agentleFS
Sign inStart free
hamzafarooqhamzafarooq/claude-code-starter/.claude/skills/karpathy-review/SKILL.md

karpathy-review

Skill145 starsChanged 6 months agoMITView on GitHub

Review code or a plan against Andrej Karpathy's LLM coding principles — catch over-engineering, silent assumptions, unnecessary abstractions, and scope creep before they ship. Use when the user wants a sanity check on code, a plan, or a feature spec.

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask the user: "Paste the code, plan, or spec you want reviewed."

    line 8

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Review the provided code, plan, or spec against Karpathy's four principles. Credit: guidelines distilled from Andrej Karpathy's January 2026 observations, adapted by Forrest Chang.

Ask the user: "Paste the code, plan, or spec you want reviewed."

Then score it against each principle:

Karpathy Review

1. Think Before Coding — were assumptions stated?

  • Did the solution state its assumptions explicitly, or pick silently between interpretations?
  • Are there any unclear requirements that should have triggered a clarifying question?
  • Finding: PASS / FLAG — [specific observation]

2. Simplicity First — is this the minimal solution?

  • Does it add features beyond what was asked?
  • Are there abstractions written for single-use code?
  • Is there "flexibility" or "configurability" that wasn't requested?
  • Could this be meaningfully shorter?
  • Finding: PASS / FLAG — [specific observation, e.g. "This 180-line class could be a 20-line function"]

3. Surgical Changes — does it stay in its lane?

  • Does it modify adjacent code, formatting, or comments that weren't part of the task?
  • Does it refactor things that weren't broken?
  • Does it delete pre-existing code that wasn't asked to be removed?
  • Finding: PASS / FLAG — [specific observation]

4. Goal-Driven Execution — is success verifiable?

  • Is there a clear success criterion?
  • For multi-step work: was a plan stated with checkpoints?
  • Is there a way to verify the output without running it?
  • Finding: PASS / FLAG — [specific observation]

Verdict

PrincipleResult
Think before coding✅ PASS / ⚠️ FLAG
Simplicity first✅ PASS / ⚠️ FLAG
Surgical changes✅ PASS / ⚠️ FLAG
Goal-driven execution✅ PASS / ⚠️ FLAG

One thing to fix: [If any flags, name the single most important change to make]

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free