llm-wiki

Ingest and maintain interlinked Markdown knowledge bases for LLM research.

Updated May 3, 2026
One-click install
npx skills add https://github.com/JuanMS20/solviora-agent --skill llm-wiki-juanms20
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: llm-wiki
Source: https://github.com/JuanMS20/solviora-agent/tree/main/skills/research/llm-wiki
Command: npx skills add https://github.com/JuanMS20/solviora-agent --skill llm-wiki-juanms20

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Karpathy's LLM Wiki helps build and maintain a persistent, compounding knowledge base as interlinked Markdown files. It enables cross-references, provenance tracking, and a searchable archive that remains current as new sources are ingested.

Core Features & Use Cases

  • Build and maintain a compounding knowledge base as interlinked Markdown files.
  • Cross-link pages, track provenance, and support Obsidian-compatible linking for research workflows.
  • Ingest sources, lint and audit for consistency, and enable rapid Q&A over a curated knowledge archive.

Quick Start

Create a wiki directory, initialize SCHEMA.md and index.md, then begin ingesting sources to build your LLM knowledge base.

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 for LLM research?

Build an interlinked Markdown knowledge base by creating a wiki directory, initializing SCHEMA.md and index.md, and ingesting sources into raw/ and assets/ folders. This creates a compounding archive with cross-linked entities and provenance tracking.

Does this knowledge base approach support Obsidian-compatible cross-linking?

Yes, the knowledge base supports Obsidian-compatible linking. Pages use frontmatter-based metadata and cross-linking to connect entities, allowing you to navigate and query your research archive directly within Obsidian.

What's the best way to maintain consistency when adding new sources to a Markdown wiki?

Maintain wiki consistency by applying periodic linting and auditing after ingesting new sources. This process checks frontmatter-based pages and cross-references, ensuring your interlinked knowledge base remains accurate and current.

Can I query my research archive after ingesting raw sources into the wiki?

Yes, you can query your research archive after ingestion. The wiki ingests sources into structured folders and applies frontmatter metadata, enabling rapid Q&A and information retrieval over your curated knowledge base.

Do I need a specific folder structure to start a Karpathy-style LLM wiki?

Yes, you need a specific folder structure including raw/ and assets/ directories for sources. You must initialize SCHEMA.md and index.md before ingestion to establish the schema and frontmatter conventions required for cross-linking.

Why use a persistent Markdown wiki instead of isolated research notes?

Use a persistent Markdown wiki to compound knowledge over time. Unlike isolated notes, it tracks provenance, cross-links entities, and remains searchable as new sources are added, creating an interlinked archive for rapid retrieval.