karpathy
Coding principles for simplicity, clarity, and surgical precision. Use when you want Claude to think before coding, keep solutions minimal, make surgical changes, and define verifiable success criteria. Triggers on: karpathy mode, think before coding, simplicity first, surgical changes.
Best use case
karpathy is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Coding principles for simplicity, clarity, and surgical precision. Use when you want Claude to think before coding, keep solutions minimal, make surgical changes, and define verifiable success criteria. Triggers on: karpathy mode, think before coding, simplicity first, surgical changes.
Teams using karpathy should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/karpathy/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How karpathy Compares
| Feature / Agent | karpathy | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Coding principles for simplicity, clarity, and surgical precision. Use when you want Claude to think before coding, keep solutions minimal, make surgical changes, and define verifiable success criteria. Triggers on: karpathy mode, think before coding, simplicity first, surgical changes.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Karpathy Coding Principles
Principles for writing clean, minimal, and purposeful code.
---
## 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.Related Skills
bgo
Automates the complete Blender build-go workflow, from building and packaging your extension/add-on to removing old versions, installing, enabling, and launching Blender for quick testing and iteration.
network-engineer
Expert network engineer specializing in modern cloud networking, security architectures, and performance optimization.
NestJS Deployment
Docker builds, Memory tuning, and Graceful shutdown.
Naming & Tagging Standards
Establish consistent resource naming conventions and mandatory tagging for cost allocation, security, and governance
Multi-Platform Deployment
This skill should be used when the user asks to "deploy application", "deploy to production", "release app", "deploy to AWS", "deploy to Vercel", "deploy to Kubernetes", "iOS deployment", "Android deployment", "deploy smart contract", "web3 deployment", "deploy to multiple platforms", or needs guidance on deployment strategies across web, mobile, and blockchain platforms.
multi-cloud-architecture
Design multi-cloud architectures using a decision framework to select and integrate services across AWS, Azure, and GCP. Use when building multi-cloud systems, avoiding vendor lock-in, or leveragin...
moon
This skill should be used when the user asks to "configure moon", "set up moonrepo", "create moon tasks", "run moon commands", "configure moon workspace", "add moon project", "moon ci setup", "moon docker", "moon query", "migrate to moon v2", or mentions moon.yml, .moon/workspace.yml, .moon/toolchains.yml, moon run, moon ci, or moonrepo in general.
moodle-mirror
Mirror Moodle course/module pages to local folders (e.g., Obsidian vaults), preserving structure, extracting page text/Markdown, and downloading attachments. Use for authenticated Moodle crawling, Cloudflare/SSO handling, and repeatable offline search across course content.
monitoring
Set up observability for applications and infrastructure with metrics, logs, traces, and alerts.
monitoring-observability
Monitoring and observability patterns for Prometheus metrics, Grafana dashboards, Langfuse LLM tracing, and drift detection. Use when adding logging, metrics, distributed tracing, LLM cost tracking, or quality drift monitoring.
mongodb
Guide for implementing MongoDB - a document database platform with CRUD operations, aggregation pipelines, indexing, replication, sharding, search capabilities, and comprehensive security. Use when working with MongoDB databases, designing schemas, writing queries, optimizing performance, configuring deployments (Atlas/self-managed/Kubernetes), implementing security, or integrating with applications through 15+ official drivers. (project)
modal-serverless-gpu
Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs, or running batch jobs with automatic scaling.