Llm Wiki

This is the foundational skill for Andrej Karpathy's LLM Wiki pattern: a three-layer system where raw sources (docs, PDFs, images) get distilled into an Obsidian vault of interconnected markdown pages, governed by a schema that tells the LLM how to maintain it. The wiki isn't a chatbot, it's a compiled artifact. Knowledge gets synthesized once, cross-referenced with wikilinks, and kept current. You get six default categories (concepts, entities, skills, references, synthesis, journal) plus project-specific namespaces. Every page tracks provenance back to sources, and a manifest enables delta ingestion so you only process what's new. Use this when you want to understand the architecture or set up a new knowledge base. Other skills handle the actual operations like ingesting and querying.

skills.sh installs: 4.2K
GitHub stars: 3.7K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add ar9av/obsidian-wiki --skill llm-wiki --agent claude-code

Installs into .claude/skills of the current project.

Files

LLM Wiki — Knowledge Distillation Pattern

You are maintaining a persistent, compounding knowledge base. The wiki is not a chatbot — it is a compiled artifact where knowledge is distilled once and kept current, not re-derived on every query.

Three-Layer Architecture

Layer 1: Raw Sources (immutable)

The user's original documents — articles, papers, notes, PDFs, conversation logs, bookmarks, and images (screenshots, whiteboard photos, diagrams, slide captures). These are never modified by the system. They live wherever the user keeps them (configured via OBSIDIAN_SOURCES_DIR in .env). Images are first-class sources: the ingest skills read them via the Read tool's vision support and treat their interpreted content as inferred unless it's verbatim transcribed text. Image ingestion requires a vision-capable model — models without vision support should skip image sources and report which files were skipped.

Think of raw sources as the "source code" — authoritative but hard to query directly.

SKILL.md on GitHub