Skill-Verzeichnis

Wiederverwendbare Skills für AI Agents entdecken.

Durchsuche reale GitHub-Skills nach Aufgabe und prüfe Stars, Trust, Audit, Kategorie und Installationspfad vor der Verwendung.

Jede Empfehlung bleibt mit ihrem Repository, Audit und Installationspfad nachvollziehbar.

Suchergebnisse: karpathy

Englisches Verzeichnis

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

175K
Stars
77/100
Trust
Kategorie: developmentAudit

Self-organizing AI second brain for Obsidian + Claude Code. Drop any source and Claude reads, links, and files it into one connected knowledge graph of plain Markdown you own. AI note-taking, personal knowledge management (PKM), and an open-source Notion alternative. Based on Karpathy's LLM Wiki pattern.

11K
Stars
88/100
Trust
Kategorie: rag-knowledgeAudit

Framework for AI agents to build and maintain a digital brain through Obsidian wiki using Karpathy's LLM Wiki pattern

3.2K
Stars
86/100
Trust
Kategorie: agent-skillsAudit

A curated list of autonomous improvement loops, research agents, and autoresearch-style systems inspired by Karpathy's autoresearch.

2.5K
Stars
77/100
Trust
Kategorie: agent-frameworksAudit

Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever.

5.1K
Stars
86/100
Trust
Kategorie: developmentAudit

Agent Skills-compatible LLM wiki for Claude Code, Cursor, and Codex. Build a Karpathy-style knowledge base from raw sources, citations, and linting.

1.6K
Stars
86/100
Trust
Kategorie: agent-skillsAudit

Codex Autoresearch Skill — A self-directed iterative system for Codex that continuously cycles through: modify, verify, retain or discard, and repeat indefinitely. Inspired by Karpathy’s autoresearch concept.

2.0K
Stars
79/100
Trust
Kategorie: automationAudit

The knowledge compiler. Raw sources in, interlinked wiki out. Inspired by Karpathy's LLM Wiki pattern.

1.5K
Stars
79/100
Trust
Kategorie: document-processingAudit

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.

1.6K
Stars
71/100
Trust
Kategorie: researchAudit

72 agent skills synthesizing 17 years of software engineering discipline into a prescriptive methodology for solo developers

84
Stars
66/100
Trust
Kategorie: utilityAudit

A framework for agent-operated knowledge wikis with typed, linked, review-gated markdown, installable as Python commands.

81
Stars
71/100
Trust
Kategorie: researchAudit

Karpathy-style LLM knowledge base Agent Skill for OpenClaw/Codex. Experimental — will iterate over time.

585
Stars
68/100
Trust
Kategorie: agent-skillsAudit