What it does. A single CLAUDE.md that turns Andrej Karpathy's observations about LLM coding pitfalls into four rules: think before coding (state assumptions, surface tradeoffs), simplicity first (no speculative code), surgical changes (touch only what the task needs), and goal-driven execution (define verifiable success criteria). Drop it into a project's CLAUDE.md or AGENTS.md, or install the same text as the karpathy-guidelines skill in skills/. This is the "Andrej Karpathy things into skills" item from the request; see also his ramble-session post in the index.

Install

• Append CLAUDE.md to your project CLAUDE.md, or /plugin marketplace add forrestchang/andrej-karpathy-skills in Claude Code, or copy skills/karpathy-guidelines/SKILL.md into ~/.claude/skills/karpathy-guidelines/.
• Raw file: curl -sL https://raw.githubusercontent.com/multica-ai/andrej-karpathy-skills/HEAD/CLAUDE.md

SKILL.md (verbatim)

CLAUDE.md

Behavioral guidelines to reduce common LLM coding mistakes. Merge with project-specific instructions as needed.

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.

These guidelines are working if: fewer unnecessary changes in diffs, fewer rewrites due to overcomplication, and clarifying questions come before implementation rather than after mistakes.

Back to Agent skills.