Agent skill

Karpathy LLM Wiki

by LearnPrompt in LearnPrompt/andrej-karpathy-skills

Build and maintain an LLM-powered personal knowledge base or wiki.

MITAuto-check passedKnowledge Management

Install Karpathy LLM Wiki

skills CLI
$ npx skills add LearnPrompt/andrej-karpathy-skills --skill karpathy-llm-wiki -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install LearnPrompt/andrej-karpathy-skills karpathy-llm-wiki --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/LearnPrompt/andrej-karpathy-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/karpathy-llm-wiki .claude/skills/karpathy-llm-wiki && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
karpathy-llm-wiki
GitHub stars
110
Token cost
~1.4k tokens
SKILL.md length
189 words
Files
1
Skills in repo
15
Repo updated
First seen
Licence
MIT

At a glance

Build and maintain an LLM-powered personal knowledge base or wiki.

  • Works in 5 steps: Ingest Prompt → Compile Wiki Entry Prompt → Weekly Ingest Prompt (run every week) → …
  • The user wants to organize research notes
  • SKILL.md covers Core Principle, Architecture, The 5 Core Prompts and Memory / Context Hygiene…, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Karpathy LLM Wiki is an agent skill from LearnPrompt/andrej-karpathy-skills. Build and maintain an LLM-powered personal knowledge base or wiki. Use this skill when the user wants to organize research notes, build a second brain, set up an Obsidian vault with LLM compilation, ingest papers or articles automatically, or mentions "personal knowledge base", "LLM wiki", "second brain", "knowledge management", "ingest papers", "obsidian + LLM". Based on Karpathy Gist and 59k-like post.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Knowledge Management, covering LLM wikis and Second brain. It works with Obsidian. The repository describes itself as: Karpathy-inspired Agent Skills collection. The licence is MIT.

When your agent uses it

  • The user wants to organize research notes
  • Build a second brain
  • Set up an Obsidian vault with LLM compilation
  • Articles automatically

Example prompts

  • “personal knowledge base”
  • “LLM wiki”
  • “second brain”
  • “/karpathy-llm-wiki”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Ingest Prompt
  2. Compile Wiki Entry Prompt
  3. Weekly Ingest Prompt (run every week)
  4. Lint / Contradiction Check Prompt
  5. Query Prompt

What it can do on your machine

Read from SKILL.md and the folder at commit 9e46dec. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • x.com
    • gist.github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Karpathy LLM Wiki loads about 1.4k tokens when it runs. Until then it costs about 106 tokens; SKILL.md has 189 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~106
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from LearnPrompt/andrej-karpathy-skills at commit 9e46dec, republished under its MIT licence (© LearnPrompt). 189 words, ~1,415 tokens.

Download SKILL.mdSave it as .claude/skills/karpathy-llm-wiki/SKILL.md (or your agent's skills folder).
name
karpathy-llm-wiki
description
Build and maintain an LLM-powered personal knowledge base or wiki. Use this skill when the user wants to organize research notes, build a second brain, set up an Obsidian vault with LLM compilation, ingest papers or articles automatically, or mentions "personal knowledge base", "LLM wiki", "second brain", "knowledge management", "ingest papers", "obsidian + LLM". Based on Karpathy Gist and 59k-like post.
disable-model-invocation
false
user-invocable
true
related_skills
karpathy-autoresearch, karpathy-output-evolution, karpathy-education-first, karpathy-idea-files

Skill 2: LLM Wiki / Personal Knowledge Base(LLM知识库)

Source: https://x.com/karpathy/status/2039805659525644595 | https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f "59k likes — LLM Knowledge Bases" — top-2 most-liked post

Core Principle

You explore. The LLM maintains.

You read the world, capture raw signals. The LLM compiles, cross-links, deduplicates, lint-checks, and surfaces contradictions. Your Obsidian vault is the output, not the input.

Architecture

RAW INPUTS                 LLM LAYER                  OUTPUT
──────────                 ─────────                  ──────
Papers (PDF/arXiv)  ──→   ingest.py              ──→  entities/*.md
Articles (URL)      ──→   compile_wiki.py        ──→  index.md
Chat logs           ──→   lint_wiki.py           ──→  contradiction_log.md
Notes (voice/text)  ──→   query_wiki.py          ──→  slides/
                          update_entity.py       ──→  weekly_digest.md

The 5 Core Prompts

1. Ingest Prompt
You are a knowledge compiler. Given this raw source:

[PASTE RAW CONTENT]

Source URL/title: [SOURCE]
Date: [DATE]

Extract and output:
1. Key entities (people, concepts, tools, papers) — one per line with a 2-sentence description
2. Key claims with confidence level (high/medium/speculative)
3. Connections to existing topics: [LIST YOUR KNOWN TOPICS]
4. Contradictions with anything you know: [WHAT YOU ALREADY BELIEVE]
5. Suggested entity page updates (format: ENTITY_NAME | UPDATE_TEXT)
2. Compile Wiki Entry Prompt
You are maintaining a personal knowledge wiki. Update the entity page for [ENTITY_NAME].

Existing page content:
[CURRENT_PAGE_CONTENT]

New information to integrate:
[NEW_INFO]

Rules:
- Preserve all existing information; only add or correct
- Flag contradictions with: ⚠️ CONFLICT: [old claim] vs [new claim]
- Keep the page under 500 words
- End with: "Last updated: [DATE] | Sources: [LINKS]"
3. Weekly Ingest Prompt (run every week)
Process this week's reading list:
[PASTE 5-10 ITEMS: title + URL + 1-sentence summary]

For each item:
1. Extract top 3 entities to update
2. List 2-3 key claims worth adding to wiki
3. Note any contradictions with existing knowledge
4. Suggest connections to other entities in my wiki

Output as structured markdown, one section per item.
4. Lint / Contradiction Check Prompt
Review these wiki entries for consistency:

[PASTE 3-5 RELATED ENTITY PAGES]

Find and report:
1. Factual contradictions between pages
2. Duplicate information that should be merged
3. Outdated claims that should be flagged
4. Missing cross-links between related entities

Format: ISSUE | PAGE | LINE | SUGGESTED FIX
5. Query Prompt
Search my personal knowledge wiki to answer this question:

Question: [QUESTION]

Wiki context:
[PASTE RELEVANT PAGES]

Answer with:
1. Direct answer (2-3 sentences)
2. Supporting evidence from wiki (with page citations)
3. Gaps: what I don't know yet
4. Suggested reading to fill gaps

Memory / Context Hygiene (Anti-Pollution Rules)

Karpathy noted LLM memory "trying too hard" — a question from 2 months ago poisons every future conversation. Prevent this:

  • Never rely on LLM built-in memory for knowledge — use your wiki instead
  • Start fresh sessions for new topics; don't let old context bleed in
  • Explicit resets: If continuing a long session, open with "Ignore all prior context about X"
  • Version your wiki: Commit wiki changes with git so you can diff what changed

Folder Structure (Obsidian-Compatible)

wiki/
├── entities/
│   ├── people/
│   │   └── andrej-karpathy.md
│   ├── concepts/
│   │   ├── agentic-engineering.md
│   │   └── llm-simulator.md
│   └── tools/
│       └── claude.md
├── index.md              ← master entity list, auto-updated
├── contradiction_log.md  ← conflicts to resolve
├── weekly_digest/
│   └── 2026-W21.md
└── raw/                  ← source dumps before compilation

Weekly Cadence

Monday:    Dump week's reads into raw/
Tuesday:   Run ingest prompt on each item
Wednesday: Run lint/contradiction check
Thursday:  Update entity pages
Friday:    Generate weekly_digest.md with LLM

Workflow

属于工作流:研究到发布(内容创作者/研究者)

位置上游下游
第2步karpathy-autoresearch(研究产出原始素材)karpathy-output-evolution(将知识转化为可发布形式)

完整链路:autoresearch → llm-wiki → output-evolution → education-first

也在月度体检工作流中用于持久化反思结论。

Prompt Contract

text
Maintain this as an LLM wiki. From the new sources provided, update existing Markdown pages, create only necessary new pages, preserve all citations and source links, flag any contradictions with existing knowledge, and output a structured change log showing: pages updated, new pages created, contradictions found, and open questions.

Verification Checklist

  • 原始来源(raw sources)保持不可变
  • 每个 wiki 页面有来源链接
  • 矛盾之处被明确标记(不是静默覆盖)
  • changelog 记录了本次更新的所有变更
  • 没有创建不必要的新页面(优先更新已有页面)
  • 可以从 index 页面导航到任何实体

© LearnPrompt, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in karpathy-llm-wiki of LearnPrompt/andrej-karpathy-skills.

Open the folder on GitHubat commit 9e46dec

Compare with similar skills

Karpathy LLM Wiki next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Karpathy LLM Wiki compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Karpathy LLM Wiki this skillLearnPrompt/andrej-karpathy-skills110—~1.4kAutomated safety check: PassMIT
Karpathy WikiSherwinQ/karpathy-wiki114—~967Automated safety check: PassMIT
My LLM WikiMartinLwx/dotfiles140—~2.7kAutomated safety check: PassNone
Obsidian Knowledge BuilderMichael-OvO/obsidian-knowledge-agent205—~917Automated safety check: PassMIT
AI Second Braincharlie947/ai-second-brain189—~3.5kAutomated safety check: PassMIT
LLM Wikiinfranodus/skills119—~8.6kAutomated safety check: NotesNone

Similar skills

  • Karpathy Wiki

    SherwinQ/karpathy-wiki

    A skill your agent uses when building or maintaining a personal knowledge base with LLM assistance.

    114 GitHub stars~967 tokensUpdated 5 mo ago
    Knowledge ManagementAuto-check passed
  • My LLM Wiki

    MartinLwx/dotfiles

    Provides access to the user's personal wiki, including notes, research, project documentation, decisions, and archived knowledge.

    140 GitHub stars~2.7k tokensUpdated 2 days ago
    Knowledge ManagementAuto-check passed
  • Obsidian Knowledge Builder

    Michael-OvO/obsidian-knowledge-agent

    Turns PDFs, slides, syllabi, papers and transcripts into structured, teaching-quality Obsidian notes, matching how much structure is built to how much the material needs.

    205 GitHub stars~917 tokensUpdated 3 mo ago
    Knowledge ManagementAuto-check passed
  • AI Second Brain

    charlie947/ai-second-brain

    Walks the user through Charlie Hills's AI Second Brain + Karpathy Wiki setup from the MarTech AI newsletter.

    189 GitHub stars~3.5k tokensUpdated 5 mo ago
    Knowledge ManagementAuto-check passed
  • LLM Wiki

    infranodus/skills

    Guide users through setting up a personal LLM-maintained wiki — a persistent, compounding knowledge base where the LLM incrementally builds and maintains interlinked markdown pages from raw sources.

    119 GitHub stars~8.6k tokensUpdated 20 days ago
    Knowledge ManagementAuto-check: notes
  • Obsidian CLI Read Transport

    AgriciDaniel/claude-obsidian

    Detects and uses the official Obsidian command-line interface for read-only vault access, falling back to direct file reads, while all mutations stay on a separate transaction core.

    15k GitHub stars~762 tokensUpdated 1 mo ago
    Knowledge ManagementAuto-check passed

More from LearnPrompt/andrej-karpathy-skills

All 15 skills in this repo
  • Karpathy Methodology Index

    LearnPrompt/andrej-karpathy-skills

    Apply Andrej Karpathy AI methodology and principles from his 2023-2026 insights. Use this skill when the user wants to apply Karpathy-style thinking, needs…

    110 GitHub stars~1.5k tokensUpdated 3 mo ago
    Auto-check passed
  • Karpathy Agentic Engineering

    LearnPrompt/andrej-karpathy-skills

    Apply Karpathy-style agentic engineering to any coding or building task.

    110 GitHub stars~1.2k tokensUpdated 3 mo ago
    Auto-check passed
  • AutoResearch Loop

    LearnPrompt/andrej-karpathy-skills

    Sets up an autonomous research loop where an agent runs experiments on git branches, logs results and proposes the next iteration while you approve each hypothesis change.

    110 GitHub stars~1.4k tokensUpdated 3 mo ago
    Auto-check passed
  • Karpathy Education First

    LearnPrompt/andrej-karpathy-skills

    Apply the education-first mindset — make everything you build teachable, create nano-project explanations, write for beginners.

    110 GitHub stars~1.8k tokensUpdated 3 mo ago
    Auto-check passed
  • Karpathy Idea Files

    LearnPrompt/andrej-karpathy-skills

    Create and share ideas as abstract Gist-style specs instead of code — letting agents or others implement.

    110 GitHub stars~1.5k tokensUpdated 3 mo ago
    Auto-check passed
  • Karpathy LLM Simulator

    LearnPrompt/andrej-karpathy-skills

    Use LLM as a simulator of expert debates and opposing viewpoints instead of getting a single sycophantic answer.

    110 GitHub stars~1.3k tokensUpdated 3 mo ago
    Auto-check passed

Works with

Questions about Karpathy LLM Wiki

What does Karpathy LLM Wiki do?

Build and maintain an LLM-powered personal knowledge base or wiki. Karpathy LLM Wiki is an agent skill from LearnPrompt/andrej-karpathy-skills. Build and maintain an LLM-powered personal knowledge base or wiki.

When should I use Karpathy LLM Wiki?

Karpathy LLM Wiki fits situations like: the user wants to organize research notes; build a second brain; set up an Obsidian vault with LLM compilation; articles automatically.

How do I install Karpathy LLM Wiki in Claude Code?

Run `npx skills add LearnPrompt/andrej-karpathy-skills --skill karpathy-llm-wiki -a claude-code`. Or copy the skill folder (karpathy-llm-wiki in LearnPrompt/andrej-karpathy-skills) into .claude/skills/karpathy-llm-wiki in your project. Claude Code loads it when a task matches its description.

How do I install Karpathy LLM Wiki in Codex?

Run `npx skills add LearnPrompt/andrej-karpathy-skills --skill karpathy-llm-wiki -a codex`. Or copy the skill folder (karpathy-llm-wiki in LearnPrompt/andrej-karpathy-skills) into .agents/skills/karpathy-llm-wiki in your project. Codex loads it when a task matches its description.

Can I use Karpathy LLM Wiki in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LearnPrompt/andrej-karpathy-skills --skill karpathy-llm-wiki -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/karpathy-llm-wiki, .gemini/skills/karpathy-llm-wiki, .github/skills/karpathy-llm-wiki and .opencode/skills/karpathy-llm-wiki in your project.

What does Karpathy LLM Wiki need to run?

SKILL.md names no scripts, command-line tools or credentials: Karpathy LLM Wiki is instructions for the agent only.

Does Karpathy LLM Wiki access the network?

SKILL.md names 2 domains. As links in the text: x.com and gist.github.com. This is read from the text; nothing was executed.

Is Karpathy LLM Wiki safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Karpathy LLM Wiki use?

Karpathy LLM Wiki is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Karpathy LLM Wiki use?

About 1.4k tokens (SKILL.md is roughly 5.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Karpathy LLM Wiki?

Skills that share tags, products or a category with Karpathy LLM Wiki: Karpathy Wiki (SherwinQ/karpathy-wiki, 114 stars), My LLM Wiki (MartinLwx/dotfiles, 140 stars), Obsidian Knowledge Builder (Michael-OvO/obsidian-knowledge-agent, 205 stars) and AI Second Brain (charlie947/ai-second-brain, 189 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Karpathy LLM Wiki?

LearnPrompt (a GitHub user) maintains it in LearnPrompt/andrej-karpathy-skills, which has 110 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on July 10, 2026.

Source: LearnPrompt/andrej-karpathy-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.