Skill Introduction

Overview

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.

Core value

Turns reusable Testing know-how into an installable skill, helping users complete github, community work faster.

Target users

Developers, testers, and maintainers who handle Testing tasks in Focus Code.
Teams that already trust workflows or content from forrestchang.
Users who want standardized prompts, steps, or conventions instead of repeating setup work.

Best practices

Read the skill content first to confirm required inputs, expected outputs, and dependencies.
Try it on a small task before relying on it for critical work.
Add project-specific constraints such as coding style, target platform, test expectations, and delivery format.
For external sources, verify the source link, version, and recent maintenance activity.

Best use cases

Tasks related to github, community that need a reusable execution flow.
Converting a community repo, team convention, or personal workflow into day-to-day assistance.
Starting from a proven skill instead of writing prompts or procedures from scratch.

Limits and boundaries

Results depend on the quality of the original skill content and may need human correction.
It does not replace code review, tests, security review, or professional judgment.
External tools, APIs, account permissions, and local dependencies still need separate setup.

Differentiation

Structured around Testing, making it easier to discover and reuse than loose prompt snippets.
Marked as GitHub, which helps users judge trust and maintenance expectations.
Keeps the original source link available for repository, documentation, or discussion follow-up.
Tagged with github, community, so it can be filtered by concrete task intent.

Detail Preview

SKILL.md

Primary filemarkdown3 KB

name: karpathy-guidelines description: 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. license: MIT

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.

karpathy guidelines