Karpathy Coding Principles

VerifiedSafe

Guides coding with principles of simplicity, clarity, and surgical precision. Use when you want to think before coding, keep solutions minimal, make targeted changes, and define verifiable success criteria.

Sby Skills Guide Bot
DevelopmentIntermediate
706/2/2026
Claude Code
#simplicity#surgical-changes#goal-driven#think-before-coding#minimal-code

Recommended for

Our review

This skill applies Andrej Karpathy's coding principles of simplicity, clarity, and surgical precision, requiring explicit thinking before implementation and limiting changes to the absolute minimum.

Strengths

  • Reduces complexity and technical debt by eliminating unnecessary code.
  • Forces explicit reasoning about assumptions and trade-offs.
  • Limits modifications to only the required lines, preventing regressions.
  • Structures work into verifiable steps, improving reliability.

Limitations

  • Can feel overly restrictive in exploratory or creative coding contexts.
  • Not suitable for major rewrites or fast-moving feature development.
  • The ban on improving adjacent code may leave underlying issues unaddressed.
When to use it

Use this skill for targeted edits, precise debugging, or when code clarity and minimalism are more important than adding flexibility.

When not to use it

Avoid this skill during early prototyping or when you need to experiment freely without worrying about code perfection.

Security analysis

Safe
Quality score90/100

This skill provides coding principles and does not instruct any actions that could cause harm, exfiltrate data, or execute destructive commands. It is purely advisory on development style.

No concerns found

Examples

Enter Karpathy mode for refactoring
Enter karpathy mode. Refactor this function to be simpler and more readable, but change only what is necessary and explain your assumptions.
Surgical bug fix
Using karpathy principles, fix the bug in this function. First, write a test that reproduces the bug, then make it pass with minimal changes.
Goal-driven implementation
Implement a sorting algorithm for this list using karpathy mode. Define verifiable success criteria before writing any code.

name: karpathy description: 'Coding principles for simplicity, clarity, and surgical precision. Use when you want Claude to think before coding, keep solutions minimal, make surgical changes, and define verifiable success criteria. Triggers on: karpathy mode, think before coding, simplicity first, surgical changes.'

Karpathy Coding Principles

Principles for writing clean, minimal, and purposeful code.


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.

Related skills