
Karpathy Methodology
- 23 installs
- 82 repo stars
- Updated July 10, 2026
- learnprompt/andrej-karpathy-skills
Helps with ai & agent building tasks.
About
karpathy-methodology is a Claude Code skill for ai & agent building. It helps solo builders move faster with AI-assisted coding.
- karpathy-methodology
- AI & Agent Building
- AI-coding skill
Karpathy Methodology by the numbers
- 23 all-time installs (skills.sh)
- +5 installs in the week ending Aug 2, 2026 (Skillselion tracking)
- Ranked #10,032 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Aug 2, 2026 (Skillselion catalog sync)
npx skills add https://github.com/learnprompt/andrej-karpathy-skills --skill karpathy-methodologyAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 23 |
|---|---|
| repo stars | ★ 82 |
| Last updated | July 10, 2026 |
| Repository | learnprompt/andrej-karpathy-skills ↗ |
What it does
Helps with ai & agent building tasks.
Files
Karpathy Methodology — 14 Core Skills
Distilled from Andrej Karpathy's most-liked posts on X (2023–2026), his LLM Wiki Gist, and the multica-ai/andrej-karpathy-skills repo.
Source: https://x.com/karpathy | https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f
This skill is the master index. When invoked, either: 1. Apply the specific sub-methodology relevant to the user's current task, or 2. Guide the user to the right one from the 14 below.
---
The 14 Methodologies
| # | Skill Name | One-line Essence |
|---|---|---|
| 1 | karpathy-agentic-engineering | Orchestrate agents with clear tasks and verifiable success criteria |
| 2 | karpathy-llm-wiki | Let LLM maintain your knowledge base; you do the exploring |
| 3 | karpathy-llm-simulator | Ask LLM to simulate expert debate, not give one opinion |
| 4 | karpathy-minimalism | 200 lines of pure Python beats 50 npm packages |
| 5 | karpathy-vibe-to-agentic | Vibe coding raises the floor; agentic engineering raises the ceiling |
| 6 | karpathy-autoresearch | Agent loops on git branches; you only change the prompt |
| 7 | karpathy-output-evolution | Text → Markdown → HTML → rendered; always demand structure |
| 8 | karpathy-understanding-first | Outsource thinking, never understanding |
| 9 | karpathy-idea-files | Ship the Gist (abstract + criteria), not the code |
| 10 | karpathy-meta-reflection | Monthly audit: what's atrophying, what's exploding |
| 11 | karpathy-supply-chain-hygiene | Every dependency is an attack surface |
| 12 | karpathy-education-first | Make everything teachable; nano-projects over monoliths |
| 13 | karpathy-system-prompt-learning | Write strategy into the system prompt like a textbook |
| 14 | karpathy-practice-environments | Build gyms where agents can try, fail, and learn |
---
Meta-Principle (the one that unifies all 14)
"You can outsource your thinking but you cannot outsource your understanding."
— Karpathy, ~46k likes, 2026
Use AI to go faster. Use your brain to know if you're going in the right direction.
---
How to Apply This Skill
Quick Decision Tree
"I need to build/code something" → Start with #1 Agentic Engineering (clear task + success criteria), layer in #4 Minimalism (avoid bloat), finish with #8 Understanding First (verify what was built).
"I need to research/learn something" → #2 LLM Wiki for building knowledge, #3 LLM Simulator for challenging assumptions, #10 Meta-Reflection for calibrating what to learn next.
"I need to make a decision" → #3 LLM Simulator (debate mode), then #8 Understanding First (own your conclusion).
"I'm designing a product/tool" → #4 Minimalism + Agent-Native, #14 Practice Environments, #12 Education First.
"I want to share an idea" → #9 Idea Files (Gist first), #7 Output Evolution (structured output), #12 Education First (teachable).
"I'm doing ML research" → #6 AutoResearch, #13 System Prompt Learning, #14 Practice Environments.
---
Master Prompt Template
When the user hasn't specified a sub-methodology, use this all-in-one Karpathy-style framing:
You are operating under the Karpathy Methodology.
Core constraints:
1. UNDERSTAND before outsourcing — never ship what you can't explain
2. MINIMIZE dependencies — prefer 200-line pure implementations
3. AGENT-NATIVE outputs — CLI-friendly, markdown-structured, LLM-legible
4. VERIFIABLE goals — every task must have a testable success criterion
5. TEACH as you build — outputs should be understandable by a curious beginner
Task: [USER_TASK]
Success criteria: [WHAT_DONE_LOOKS_LIKE]
Constraints: [TECH_STACK, SIZE_LIMIT, NO_LIBS]---
Source Posts (Top by Likes)
1. 145k likes — Joins Anthropic: https://x.com/karpathy/status/2056753169888334312 2. 59k likes — LLM Knowledge Bases: https://x.com/karpathy/status/2039805659525644595 3. 56k likes — "Never felt this behind as a programmer": https://x.com/karpathy/status/2004607146781278521 4. 46k likes — "Outsource thinking not understanding": https://x.com/karpathy/status/2049907410303865030 5. 40k likes — Claude coding notes: https://x.com/karpathy/status/2015883857489522876 6. 37k likes — Programming phase shift: https://x.com/karpathy/status/2026731645169185220 7. 31k likes — LLM argue the opposite: https://x.com/karpathy/status/2037921699824607591 8. 28k likes — AutoResearch project: https://x.com/karpathy/status/2030371219518931079 9. 28k likes — litellm supply chain attack: https://x.com/karpathy/status/2036487306585268612 10. 25k likes — 243 lines pure Python GPT: https://x.com/karpathy/status/2021694437152157847 11. 22k likes — Agent network discussion: https://x.com/karpathy/status/2017442712388309406 12. 19k likes — HTML output + I/O evolution: https://x.com/karpathy/status/2053872850101285137 13. 27k likes — LLM Wiki Gist version: https://x.com/karpathy/status/2040470801506541998
Karpathy Methodology — 14 Skills Reference
Distilled from Andrej Karpathy's top X posts (2023–2026)
Installed at: ~/.clacky/skills/karpathy-*/Master skill: karpathy-methodologyQuick Reference
| # | Skill | Invoke When... |
|---|---|---|
| 0 | karpathy-methodology | Not sure which sub-skill to use; Karpathy-style approach overview |
| 1 | karpathy-agentic-engineering | Setting up agent workflows, writing CLAUDE.md, orchestrating agents |
| 2 | karpathy-llm-wiki | Building personal knowledge base, ingesting papers, Obsidian + LLM |
| 3 | karpathy-llm-simulator | Making important decisions, stress-testing ideas, debate mode |
| 4 | karpathy-minimalism | Reducing dependencies, auditing packages, agent-native design |
| 5 | karpathy-vibe-to-agentic | Leveling up a prototype to production-quality |
| 6 | karpathy-autoresearch | Automating ML experiments, agent research loops |
| 7 | karpathy-output-evolution | Better output format — HTML, Marp slides, structured rendering |
| 8 | karpathy-understanding-first | Verifying AI-built work, anti-atrophy, capability mapping |
| 9 | karpathy-idea-files | Capturing ideas as specs before building, Gist-first sharing |
| 10 | karpathy-meta-reflection | Monthly career audit, skills atrophy review |
| 11 | karpathy-supply-chain-hygiene | Dependency audits, supply chain risk, security hardening |
| 12 | karpathy-education-first | Making things teachable, nano-projects, beginner explanations |
| 13 | karpathy-system-prompt-learning | Writing better system prompts, encoding strategy into prompts |
| 14 | karpathy-practice-environments | Building eval gyms, agent practice loops, RL-style environments |
Source Posts
All skills trace back to Karpathy's most-liked posts:
- https://x.com/karpathy (profile)
- https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f (LLM Wiki Gist)
- https://github.com/multica-ai/andrej-karpathy-skills (community repo)
Installation Location
~/.clacky/skills/
├── karpathy-methodology/ ← master index (start here)
├── karpathy-agentic-engineering/
├── karpathy-llm-wiki/
├── karpathy-llm-simulator/
├── karpathy-minimalism/
├── karpathy-vibe-to-agentic/
├── karpathy-autoresearch/
├── karpathy-output-evolution/
├── karpathy-understanding-first/
├── karpathy-idea-files/
├── karpathy-meta-reflection/
├── karpathy-supply-chain-hygiene/
├── karpathy-education-first/
├── karpathy-system-prompt-learning/
└── karpathy-practice-environments/The One Principle That Unifies All 14
"You can outsource your thinking but you cannot outsource your understanding."
— Andrej Karpathy, ~46k likes