No visual example yet
Explore the skillkarpathy
gaasher
Use when the user wants the LLM to do its own ML research: a fully-autonomous loop that hacks the training code, runs it, and keeps changes that lower a single scalar me…
OPENAGENTSKILL / DIRECTORY
Encuentra una habilidad para tu próxima tarea con Codex, Claude Code, Cursor y más.
5 Skills
Resultados: 5
Archivos entregados aquí desde el 14 de octubre de 2026. Una descarga por cuenta y Skill al día UTC. Excluye sitios externos, comandos copiados e instalaciones. Actualización en hasta 5 minutos.
No visual example yet
Explore the skillgaasher
Use when the user wants the LLM to do its own ML research: a fully-autonomous loop that hacks the training code, runs it, and keeps changes that lower a single scalar me…
No visual example yet
Explore the skilltoolboxmd
Read protocol for the main agent. Load on demand when answering ANY user question (per Iron Rule 4 in `using-karpathy-wiki/SKILL.md`). Defines the deterministic 6-step o…
No visual example yet
Explore the skillkarpathy
arxiv-sanity lite: tag arxiv papers of interest get recommendations of similar papers in a nice UI using SVMs over tfidf feature vectors based on paper abstracts.
No visual example yet
Explore the skillalvinreal
A curated list of autonomous improvement loops, research agents, and autoresearch-style systems inspired by Karpathy's autoresearch.
No visual example yet
Explore the skilldarkroomengineering
Autonomous skill-prompt optimization — Karpathy-style mutate/score/keep loop on SKILL.md. Triggers "autoresearch", "optimize skill", "tune", "evolve" a skill, "prompt op…