karpathy-guidelines

Enforce behavioral guidelines for writing, reviewing, and refactoring code.

1|Updated Apr 9, 2026

Search Tags:#verification #tradeoffs #surgical-changes #karpathy-guidelines #llm-coding #assumption-surface

Ready to run

npx skills add https://github.com/hbvg234/jnmt.vn --skill karpathy-guidelines-hbvg234

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: karpathy-guidelines
Source: https://github.com/hbvg234/jnmt.vn/tree/main/Claude-code/.claude/skills/karpathy-guidelines
Command: npx skills add https://github.com/hbvg234/jnmt.vn --skill karpathy-guidelines-hbvg234

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Behavioral guidelines to reduce common LLM coding mistakes by surfacing assumptions, encouraging clarity, and constraining complexity.

Core Features & Use Cases

Surface explicit assumptions and tradeoffs before coding.
Favor surgical changes and avoid unnecessary refactoring.
Define and verify success criteria to guide iterative work.

Quick Start

State your assumptions, surface tradeoffs, and define verifiable success criteria for this coding task.

Frequently Asked Questions about karpathy-guidelines

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I reduce LLM coding mistakes when generating or refactoring code?▼

To reduce LLM coding mistakes, enforce guidelines that surface assumptions and tradeoffs before coding, favor surgical changes, and define verifiable success criteria to guide iterative improvements.

What are Karpathy guidelines for LLM coding and how do they work?▼

Karpathy guidelines for LLM coding are behavioral constraints that force models to state explicit assumptions, surface tradeoffs, and define verifiable success criteria before coding, preventing overcomplication and unnecessary refactoring.

How to surface assumptions and tradeoffs before writing code with an LLM?▼

Surface assumptions and tradeoffs before writing code by applying behavioral guidelines that require the LLM to explicitly state all assumptions and design tradeoffs, minimizing overcomplication and ensuring surgical changes.

Does enforcing explicit success criteria improve LLM code refactoring?▼

Enforcing explicit and verifiable success criteria improves LLM code refactoring by guiding iterative work and ensuring changes remain surgical, which prevents unnecessary refactoring and constrains complexity.

Best way to prevent LLMs from making unnecessary refactoring changes?▼

The best way to prevent unnecessary LLM refactoring is to enforce guidelines that favor surgical changes and surface tradeoffs, requiring explicit assumptions to constrain complexity and limit overcomplication.

When should I not use behavioral guidelines for LLM coding tasks?▼

Avoid behavioral guidelines for LLM coding tasks when rapid prototyping without explicit assumptions or verifiable success criteria is needed, as the guidelines add overhead by surfacing tradeoffs and enforcing surgical changes.