Transition from vibe coding (fast prototyping) to agentic engineering (rigorous iteration).
$ npx skills add LearnPrompt/andrej-karpathy-skills --skill karpathy-vibe-to-agentic -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install LearnPrompt/andrej-karpathy-skills karpathy-vibe-to-agentic --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/LearnPrompt/andrej-karpathy-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/karpathy-vibe-to-agentic .claude/skills/karpathy-vibe-to-agentic && rm -rf skills-srcUse ~/.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/
Install the "karpathy-vibe-to-agentic" agent skill from https://github.com/LearnPrompt/andrej-karpathy-skills/tree/main/karpathy-vibe-to-agentic into .claude/skills/karpathy-vibe-to-agentic/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "karpathy-vibe-to-agentic", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/LearnPrompt/andrej-karpathy-skills/tree/main/karpathy-vibe-to-agenticType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add LearnPrompt/andrej-karpathy-skills --skill karpathy-vibe-to-agentic -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install LearnPrompt/andrej-karpathy-skills karpathy-vibe-to-agentic --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LearnPrompt/andrej-karpathy-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/karpathy-vibe-to-agentic .agents/skills/karpathy-vibe-to-agentic && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "karpathy-vibe-to-agentic" agent skill from https://github.com/LearnPrompt/andrej-karpathy-skills/tree/main/karpathy-vibe-to-agentic into .agents/skills/karpathy-vibe-to-agentic/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "karpathy-vibe-to-agentic", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LearnPrompt/andrej-karpathy-skills --skill karpathy-vibe-to-agentic -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install LearnPrompt/andrej-karpathy-skills karpathy-vibe-to-agentic --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LearnPrompt/andrej-karpathy-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/karpathy-vibe-to-agentic .cursor/skills/karpathy-vibe-to-agentic && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "karpathy-vibe-to-agentic" agent skill from https://github.com/LearnPrompt/andrej-karpathy-skills/tree/main/karpathy-vibe-to-agentic into .cursor/skills/karpathy-vibe-to-agentic/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "karpathy-vibe-to-agentic", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/LearnPrompt/andrej-karpathy-skills.git --path karpathy-vibe-to-agentic--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add LearnPrompt/andrej-karpathy-skills --skill karpathy-vibe-to-agentic -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install LearnPrompt/andrej-karpathy-skills karpathy-vibe-to-agentic --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LearnPrompt/andrej-karpathy-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/karpathy-vibe-to-agentic .gemini/skills/karpathy-vibe-to-agentic && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "karpathy-vibe-to-agentic" agent skill from https://github.com/LearnPrompt/andrej-karpathy-skills/tree/main/karpathy-vibe-to-agentic into .gemini/skills/karpathy-vibe-to-agentic/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "karpathy-vibe-to-agentic", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install LearnPrompt/andrej-karpathy-skills karpathy-vibe-to-agenticInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add LearnPrompt/andrej-karpathy-skills --skill karpathy-vibe-to-agentic -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/LearnPrompt/andrej-karpathy-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/karpathy-vibe-to-agentic .github/skills/karpathy-vibe-to-agentic && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "karpathy-vibe-to-agentic" agent skill from https://github.com/LearnPrompt/andrej-karpathy-skills/tree/main/karpathy-vibe-to-agentic into .github/skills/karpathy-vibe-to-agentic/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "karpathy-vibe-to-agentic", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LearnPrompt/andrej-karpathy-skills --skill karpathy-vibe-to-agentic -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install LearnPrompt/andrej-karpathy-skills karpathy-vibe-to-agentic --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LearnPrompt/andrej-karpathy-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/karpathy-vibe-to-agentic .opencode/skills/karpathy-vibe-to-agentic && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "karpathy-vibe-to-agentic" agent skill from https://github.com/LearnPrompt/andrej-karpathy-skills/tree/main/karpathy-vibe-to-agentic into .opencode/skills/karpathy-vibe-to-agentic/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "karpathy-vibe-to-agentic", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
karpathy-vibe-to-agenticTransition from vibe coding (fast prototyping) to agentic engineering (rigorous iteration).
Karpathy Vibe To Agentic is an agent skill from LearnPrompt/andrej-karpathy-skills. Transition from vibe coding (fast prototyping) to agentic engineering (rigorous iteration). Use this skill when the user has a rough prototype and wants to level it up, needs to go from "it kind of works" to production-quality, wants to understand the difference between vibe coding and agentic coding, or says "polish this", "make this production-ready", "level up from prototype", "vibe coded this now what". Based on Karpathy posts 3 and 6.
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 Development, covering Prototyping. The repository describes itself as: Karpathy-inspired Agent Skills collection. The licence is MIT.
3 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 9e46dec. It shows what the files ask for, not the result of running them.
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.
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.
Links to these hosts (documentation or services it may open):
x.comFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Karpathy Vibe To Agentic loads about 1.4k tokens when it runs. Until then it costs about 117 tokens; SKILL.md has 196 words of instructions outside code blocks.
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.
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.
The full file from LearnPrompt/andrej-karpathy-skills at commit 9e46dec, republished under its MIT licence (© LearnPrompt). 196 words, ~1,380 tokens.
.claude/skills/karpathy-vibe-to-agentic/SKILL.md (or your agent's skills folder).Source: https://x.com/karpathy/status/2004607146781278521 | https://x.com/karpathy/status/2026731645169185220 "I've never felt this much behind as a programmer" — 56k likes
Vibe coding raises the floor. Agentic engineering raises the ceiling.
They're not the same thing and you need both:
| Vibe Coding | Agentic Engineering | |
|---|---|---|
| Goal | Fast prototype, explore ideas | Reliable, maintainable, verifiable |
| How | Natural language → run it | Task specs + success criteria + loops |
| When | First 20% (exploration) | Last 80% (execution) |
| Risk | You don't understand what you built | Agent doesn't understand what you want |
| Karpathy says | "raises the floor" | "raises the ceiling" |
When you have a vibe-coded prototype and need to level it up:
I vibe-coded this [project/script/app]. I need to understand what I actually have before leveling it up.
[PASTE CODE OR DESCRIBE IT]
Please:
1. Describe exactly what this does in plain English (3-5 sentences)
2. List every assumption baked in (hardcoded values, expected input format, etc.)
3. Identify the 3 most likely failure modes
4. List what's missing for this to be production-ready
5. What would break if I ran this on a different machine / with different data?
Be blunt. I'm about to invest more time in this and need to know if it's worth it.Based on this audit of my prototype:
[AUDIT OUTPUT FROM STEP 1]
Help me define clear, verifiable success criteria for the "production-ready" version.
Format each criterion as a testable assertion:
- GIVEN [input/condition]
- WHEN [action]
- THEN [expected output/behavior]
List 5-7 criteria. Start with the most important.You are a senior engineer reviewing this prototype. Your job is to systematically improve it.
Prototype: [CODE]
Success criteria: [FROM STEP 2]
Work incrementally:
1. First fix: address the most critical issue only (one diff)
2. After I approve each fix, suggest the next
3. Never refactor unrelated code
4. For each fix, explain: WHAT changed, WHY this matters, RISK of this change
Start with fix #1.Review this vibe-coded project for these specific anti-patterns:
[PASTE CODE]
Check for:
1. Hardcoded credentials, paths, or magic numbers → suggest config/env vars
2. No error handling on file I/O or network calls → add try/except with clear messages
3. print() debugging left in → identify and offer to remove
4. Functions doing 3+ things → suggest split points
5. No way to run without human supervision → suggest automation hooks
6. Dependencies that aren't in requirements.txt / package.json
For each issue found: show the exact line and suggest the minimal fix.Karpathy runs these in parallel:
TRACK A (IDE / Human) TRACK B (Agent)
───────────────────── ───────────────
- Review diffs - Implement incrementally
- Apply taste/judgment - Run tests automatically
- Verify understanding - Suggest next steps
- Commit good work - Generate options
- Ask "is this right?" - Never commit autonomouslyAlways keep a human in the loop for the taste judgment. Agents are for execution, not for deciding what's worth building.
For fast one-shot upgrade of a simple vibe script:
Upgrade this vibe-coded script to production quality.
[PASTE SCRIPT]
Requirements:
1. Add proper error handling (no unhandled exceptions)
2. Make all hardcoded values configurable via CLI args or env vars
3. Add a --dry-run flag that shows what would happen without doing it
4. Add basic logging (not print) with timestamps
5. Keep the core logic identical — only add robustness
6. Maximum 20% increase in line count
Output the complete upgraded script.属于工作流：想法到上线（开发者）
| 位置 | 上游 | 下游 |
|---|---|---|
| 第5步（收尾） | karpathy-supply-chain-hygiene（安全审查后） | 部署/交付 |
完整链路：idea-files → agentic-engineering → minimalism → supply-chain-hygiene → vibe-to-agentic
I have a vibe-coded prototype: <PASTE_CODE_OR_DESCRIBE>. Step 1: Audit — describe what it does, list hidden assumptions, identify failure modes, list what's missing for production. Step 2: Define 5-7 verifiable success criteria in GIVEN/WHEN/THEN format. Step 3: Start the agentic cleanup loop — one incremental fix at a time, explain WHAT/WHY/RISK for each.© LearnPrompt, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in karpathy-vibe-to-agentic of LearnPrompt/andrej-karpathy-skills.
Open the folder on GitHubat commit 9e46dec
Karpathy Vibe To Agentic 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Karpathy Vibe To Agentic this skillLearnPrompt/andrej-karpathy-skills | 110 | — | ~1.4k | Automated safety check: Pass | MIT | |
| Native Feel Cross Platform Desktopyetone/native-feel-skill | 1.9k | 1 repos | ~1.5k | Automated safety check: Pass | MIT | |
| Compound Engineering PrototypeEveryInc/compound-engineering-plugin | 25k | — | ~1.9k | Automated safety check: Pass | MIT | |
| Collaborating With CodexGuDaStudio/collaborating-with-codex | 132 | 1 repos | ~712 | Automated safety check: Pass | MIT | |
| Digikeyaklofas/kicad-happy | 1.4k | 1 repos | ~4.5k | Automated safety check: Pass | MIT | |
| Collaborating With Geminihaoyu-haoyu/Multi-AI-Workflow | 109 | — | ~521 | Automated safety check: Pass | MIT |
yetone/native-feel-skill
A skill your agent uses when the user is designing, prototyping, or rewriting a desktop app that must run on multiple OSes (macOS + Windows, optionally Linux) AND feel indistinguishable from a…
EveryInc/compound-engineering-plugin
Builds a throwaway prototype at just the fidelity needed to settle a specific how-it-should-work-or-feel question, before committing to an approach other work will treat as fixed.
GuDaStudio/collaborating-with-codex
Delegates coding tasks to Codex CLI for prototyping, debugging, and code review.
aklofas/kicad-happy
Search DigiKey for electronic components and download datasheets — primary source for prototype orders and the preferred API method for fetching datasheets.
haoyu-haoyu/Multi-AI-Workflow
Delegates coding tasks to Gemini CLI for prototyping, debugging, and code review.
adobe/spectrum-design-data
Look up Spectrum 2 (S2) component documentation, design guidelines, and usage patterns when building with React Spectrum or Spectrum Web Components.
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…
LearnPrompt/andrej-karpathy-skills
Apply Karpathy-style agentic engineering to any coding or building task.
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.
LearnPrompt/andrej-karpathy-skills
Apply the education-first mindset — make everything you build teachable, create nano-project explanations, write for beginners.
LearnPrompt/andrej-karpathy-skills
Create and share ideas as abstract Gist-style specs instead of code — letting agents or others implement.
LearnPrompt/andrej-karpathy-skills
Use LLM as a simulator of expert debates and opposing viewpoints instead of getting a single sycophantic answer.
Categories
Transition from vibe coding (fast prototyping) to agentic engineering (rigorous iteration). Karpathy Vibe To Agentic is an agent skill from LearnPrompt/andrej-karpathy-skills. Transition from vibe coding (fast prototyping) to agentic engineering (rigorous iteration).
Karpathy Vibe To Agentic fits situations like: the user has a rough prototype and wants to level it up; needs to go from it kind of works to production-quality; wants to understand the difference between vibe coding and agentic coding; says polish this.
Run `npx skills add LearnPrompt/andrej-karpathy-skills --skill karpathy-vibe-to-agentic -a claude-code`. Or copy the skill folder (karpathy-vibe-to-agentic in LearnPrompt/andrej-karpathy-skills) into .claude/skills/karpathy-vibe-to-agentic in your project. Claude Code loads it when a task matches its description.
Run `npx skills add LearnPrompt/andrej-karpathy-skills --skill karpathy-vibe-to-agentic -a codex`. Or copy the skill folder (karpathy-vibe-to-agentic in LearnPrompt/andrej-karpathy-skills) into .agents/skills/karpathy-vibe-to-agentic in your project. Codex loads it when a task matches its description.
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-vibe-to-agentic -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-vibe-to-agentic, .gemini/skills/karpathy-vibe-to-agentic, .github/skills/karpathy-vibe-to-agentic and .opencode/skills/karpathy-vibe-to-agentic in your project.
SKILL.md names no scripts, command-line tools or credentials: Karpathy Vibe To Agentic is instructions for the agent only.
SKILL.md names 1 domain. As links in the text: x.com. This is read from the text; nothing was executed.
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.
Karpathy Vibe To Agentic is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.4k tokens (SKILL.md is roughly 5.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Karpathy Vibe To Agentic: Native Feel Cross Platform Desktop (yetone/native-feel-skill, 1.9k stars), Compound Engineering Prototype (EveryInc/compound-engineering-plugin, 25k stars), Collaborating With Codex (GuDaStudio/collaborating-with-codex, 132 stars) and Digikey (aklofas/kicad-happy, 1.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
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.
