karpathy-guidelines

multica-ai/andrej-karpathy-skills · Agent Skill

提供行為準則，以盡量減少常見的 LLM 編碼錯誤，促進清晰度和效率。

總覽

發布者	multica-ai組織
儲存庫	multica-ai/andrej-karpathy-skills ↗
技能資料夾	`karpathy-guidelines`
星	210,607
附帶檔案	1
授權	未標示 — 請向作者確認
最近更新	2026年1月27日
連結	技能原始碼 ↗ · 儲存庫 ↗

Mozgi 檢查

我們在技能檔案中發現的內容。詳細資訊需訂閱。

安全性

低風險 · 未發現明顯風險 — 完整報告會顯示細節

相容性

僅含說明 — 適用於多數代理

相似技能

找到 144 個相似技能

訂閱另含

安裝

技能就是一個含 SKILL.md 的資料夾。選擇你的代理，在專案根目錄的終端機（macOS、Linux 或 Windows 的 Git Bash）執行指令。

把提示貼到 Claude、Codex 或其他助理：它會自行檢查並安裝技能。

Install the “karpathy-guidelines” skill from mozgi.io (https://mozgi.io/skills/karpathy-guidelines/) for me.

1. Download the archive: https://mozgi.io/skills/karpathy-guidelines/download
   If it fails, take the skill folder from the source: https://github.com/multica-ai/andrej-karpathy-skills/tree/main/skills/karpathy-guidelines
2. Read SKILL.md and the other files. Check the skill is safe: no hidden commands, no sending data elsewhere, no scripts doing something other than described. If anything looks suspicious, stop and tell me.
3. Put the “karpathy-guidelines” folder into your agent's skills folder: .claude/skills/ for Claude Code, .agents/skills/ for Codex, .cursor/skills/ for Cursor, .gemini/skills/ for Gemini CLI. Inside the project if we are in one, otherwise in the home folder (~/.claude/skills/ etc.).
4. Make sure <skills folder>/karpathy-guidelines/SKILL.md exists.
5. Briefly tell me what this skill does and offer to try it on my task.

If you cannot do a step yourself, tell me what to click or type.

git clone --depth 1 --branch main https://github.com/multica-ai/andrej-karpathy-skills.git /tmp/andrej-karpathy-skills
mkdir -p .claude/skills
cp -r /tmp/andrej-karpathy-skills/skills/karpathy-guidelines .claude/skills/karpathy-guidelines

重新啟動 Claude Code — 技能就會出現在清單中，手動呼叫：/karpathy-guidelines。要套用到所有專案，請放在 ~/.claude/skills。

git clone --depth 1 --branch main https://github.com/multica-ai/andrej-karpathy-skills.git /tmp/andrej-karpathy-skills
mkdir -p .agents/skills
cp -r /tmp/andrej-karpathy-skills/skills/karpathy-guidelines .agents/skills/karpathy-guidelines

Codex 會從目前資料夾往上到儲存庫根目錄，在 .agents/skills 中尋找技能；用 /skills 或 $karpathy-guidelines 呼叫。所有專案：~/.agents/skills。

git clone --depth 1 --branch main https://github.com/multica-ai/andrej-karpathy-skills.git /tmp/andrej-karpathy-skills
mkdir -p .cursor/skills
cp -r /tmp/andrej-karpathy-skills/skills/karpathy-guidelines .cursor/skills/karpathy-guidelines

Cursor 啟動時會載入技能；在 Agent 聊天輸入「/」呼叫。Cursor 也會讀取 .claude/skills 與 .agents/skills。所有專案：~/.cursor/skills。

git clone --depth 1 --branch main https://github.com/multica-ai/andrej-karpathy-skills.git /tmp/andrej-karpathy-skills
mkdir -p .gemini/skills
cp -r /tmp/andrej-karpathy-skills/skills/karpathy-guidelines .gemini/skills/karpathy-guidelines

任務符合時，Gemini CLI 會提議啟用技能，由你確認。所有專案：~/.gemini/skills。

技能檔案

1 個檔案下載 ZIP

安裝前請先檢視 SKILL.md 與相關檔案。點擊檔案即可預覽。

SKILL.md 內容

作者原文 · 唯讀

Karpathy Guidelines

Behavioral guidelines to reduce common LLM coding mistakes, derived from Andrej Karpathy's observations ↗ on LLM coding pitfalls.

Tradeoff: These guidelines bias toward caution over speed. For trivial tasks, use judgment.

1. Think Before Coding

Don't assume. Don't hide confusion. Surface tradeoffs.

Before implementing:

State your assumptions explicitly. If uncertain, ask.
If multiple interpretations exist, present them - don't pick silently.
If a simpler approach exists, say so. Push back when warranted.
If something is unclear, stop. Name what's confusing. Ask.

2. Simplicity First

Minimum code that solves the problem. Nothing speculative.

No features beyond what was asked.
No abstractions for single-use code.
No "flexibility" or "configurability" that wasn't requested.
No error handling for impossible scenarios.
If you write 200 lines and it could be 50, rewrite it.

Ask yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.

3. Surgical Changes

Touch only what you must. Clean up only your own mess.

When editing existing code:

Don't "improve" adjacent code, comments, or formatting.
Don't refactor things that aren't broken.
Match existing style, even if you'd do it differently.
If you notice unrelated dead code, mention it - don't delete it.

When your changes create orphans:

Remove imports/variables/functions that YOUR changes made unused.
Don't remove pre-existing dead code unless asked.

The test: Every changed line should trace directly to the user's request.

4. Goal-Driven Execution

Define success criteria. Loop until verified.

Transform tasks into verifiable goals:

"Add validation" → "Write tests for invalid inputs, then make them pass"
"Fix the bug" → "Write a test that reproduces it, then make it pass"
"Refactor X" → "Ensure tests pass before and after"

For multi-step tasks, state a brief plan:

1. [Step] → verify: [check]
2. [Step] → verify: [check]
3. [Step] → verify: [check]

Strong success criteria let you loop independently. Weak criteria ("make it work") require constant clarification.

常見問題

karpathy-guidelines 技能有什麼用途？

提供行為準則，以盡量減少常見的 LLM 編碼錯誤，促進清晰度和效率。

如何安裝 karpathy-guidelines？

打開本頁的「安裝」區塊並選擇你的代理 — Claude Code、Codex、Cursor 或 Gemini CLI：那裡有把技能資料夾複製到正確位置的現成指令。也可以複製「透過助理」分頁中的提示，讓助理自行檢查並安裝技能。

karpathy-guidelines 適用哪些 AI 模型？

技能是純 Markdown 指示（Agent Skills 格式），因此 karpathy-guidelines 適用任何讀取 SKILL.md 的代理：Claude Code、Codex、Cursor、Gemini CLI、GitHub Copilot、OpenCode 等。只有在任務符合技能描述時，模型才會載入指示。

karpathy-guidelines 是免費的嗎？

此技能由 multica-ai 公開發布。技能本身免費 — 你只需向 AI 供應商支付實際使用的 token 費用。儲存庫未標示授權 — 商業使用前請向作者確認條款。

安裝技能安全嗎？

技能是代理會遵循的指示，安裝前請閱讀 SKILL.md 及相關檔案。技能資料夾中的腳本只有在代理執行時才會運行 — 留意它的動作，不要授予多餘權限。

技能和 MCP 伺服器或外掛有何不同？

MCP 伺服器或外掛為模型提供新工具 — 會執行並回傳結果的程式碼。技能提供的是知識與流程：如何處理任務、要遵循哪些步驟、好的成果長什麼樣子。它不需要伺服器或 API 金鑰。

總覽