AI Agent Skills

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…

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

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

Applies the mental models and frameworks of Andrej Karpathy (deep learning, former Director of AI at Tesla, founding member of OpenAI, Eureka Labs). Use this skill whene…

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…

Capture-authoring protocol for the main agent. Read on demand when a TRIGGER fires (per `using-karpathy-wiki/SKILL.md`). Defines how to format a capture, how to invoke `…

Behavioral guidelines to reduce common LLM coding mistakes — Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven Execution.

For a detached wiki ingester only. The main agent never loads this. Defines orientation protocol, page format, role guardrail, validator contract, manifest protocol, and…

Detached doctor only. Whole-wiki census: tests, schema, tags, frontmatter, related, rewrite jobs. Does not rewrite page bodies. Launched by wiki doctor or when doctor ca…

Auto-loaded by the SessionStart hook. Defines when to capture and routes the main agent or detached ingester to the appropriate on-demand skill.

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface as…

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.

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

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

Build Karpathy's LLM Wiki with Claude Code. L1/L2 cache architecture. Logseq + Obsidian support.

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 yo…