llm-wiki

Create and maintain an interlinked Markdown knowledge base with YAML frontmatter.

Updated Jun 15, 2026
One-click install
npx skills add https://github.com/faramirezs/talking_printer --skill llm-wiki-faramirezs
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: llm-wiki
Source: https://github.com/faramirezs/talking_printer/tree/main/hermes-agent/skills/research/llm-wiki
Command: npx skills add https://github.com/faramirezs/talking_printer --skill llm-wiki-faramirezs

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Karpathy's LLM Wiki pattern enables building and querying a persistent, interlinked markdown knowledge base that consolidates scattered notes, sources, and cross-references, reducing duplication and inconsistency.

Core Features & Use Cases

  • Creates a structured, interlinked markdown wiki with raw sources, entities, concepts, and queries
  • Ingests sources, maintains provenance, cross-references pages, and performs consistency checks
  • Answers questions against a configured local wiki path and supports auditing and health checks

Quick Start

Instruct the agent to initialize or update the wiki from your notes and sources.

Frequently Asked Questions about llm-wiki

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build a persistent knowledge base from scattered markdown notes?

You build a persistent knowledge base by ingesting notes into a structured markdown wiki with enforced YAML frontmatter, provenance markers, and cross-linking to eliminate duplication and maintain source consistency.

What is an LLM wiki and how does it differ from standard RAG?

An LLM wiki is a persistent, interlinked markdown knowledge base that consolidates sources and cross-references, functioning as a RAG alternative by querying a configured local wiki path to reduce duplication and inconsistency.

How do I ingest sources into a markdown wiki while maintaining provenance?

You ingest sources by instructing the agent to update the wiki, a process that enforces provenance markers, tracks origins, performs consistency checks, and maintains structured cross-references across pages.

Can I use this to lint and check the health of my existing knowledge base?

Yes, you can lint and check health by querying the configured wiki path to perform consistency checks, audit provenance markers, enforce page thresholds, and identify structural issues across your markdown knowledge base.

What are the limitations of using markdown cross-linking for knowledge management?

Limitations include strict structural requirements: your markdown files must conform to enforced YAML frontmatter, provenance markers, and page thresholds, meaning non-compliant sources require formatting before safe ingestion.