llm-wiki

Ingest diverse sources into an interlinked Obsidian-compatible Markdown knowledge base.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/HugoAlmeidaMoreira/zeus-agent --skill llm-wiki-hugoalmeidamoreira
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: llm-wiki
Source: https://github.com/HugoAlmeidaMoreira/zeus-agent/tree/main/skills/research/llm-wiki
Command: npx skills add https://github.com/HugoAlmeidaMoreira/zeus-agent --skill llm-wiki-hugoalmeidamoreira

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Karpathy's LLM Wiki provides a method to build and maintain a persistent, interlinked markdown knowledge base that stays up-to-date as new sources are ingested, without reprocessing from scratch for every query.

Core Features & Use Cases

  • Interlinked markdown pages with a defined schema for entities, concepts, and queries, enabling fast navigation and traceable knowledge synthesis.
  • Persistent, compounding knowledge base that evolves as sources are ingested, with provenance markers and cross-references to ensure consistency.
  • Use case: researchers ingest diverse sources and query for cross-cutting insights with traceable sources and summaries.

Quick Start

Create a new wiki with an initialized schema, index, and cross-linked pages ready for ingestion.

Frequently Asked Questions about llm-wiki

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

FAQPage Schema
How do I build an interlinked Markdown knowledge base from diverse research sources?

An interlinked Markdown knowledge base organizes diverse ingested sources into persistent pages with cross-linking and provenance tracking. This enables fast, contextual queries across entities and concepts without reprocessing from scratch.

What is the best way to maintain a persistent knowledge wiki as new research sources are added?

A persistent knowledge wiki stays up-to-date by applying cross-linking and provenance markers to new sources as they are ingested. This compounding structure evolves continuously without reprocessing the entire knowledge base for every new query.

Can I use an Obsidian-compatible structure for my research wiki?

Yes, the research wiki satisfies an Obsidian-compatible structure by utilizing Markdown frontmatter and wikilinks for reliable navigation. This ensures entities, concepts, and notes remain interlinked and traceable across the knowledge base.

How do I track provenance and cross-references in a Markdown wiki?

To track provenance and cross-references in a Markdown wiki, apply provenance markers and wikilinks during source ingestion. This ensures traceable knowledge synthesis and consistency across interlinked entities, concepts, and notes.

Does the knowledge base support fast contextual queries across multiple entities?

Yes, the knowledge base supports fast contextual queries across entities by applying cross-linking and a defined schema during ingestion. This allows researchers to query cross-cutting insights with traceable sources and summaries.

When do I need a compounding Markdown wiki for RAG instead of reprocessing sources?

You need a compounding Markdown wiki for RAG when ingesting diverse sources continuously and needing traceable, cross-cutting insights. It prevents reprocessing from scratch by maintaining persistent, interlinked pages with provenance markers.