llm-wiki

Build and maintain an interlinked Markdown knowledge base with wikilinks and sha256 provenance.

2|Updated Apr 25, 2026
One-click install
npx skills add https://github.com/john-data-chen/hermes-agent-backup --skill llm-wiki-john-data-chen
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: llm-wiki
Source: https://github.com/john-data-chen/hermes-agent-backup/tree/main/skills/research/llm-wiki
Command: npx skills add https://github.com/john-data-chen/hermes-agent-backup --skill llm-wiki-john-data-chen

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Karpathy's LLM Wiki enables building and maintaining a persistent, interlinked Markdown knowledge base from diverse sources so users can navigate complex knowledge with cross-references and provenance.

Core Features & Use Cases

  • Create a centralized, cross-referenced Markdown knowledge base from ingested sources (articles, notes, papers) that stays current.
  • Use [[wikilinks]] to connect entities, concepts, and queries, enabling rapid, contextual retrieval.
  • Maintain a structured schema and provenance to support audits, updates, and collaborative curation.

Quick Start

Instruct the agent to initialize a new wiki and begin ingesting sources into an interlinked Markdown 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 from research notes?

Build an interlinked Markdown knowledge base by ingesting diverse sources like articles and papers, then organizing them into entities and concepts with cross-references. The wiki applies structured frontmatter and [[wikilinks]] to connect notes for reliable knowledge synthesis.

What is the best way to organize ingested sources into a cross-referenced wiki?

Organizing ingested sources into a cross-referenced wiki involves mapping content into entities and concepts connected through [[wikilinks]]. This structure supports contextual retrieval and maintains sha256 provenance for raw sources to ensure reliable knowledge synthesis.

Can I use an Obsidian-compatible structure for my knowledge base with this approach?

Yes, an Obsidian-compatible structure is fully supported through [[wikilinks]] for cross-linking entities and concepts. The knowledge base enforces structured frontmatter requirements including title, created, updated, type, tags, and sources for valid interlinked Markdown files.

How do I maintain provenance and audit sources in a Markdown wiki?

Maintain provenance and audit sources by applying sha256 hashing to raw ingested sources and enforcing structured frontmatter. This supports reliable knowledge synthesis, audits, updates, and collaborative curation within the persistent interlinked Markdown knowledge base.

Does the interlinked wiki approach work for ingesting academic papers and research notes?

Yes, ingesting academic papers and research notes is a core use case for the interlinked wiki. Diverse sources are ingested and organized into entities, concepts, and queries with cross-links and provenance for reliable knowledge synthesis.

What frontmatter is required to create a valid interlinked Markdown wiki entry?

Creating a valid interlinked Markdown wiki entry requires frontmatter fields including title, created, updated, type, tags, and sources. This schema ensures the persistent knowledge base maintains structure for audits and reliable knowledge synthesis.