andrej-karpathy
Skill0 starsChanged 7 months agoMITView on GitHub
Andrej Karpathy's cognitive patterns — practical AI educator who debugs prompts like code
1 other project uses a version of this.
Adopted by
Most recently taken up by
- TheHiddenDeveloper/jarvis-skillstheir own version, first seen Aug 19, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- TheHiddenDeveloper/jarvis-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
Files
Andrej Karpathy
Andrej Karpathy's cognitive patterns -- practical AI educator who debugs prompts like code.
Architecture
This is a cognitive mind -- a 5-layer cognitive architecture, not a flat advisor.
| Layer | File | Purpose |
| 1. Boot | AGENT.md | Identity, principles, cognitive patterns |
| 2. Cognitive Core | references/cognitive-core.md | Biography, architecture, singularity |
| 3. Personality | references/personality.md | Behavioral matrix, style, interaction |
| 4. Knowledge | references/knowledge-base.md | Domain depth + boundaries |
| 5. Reasoning | references/reasoning-engine.md | Patterns, models, triggers |
Install
myclaude install andrej-karpathyUsage
This mind activates as a Claude Code agent:
/andrej-karpathy "How do I structure a complex prompt for code review?"Or invoke via the Agent tool in any conversation where practical AI thinking is needed.
Requirements
- Claude Code >= 1.0.0
- Model: claude-opus-4-6 (recommended for cognitive depth)
What Makes This Different
Not a generic "act as Karpathy" prompt. This is a 5-layer cognitive architecture built from forensic analysis of 475,000 words across 13 years of Karpathy's writing, talks, and code. It captures the debugging hierarchy, the from-scratch pedagogy, the linguistic fingerprint ("turns out", "magical", staccato rhythm), and the cognitive immune system that makes Karpathy's thinking distinctive.
Image: MCS Level 1 Image: Available on myclaude.sh
Published on myclaude.sh | Built with MyClaude Studio Engine
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.