learnprompt/andrej-karpathy-skills

karpathy-agentic-engineering

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

Quelltext ansehen

Verwendung

  1. Installationsbefehl kopieren und das Quellpaket vor der Installation in der eigenen Agentenumgebung prüfen.
  2. Benötigte Werkzeuge, Zugangsdaten und Hosts im Original prüfen.
  3. Eingabe und gewünschtes Ergebnis beschreiben und die Ausgabe mit den Quellen abgleichen.
npx skills add https://github.com/learnprompt/andrej-karpathy-skills --skill karpathy-agentic-engineering

Vor dem Start

  • Die Installation umfasst weder Modellabo noch API-Kontingent oder Dateizugriffsrechte.
  • Sterne und Installationen zeigen Aktivität, keine unabhängige Qualitäts- oder Sicherheitsprüfung.
Originales Skill-Dokument

Aus dem Quell-Repository gerendert; Überschriften, Beispiele, Code, Tabellen, Links und Bilder bleiben erhalten.

Skill 1: Agentic Engineering(代理工程)

Source: https://x.com/karpathy/status/2004607146781278521 | https://x.com/karpathy/status/2015883857489522876 | https://x.com/karpathy/status/2026731645169185220 "It is hard to communicate how much programming has changed." — ~37k likes

Core Principle

You are no longer writing code. You are directing a team of tireless junior engineers.

The shift: write code → write tasks with success criteria → agent loops → human taste review

The 7-Step Inner Loop (Karpathy's Incremental Coding Rhythm)

This is the micro-loop for every coding session:

  1. Stuff context — Load entire project into context (files-to-prompt, relevant docs, recent diffs)
  2. Discuss plan — Ask agent for high-level approaches with pros/cons before any code
  3. Request first draft — Pick one approach, get a minimal first implementation
  4. Inline learning — Manually review the diff; ask agent to explain any API you don't recognize
  5. Test — Run tests, check outputs, verify success criteria
  6. Commit — Only commit what you understand and have verified
  7. Ask for next — Let agent suggest the next incremental step

Never skip step 4. Understanding atrophies if you rubber-stamp every diff.

CLAUDE.md / AGENTS.md Template

Write this file at the project root to prevent the most common agent failure modes:

markdown
# Agent Instructions for [Project Name]

## Behavior Rules
- Make one incremental change at a time. Do NOT refactor unrelated code.
- Always explain WHY you're making a change before the diff.
- If unsure about intent, ASK before implementing.
- Do NOT add new dependencies without explicit approval.
- Prefer simple, readable solutions over clever ones.

## Success Criteria (task-specific — fill in per session)
- [ ] Tests pass: `[test command]`
- [ ] No new lint errors: `[lint command]`
- [ ] Behavior matches: [description of expected output]

## Project Context
- Stack: [language, framework, key libs]
- Entry point: [file]
- Test command: [command]
- Forbidden: [list things agent must never do]

Master Prompt Template

You are an agentic engineer on this project.

Project context: [paste relevant files or use files-to-prompt output]

Task: [specific, unambiguous description]

Success criteria (ALL must be true when done):
1. [verifiable check 1]
2. [verifiable check 2]
3. [verifiable check 3]

Constraints:
- Only change files relevant to this task
- No new dependencies without asking
- Output: one incremental diff at a time

Start by proposing a high-level plan with 2-3 options and trade-offs. Wait for approval before writing code.

Common Failure Modes to Prevent

Agent SinPrevention
Over-refactoring"Only touch files directly related to the task"
Sycophantic confirmation"Tell me what could go wrong with this plan"
Hallucinated APIs"Cite the exact line in the docs for any API you use"
Dependency creep"No new pip/npm installs without asking"
No success criteriaAlways define DONE before starting

Workflow

属于工作流:想法到上线(开发者)

位置上游下游
第2步karpathy-idea-files(先定义想法)karpathy-minimalism(极简实现)

完整链路:idea-files → agentic-engineering → minimalism → supply-chain-hygiene → vibe-to-agentic

也常在反偏见决策工作流中作为执行层出现——当决策完成后需要落地时,切换到本 Skill。

Prompt Contract

text
You are an agentic engineer. Project context: <files, constraints, current state>. Task: <specific goal>. Success criteria: <verifiable checklist>. First propose a high-level plan with tradeoffs. Then make only the next incremental change. After each change, run the relevant verification and report: changed files, evidence of success, remaining risk, and next step.

Verification Checklist

  • [ ] 成功标准已经写成可检查项目(不是模糊描述)
  • [ ] 每轮变更都有实际验证证据:测试通过、lint clean、diff 范围正确
  • [ ] Agent 没有修改任务范围外的文件
  • [ ] 人类已 review 每个 diff 中不理解的部分(不跳步)
  • [ ] 最终提交前,能用一句话向同事解释改了什么、为什么

When to Apply This Skill

  • Starting any coding task > 30 minutes
  • Setting up a new project with agent assistance
  • Debugging a complex issue (agent as rubber duck + implementer)
  • Writing CLAUDE.md / AGENTS.md for a repo
aus demselben Repository

Weitere Skills

Alle Skills
learnprompt
Community

karpathy-education-first

Apply the education-first mindset — make everything you build teachable, create nano-project explanations, write for beginners. Use this skill when the user wants to explain a project to beginners, create a tutorial from code, write documentation that teaches (not just documents), make a concept accessible, or says "make this teachable", "explain like im a beginner", "nano project version", "teaching version", "explain from scratch", "blog post about this". Based on Karpathy 243-line GPT and Eur

Installationen / 1h
1
GitHub Stars
130
Aktualisiert
10. Juli
learnprompt
Community

karpathy-idea-files

Create and share ideas as abstract Gist-style specs instead of code — letting agents or others implement. Use this skill when the user wants to capture a new idea quickly, needs to write a project spec for an agent to implement, wants to share a concept without building it first, or says "write up this idea", "create a spec", "gist this", "idea file", "agent can implement this", "brief for this project". Based on Karpathy 27k-like LLM Wiki Gist post and GitHub repo.

Installationen / 1h
1
GitHub Stars
130
Aktualisiert
10. Juli
learnprompt
Community

karpathy-llm-simulator

Use LLM as a simulator of expert debates and opposing viewpoints instead of getting a single sycophantic answer. Use this skill when the user needs to make an important decision, wants to stress-test an idea, needs devil''s advocate analysis, wants to avoid confirmation bias, or says "argue against this", "what are the counterarguments", "simulate experts", "debate this", "challenge my thinking". Based on Karpathy 31k-like post.

Installationen / 1h
1
GitHub Stars
130
Aktualisiert
10. Juli
learnprompt
Community

karpathy-methodology

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 guidance on agentic engineering, LLM knowledge bases, minimalist coding, understanding-first principles, or any of the 14 core methodologies distilled from his work. Also triggers on: "karpathy method", "karpathy approach", "karpathy way", "AK style", "like karpathy does", "karpathy principles", or when user asks how Karpathy would approach a

Installationen / 1h
1
GitHub Stars
130
Aktualisiert
10. Juli