Karpathy Coder
Skill Verified ActiveUse when writing, reviewing, or committing code to enforce Karpathy's 4 coding principles — surface assumptions before coding, keep it simple, make surgical changes, define verifiable goals. Triggers on "review my diff", "check complexity", "am I overcomplicating this", "karpathy check", "before I commit", or any code quality concern where the LLM might be overcoding.
Enforce disciplined coding practices by actively identifying and flagging deviations from Karpathy's four core principles during development.
Features
- Detects over-engineering via complexity, length, and abstraction analysis.
- Identifies "noise" in code changes (comments, style, unrelated edits).
- Flags hidden assumptions and vague language in plans.
- Verifies if success criteria are concrete and measurable.
- Provides integration for pre-commit hooks and CI pipelines.
Use Cases
- Use when writing code to ensure simplicity and avoid premature abstractions.
- Use when reviewing code to catch deviations from the stated task.
- Use before committing to catch style drift or unrelated changes.
- Use when defining plans to ensure clear, verifiable goals.
Non-Goals
- Performing actual code refactoring or style correction.
- Replacing comprehensive code linters or static analysis tools.
- Providing AI-generated code that adheres to the principles (focus is on analysis).
Workflow
- Analyze code/plan for adherence to Karpathy's 4 principles.
- Identify potential violations (over-complexity, noise, assumptions, vague goals).
- Report findings with specific examples and recommendations.
- Integrate into development workflow (hooks, CI, agent commands) for automated enforcement.
Practices
- Code Quality
- Developer Workflow
- LLM Best Practices
- Code Review
Prerequisites
- Python 3.x
- Git
Installation
First, add the marketplace
/plugin marketplace add alirezarezvani/claude-skills/plugin install karpathy-coder@claude-code-skillsQuality Score
VerifiedTrust Signals
Similar Extensions
Migrate Validate
100Validate pending migrations for foreign key consistency, rollback safety, and best practices
Semgrep Rule Creator
100Creates custom Semgrep rules for detecting security vulnerabilities, bug patterns, and code patterns. Use when writing Semgrep rules or building custom static analysis detections.
Moyu (摸鱼)
100과잉 엔지니어링 패턴이 감지되면 자동으로 활성화됩니다: (1) 사용자가 명시적으로 변경을 요청하지 않은 코드나 파일을 수정하는 경우 (2) 요청되지 않은 새로운 추상화 레이어(class, interface, factory, wrapper)를 생성하는 경우 (3) 요청되지 않은 주석, 문서, JSDoc, 타입 어노테이션을 추가하는 경우 (4) 요청되지 않은 새로운 의존성을 도입하는 경우 (5) 최소한의 편집 대신 파일 전체를 다시 작성하는 경우 (6) diff 범위가 사용자의 요청을 명백히 초과하는 경우 (7) 사용자가 "너무 많아", "거기는 건드리지 마", "X만 변경해", "간단하게", "그만" 등의 신호를 보내는 경우 (8) 발생할 수 없는 시나리오에 대한 에러 처리, 유효성 검사, 방어적 코드를 추가하는 경우 (9) 요청되지 않은 테스트, 설정 스캐폴딩, 문서를 생성하는 경우
Cleanup Cycles
100Detect and untangle circular dependencies. Runs madge/skott (TS), pycycle (Py), or compiler-only checks (Go/Rust). Auto-fixes leaf-extractable cycles; reports core cycles for human review. Use when the user asks to find circular imports, fix dependency cycles, or untangle module graph. Example queries — "find circular imports", "fix dependency cycles", "untangle our module graph", "why is madge complaining".
Definition Of Done
100Mandatory checks to run before completing any task that touches md files or dart code in this repository.
Wrap Up Ritual
100End-of-session ritual that audits changes, runs quality checks, captures learnings, and produces a session summary. Use when saying "wrap up", "done for the day", "finish coding", or ending a coding session.