📄 skillStaleExperimentallow

multica-ai/andrej-karpathy-skills

by multica-ai

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

Supported Platforms

🤖 Claude Code

Stars

177.4k

Skill Type

📖 Library & API Reference

Quality Score

54/200

License

Not specified

Forks

18.1k

Last Updated

Jul 27, 2026

Discovered

Apr 18, 2026

Validation

Passed

github.com/multica-ai/andrej-karpathy-skills

Quality Breakdown

54/ 200

Content Signals

Gotchas/Edge Cases+40
Progressive Disclosure+30
Trigger Description+20
Verification/Safety+20
Code Examples+15
Composability+15

Repo Health

Recent Activity+15
Scripts/Automation+10
Real Usage (Issues)+10
Single Responsibility+10
Config/Persistence+10
Install Instructions+5

Multi-platform bonus: +5 pts if tool supports 2+ platforms. Score derived from 12 structural signals — not stars or popularity.

Trust & Verification

low

Standard permissions only. Safe for general use.

Stale

No commits in 90-365 days and no tagged releases.

Unverified skill. Always review source code before installing any skill from an unknown author.

Risk Assessment

  • Repository contains only documentation and configuration files for Claude/Cursor coding guidelines
  • No executable scripts, shell commands, or system access requests present
  • No autonomous operation, multi-agent spawning, or external code execution capabilities
  • Files are configuration metadata (.claude-plugin, .cursor) and markdown documentation only
  • Content is educational guidelines derived from public best practices, not malicious instructions
  • No install scripts, bootstrap automation, or persistent system modification logic

Related guides