All skills
forrestchang avatar

/karpathy-guidelines

@64723a4

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

Use this Skill: https://skilld.dev/gh/forrestchang/andrej-karpathy-skills/karpathy-guidelines

This session only. Nothing lands on disk.

SKILL.md

≈60 tokens always: the name and description. ≈559 when used: this file.

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.

Source: SKILL.md on GitHub

No alerts16d5 checks · Risk SAFE
  • Gen Agent Trust Hub16d

    This skill consists of behavioral guidelines for code generation and refactoring. It contains no executable code or security risks.

  • Socket16d

    No alerts

  • Snyk16d

    Risk: LOW · No issues

  • Runlayer7mo

    1 file scanned · No issues

  • ZeroLeaks5mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at 64723a4. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 months ago.

Steadyupdated 8 months ago
  • Refactoring
  • Testing
  • llm-coding
  • guidelines
  • code-review
  • simplicity
  • best-practices
  • behavioral-guidelines

README badge

README badge for forrestchang/andrej-karpathy-skills

Behavioral guidelines for reducing common LLM coding mistakes: think through assumptions before implementing, write minimal code without speculation, make surgical edits that touch only what's necessary, and define verifiable success criteria for each task. Based on Andrej Karpathy's observations on LLM coding pitfalls, the skill is meant to be loaded when writing, reviewing, or refactoring code to avoid overcomplication and hidden confusion.

Generated from the current SKILL.md.

Does this skill apply to all coding tasks or just some?
The guidelines bias toward caution and are most useful for complex changes, refactoring, and bug fixes. For trivial tasks, the skill itself recommends using judgment rather than following all guidelines rigidly.
What specific mistakes do these guidelines help avoid?
They target common LLM pitfalls: overcomplication, hidden assumptions, unnecessary abstractions, speculative features, and unclear success criteria. The guidelines stem from Andrej Karpathy's observations on LLM coding errors.
How do I apply these guidelines when reviewing or writing code?
Use them as a checklist before and during implementation: surface assumptions explicitly, write only what was asked, make surgical edits to existing code, and define verifiable success criteria upfront before coding begins.
Does this work with any language or framework?
Yes. These are behavioral guidelines independent of language, framework, or tool. They apply to any code writing, review, or refactoring task.

Generated from the current SKILL.md. These answers refresh after source changes.