Home / index-login / mobilere-skill · .kilo/skill/karpathy-guidelines/SKILL.md · GitHub

karpathy-guidelines skillA

karpathy-guidelines is agent-read markdown (skill) from index-login/mobilere-skill: 减少 LLM 常见编码错误的行为准则。在编写、审查或重构代码时使用，避免过度设计、精准修改、暴露假设、定义可验证的成功标准。.

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# Karpathy 编码准则

**取舍：** 这些准则偏向谨慎而非速度。对于简单任务，自行判断。

## 1. 先想后写

**不假设，不隐藏困惑，暴露权衡。**

开始实现前：
- 明确陈述假设。如果不确定，提问。
- 如果存在多种解读，列出它们——不要默默选择一种。
- 如果有更简单的方案，指出来。有必要时坚持己见。
- 如果某个地方不清楚，停下来。说出困惑点。提问。

## 2. 简洁优先

**最少代码解决问题。不写投机性代码。**

- 不添加未请求的功能。
- 不为单次使用的代码创建抽象。
- 不添加未被要求的"灵活性"或"可配置性"。
- 不为不可能发生的场景做错误处理。
- 如果写了 200 行但可以缩减到 50 行，重写。

问自己："资深工程师会说这过度设计吗？"如果是，简化。

## 3. 精准修改

**只动必须动的。只清理自己造成的烂摊子。**

编辑已有代码时：
- 不"顺手优化"相邻的代码、注释或格式。
- 不重构没坏的东西。
- 匹配已有风格，即使你对此有不同意见。
- 如果注意到无关的死代码，提出来——但不要删除它。

当你的改动产生孤儿代码时：
- 删除由你的改动导致不再使用的 import / 变量 / 函数。
- 不要删除改动前就存在的死代码，除非被要求。

检验标准：每一行改动都应直接追溯到用户的需求。

## 4. 目标驱动执行

**定义成功标准。循环迭代直到验证通过。**

将任务转化为可验证的目标：
- "添加验证" → "为无效输入写测试，然后让测试通过"
- "修复 bug" → "写一个能复现的测试，然后让它通过"
- "重构 X" → "确保重构前后测试都通过"

对于多步骤任务，先给出简要计划：
```
1. [步骤] → 验证: [检查项]
2. [步骤] → 验证: [检查项]
3. [步骤] → 验证: [检查项]
```

强成功标准让你能独立迭代。弱标准（"把它弄好"）需要不断澄清。

Read the whole file at its exact version.

How to install

Latest version
mdr add index-login/mobilere-skill/karpathy-guidelines@git:20260803.71f8be9
Exact content
mdr add index-login/mobilere-skill/karpathy-guidelines@sha256:c160393dc48c6ffa

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_44lxljvwfkww6wtv.svg)](https://markdownregistry.com/a/art_44lxljvwfkww6wtv)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260803.71f8be9 latest2026-08-03 71f8be9 2,274 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (2274 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

index-login/mobilere-skill · 54 stars · license MIT · pushed 2026-09-24 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_44lxljvwfkww6wtv
GET https://markdownregistry.com/api/v1/resolve?ref=index-login/mobilere-skill/karpathy-guidelines
GET https://markdownregistry.com/api/v1/blob/c160393dc48c6ffa11721ca5a94a562a87f68d37f051fc8aa83a6a4f117facf0

Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

More from index-login/mobilere-skill

frida-mobile-security skill
index-login/mobilere-skill · .kilo/skill/frida-mobile-security/SKILL.md · 用于 Android/iOS 移动应用安全逆向分析：Frida 动态插桩、绕过反调试/反注入/加固壳、脱壳、加密与 native SO 层 hook、运行时行为分析、jadx-mcp 静态攻击面分析、离线 SO 静态分析（ELF…
git:20260924.aeb9e2f · audit A · 54 stars
rev-dex-dumper skill
index-login/mobilere-skill · .kilo/skill/rev-dex-dumper/SKILL.md · Root memory dump of DEX from a running Android app: no injection, no ptrace (survives ptrace-blocking anti-debug…
git:20260923.11daeaa · audit A · 54 stars
rev-struct skill
index-login/mobilere-skill · .kilo/skill/rev-struct/SKILL.md · Reconstruct data structures by analyzing memory access patterns across functions
git:20260923.11daeaa · audit A · 54 stars
rev-symbol skill
index-login/mobilere-skill · .kilo/skill/rev-symbol/SKILL.md · Restore function symbols by analyzing code patterns, strings, constants, and cross-references
git:20260924.aeb9e2f · audit A · 54 stars
rev-unicorn-debug skill
index-login/mobilere-skill · .kilo/skill/rev-unicorn-debug/SKILL.md · Debug and emulate specific code fragments or functions using the Unicorn engine. Activate when the user wants to…
git:20260924.aeb9e2f · audit A · 54 stars
AGENTS.md agents
index-login/mobilere-skill · AGENTS.md
git:20260924.aeb9e2f · audit A · 54 stars

Every file in index-login/mobilere-skill

Other files named karpathy-guidelines

karpathy-guidelines skill
hashgraph-online/awesome-codex-plugins · plugins/Colin4k1024/tsp/skills/karpathy-guidelines/SKILL.md · 提供一组面向编码行为的轻量约束，帮助代理在动手前暴露假设、优先简单方案、保持改动外科化，并把任务改写成可验证目标。 当任务容易被误解、过度设计、顺手扩散改动，或需要先锁定成功标准时使用。
git:20260512.6523792 · audit A · 1,074 stars
karpathy-guidelines skill
mxyhi/ok-skills · karpathy-guidelines/SKILL.md · Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid…
git:20260508.0cab7e8 · audit A · 490 stars
karpathy-guidelines skill
cowork-os/cowork-os · resources/skills/karpathy-guidelines/SKILL.md · Surgical execution guardrails for coding, debugging, review, and refactor tasks
v1.0.0 · audit A · 459 stars
karpathy-guidelines skill
coco-research/coco · skills/karpathy-guidelines/SKILL.md · Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid…
git:20260802.1479e32 · audit A · 478 stars
karpathy-guidelines skill
openyida/openyida · .agents/skills/karpathy-guidelines/SKILL.md · Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid…
git:20260728.2c22517 · audit A · 217 stars
karpathy-guidelines skill
youdotcom-oss/agent-skills · .agents/skills/karpathy-guidelines/SKILL.md · Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid…
git:20260723.e470633 · audit A · 78 stars
karpathy-guidelines skill
jjmartres/ai-coding-agents · shared/.ai-agents/skills/karpathy-guidelines/SKILL.md · Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid…
git:20260428.dfccef3 · audit A · 48 stars
karpathy-guidelines skill
cmc-27/pass-the-parcel · .devops/skills/karpathy-guidelines/SKILL.md · Make sure to use this skill whenever you write, review, or refactor code, or when the user asks to implement a feature…
v1 · audit A · 33 stars

Browse by kind, by grade A, or by owner.