Karpathy Guidelines
by multica-ai2c606141936fMITListed Oct 8, 2026Updated Oct 8, 2026
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.
Only the file list is public. File contents are available once the skill is installed in a workspace.
| Path | Size | Type |
|---|---|---|
| SKILL.md | 2.5 KB | text/markdown |
Source and attribution
Source:multica-ai/andrej-karpathy-skillsinskills/karpathy-guidelinesat commit2c60614
License: MIT
Content belongs to its original authors. SourceWeft indexes it from a public repository.
More in Software Development
Playground
anthropics
Builds self-contained interactive HTML playgrounds with controls, live preview, and copyable prompt output.
M5 Onboard
anthropics
Provisions M5Stack ESP32 boards by detecting them on USB, flashing UIFlow 2.0 firmware, and installing a MicroPython app bundle.
Cardputer Buddy
anthropics
Guides iterating on a Cardputer-Adv MicroPython app bundle: adding apps, pushing files over USB-serial, tailing logs, and running REPL commands.
Testing Strategy
anthropics
Designs test strategies and test plans, covering test types, coverage targets, and example test cases.
Tech Debt
anthropics
Identifies, categorizes, and prioritizes technical debt, producing a scored backlog and phased remediation plan.
System Design
anthropics
Guides system and architecture design through requirements, high-level design, deep dives, scaling, and trade-off analysis.