How do I install the Karpathy Check skill?

Run npx skillmds@latest add zuoguyoupan2023/karpathy-check in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

What does the Karpathy Check skill do?

Run Karpathy's 4-principle review on staged changes or the last commit. Checks complexity, diff noise, hidden assumptions, and goal verification. Usage /karpathy-check [--last-commit] It is listed under Coding & Dev Tools on SkillMD.

Is Karpathy Check safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Karpathy Check?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Karpathy Check free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Karpathy Check?

zuoguyoupan2023 (@zuoguyoupan2023) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Karpathy Check by zuoguyoupan2023 — Agent Skill

Name: Karpathy Check
Rating: 4.2 (5 reviews)
Author: zuoguyoupan2023

File contents

/karpathy-check

Review your staged changes (or last commit) against Karpathy's 4 coding principles.

Usage

/karpathy-check                 # review staged changes
/karpathy-check --last-commit   # review the most recent commit

What it runs

Principle #2 (Simplicity): scripts/complexity_checker.py on all changed files — detects over-engineering, premature abstractions, deep nesting, long functions
Principle #3 (Surgical): scripts/diff_surgeon.py on the diff — detects comment-only changes, whitespace noise, style drift, drive-by refactors
Principles #1 + #4 (Think + Goals): The karpathy-reviewer agent reads the diff and applies human-judgment checks — hidden assumptions, missing verification

Output

A structured report with per-principle verdicts and specific line-level fix recommendations.

When to run

Before committing (catches noise and overcomplication early)
After completing a feature (sanity check before PR)
When you suspect the LLM overcoded something

Sub-agent

Dispatches the karpathy-reviewer agent. See agents/karpathy-reviewer.md.

Scripts

engineering/karpathy-coder/scripts/complexity_checker.py
engineering/karpathy-coder/scripts/diff_surgeon.py
engineering/karpathy-coder/scripts/assumption_linter.py
engineering/karpathy-coder/scripts/goal_verifier.py

Skill Reference

→ engineering/karpathy-coder/SKILL.md

Frequently asked questions

Karpathy Check