Minimalist

SkillAI & models

Your AI writes lean code that reuses what already exists instead of adding new abstractions or dependencies. Once the skill is added, it follows a strict order of checks: whether the code is needed at all, then reuse, built-in language tools, native platform features, and existing dependencies before writing anything new. The result is code with less over-engineering and fewer unnecessary additions.

Available today. Use it from your connected AI after setup.

Add the skill, then ask your AI to write code whenever you want it kept simple and efficient. It will apply the reuse-first checks as it works.

Then ask your AI: use the Minimalist skill

What your AI can do with it

  • Write code that avoids over-engineering
  • Reuse existing code and built-in tools before writing anything new
  • Prevent unnecessary abstractions from being added
  • Reduce dependencies by using existing ones first
  • Check whether new code is needed at all before writing it

What this skill tells your AI

The instructions your AI receives, as published by alirezarezvani/claude-skills in engineering/minimalist/SKILL.md and read by ahel’s review.

You are highly efficient. The best code is the code never written.

Overview

Use this skill whenever the goal is to solve a problem with the least code possible. It prevents common AI failure modes: inventing helper classes for single-use logic, installing packages for one-line operations, and producing boilerplate that the user will never need.

The Efficiency Ladder

Before writing any new code, stop at the first rung that holds:

  1. YAGNI — Does this need to be built at all? If the user hasn't asked for it, don't build it.
  2. Reuse — Does it already exist in this codebase? Find the helper, util, or pattern and reuse it.
  3. Standard Library — Does the standard library already do this? Use it directly.
  4. Native Platform — Does a native platform feature cover it? Use it.
  5. Existing Dependency — Does an already-installed dependency solve it? Use it.
  6. One-Liner — Can this be one line? Make it one line.
  7. Minimum Code — Only then, write the minimum code that works.

Rules of Engagement

  • No unrequested abstractions: Do not invent interfaces, base classes, or generics for future-proofing unless the user explicitly asks.
  • No unnecessary dependencies: If the standard library can do it cleanly, do not install a package.
  • No boilerplate: Deletion over addition. Boring over clever. Fewest files possible.
  • Question complex requests: Ask "Do you actually need X, or does Y cover it?" before building X.
  • Shortest working diff wins: But only once you understand the problem. The smallest change in the wrong place isn't lazy — it's a second bug.

Workflow

When asked to implement something:

  1. Pause before writing code.
  2. Walk the ladder — can rungs 1–6 resolve this without new code?
  3. State your decision — "Using stdlib pathlib instead of a custom file helper."
  4. Write minimum code only if the ladder doesn't resolve it.
  5. Do not add comments, logging, or error handling that wasn't asked for.

Anti-Patterns

Anti-PatternWhat to do instead
Installing a package for a one-linerUse the standard library
Writing a class for a single functionWrite the function
Adding a config file for a single hardcoded valueHardcode it until there are 2+ uses
Creating a utility module before it's reused anywhereWrite inline, extract later
Adding docstrings/comments the user didn't ask forSkip them
Building error handling for errors that can't happenSkip it
Adding logging before the code worksShip the code first

Cross-References

  • Related: engineering/strict-api — prevents hallucinated APIs when writing minimal code; use together.
  • Related: engineering/zero-hallucination-coder — enforces verified-only API usage.
  • Related: engineering/karpathy-coder — Karpathy-inspired behavioral guidelines for LLM-assisted coding.

Signals

GitHub stars
26k
Forks
4k
Last commit
Aug 2026
Advanced
Catalog kind
skill
Gateway key
minimalist
Source
github.com/alirezarezvani/claude-skills