑换、麦麦商城、积分抽奖、麦当劳活动，或询问"怎么点麦当劳最划算"时使用本技能。核心能力：在下单前自动完成"领券→选券→比价→积分抵扣评估"，用 35 个官方工具帮用户以最低价格吃到同样的麦当劳。

AI, LLMs & Agents

Humanizer Indonesia

117

adhiprib/humanizer-indonesia

Menyunting teks bahasa Indonesia agar tidak terbaca sebagai tulisan AI atau terjemahan, dan kembali ke gaya penulis. Juga untuk mengaudit berkas yang sudah disunting model lain. Trigger: /humanizer-id, humanize, rapikan bahasa, biar tidak kaku, lebih mengalir, cek gaya, audit hasil Gemini.

AI, LLMs & Agents18

AI Tryon

103

wzj177/shop-tryon-skill

AI 虚拟试穿 Agent。用户提供服装信息（图片或文字描述均可）， Agent 全程引导完成：服装图预处理 → AI 生成模特 → 虚拟试穿合成 → 生成展示视频。 支持阿里云百炼试衣 API、豆包 Seedream 生图、豆包 Seedance 生视频。 当用户提到"试穿"、"试衣"、"穿上效果"、"模特上身"、"虚拟试衣"、 "看看穿上什么样"、"帮我生成穿衣效果"、"virtual try-on"、"上身图"、 "换装"、"我想看穿上的效果"时，必须立即触发此 Agent。

AI, LLMs & Agents22

Avoid AI Design

136

funboy322/avoid-ai-design

Audit and rewrite frontend UI to remove generic AI design patterns ("AI slop"), both the first-order defaults (purple gradients, Inter, a centered hero over three cards, untouched shadcn) and the second-order "tasteful AI" ones (cream with terracotta, near-black with acid green, all-caps mono chrome, one accented headline word, decorative 01/02/03). Use when asked to "de-slop a UI", "make a design look less AI-generated", "audit a page or component for AI design tells", "fix Claude/Codex-generated frontend that looks generic", or keep a multi-page site on one design system. Covers HTML/CSS and

AI, LLMs & Agents

Mcd Agent Gourmet

150

polaris-smart/mcd-agent-gourmet

麦门点餐议事会。用户想按预算和口味比较完整的麦当劳餐单，或问“我的券快过期了吗”“这顿能用哪张券”时使用。先确认门店与到店/配送，保留有糖无糖和冰量偏好；分清券包、时段和门店适用性，再使用官方 MCP 核价。只查询核价，不领券不下单。

AI, LLMs & Agents

Docmancer

133

docmancer/docmancer

Work from the same local memory as every other coding agent on this machine. Recall prior decisions, preferences, instructions, and project conventions that Claude Code, Codex, Cursor, and other agents wrote here, with cited sources, fully local. Also searches a separate local technical-documentation index.

AI, LLMs & Agents12

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.