llm-wiki
The foundational knowledge distillation pattern for building and maintaining an AI-powered Obsidian wiki. Based on Andrej Karpathy's LLM Wiki architecture. Use this skill whenever the user wants to understand the wiki pattern, set up a new knowledge base, or needs guidance on the three-layer architecture (raw sources → wiki → schema). Also use when discussing knowledge management strategy, wiki structure decisions, or how to organize distilled knowledge. This is the "theory" skill — other skills handle specific operations (ingesting, querying, linting).
npx skills add Ar9av/obsidian-wiki --skill llm-wiki --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Describes a knowledge-distillation pattern to build and maintain an AI-powered Obsidian wiki. It guides users on understanding the wiki pattern, setting up a new knowledge base, and organizing knowledge using a three-layer architecture (raw sources, the wiki, and the schema). It positions the wiki as a compiled artifact rather than a responsive chatbot, and it outlines how to organize content into categories (concepts, entities, skills, references, synthesis, journal) and projects, including how pages should be linked and how provenance and frontmatter are used.
How it works
Outlines a concrete three-layer workflow:
- Layer 1: Raw Sources (immutable) including documents and images, stored outside the wiki; images are ingested with vision support and treated as inferred unless transcribed.
- Layer 2: The Wiki (LLM-maintained) consisting of Obsidian-compatible markdown files with YAML frontmatter, wikilinks, and clear provenance; stored at the path defined by OBSIDIAN_VAULT_PATH.
- Layer 3: The Schema (the skill + config) governing structure, categories, page templates, and workflows.
Describes wiki organization with two structural levels: categories and projects, and provides specific category directories (concepts, entities, skills, references, synthesis, journal). Also specifies naming and linking conventions for project pages and a template for new pages including frontmatter fields like title, category, tags, sources, provenance, and lifecycle.
When to use it
Use when the user wants to understand the wiki pattern, set up a new knowledge base, or needs guidance on the three-layer architecture, knowledge-management strategy, wiki structure decisions, or organizing distilled knowledge. This is the theory-oriented skill; other skills handle ingestion, querying, and linting.
What it can touch
Not applicable in this excerpt beyond describing the schema and file organization. The summary indicates the wiki files and frontmatter templates, and references the paths and folder structure that would be manipulated by ingestion and maintenance skills.
Caveats
Notes that the wiki is a compiled artifact, not a chatbot, and that images require vision-capable models for ingestion. Field values such as paths, categories, and templates are described as rules for organization and do not guarantee successful ingestion or querying outcomes.
# 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, bookma
What does the llm-wiki skill do?
The foundational knowledge distillation pattern for building and maintaining an AI-powered Obsidian wiki. Based on Andrej Karpathy's LLM Wiki architecture. Use this skill whenever the user wants to understand the wiki pattern, set up a new knowledge base, or needs guidance on the three-layer architecture (raw sources → wiki → schema). Also use when discussing knowledge management strategy, wiki structure decisions, or how to organize distilled knowledge. This is the "theory" skill — other skills handle specific operations (ingesting, querying, linting).
How do I install it?
Run `npx skills add Ar9av/obsidian-wiki --skill llm-wiki --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From Ar9av/obsidian-wiki, a repository with 3,115 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.