llm-wiki

Ingest sources into a persistent, interlinked Markdown knowledge base.

Updated Apr 24, 2026
One-click install
npx skills add https://github.com/Harries/hermes-agent --skill llm-wiki-harries
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: llm-wiki
Source: https://github.com/Harries/hermes-agent/tree/main/skills/research/llm-wiki
Command: npx skills add https://github.com/Harries/hermes-agent --skill llm-wiki-harries

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Karpathy's LLM Wiki provides a persistent, interlinked Markdown knowledge base that ingests sources, cross-references concepts, and keeps content consistent, reducing duplication and drift across research notes.

Core Features & Use Cases

  • Ingest sources into a structured wiki with layers for raw sources, entities, concepts, and queries.
  • Cross-reference pages, lint for consistency, and maintain provenance to ensure traceable knowledge.
  • Use cases include building a long-lived research wiki, answering complex domain questions, and auditing knowledge for contradictions.

Quick Start

Ingest a source into the wiki and seed interconnected pages for core concepts.

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 Markdown knowledge base from research sources?

To build a persistent Markdown knowledge base, ingest sources into structured layers for raw data, entities, and concepts. The system enforces frontmatter metadata and cross-linking to maintain traceable, interlinked research notes.

How does provenance tracking work in an interlinked wiki?

Provenance tracking in an interlinked wiki enforces schema conventions and provenance markers on Markdown pages. This ensures every piece of ingested knowledge remains traceable to its original source, reducing content drift and duplication.

What is the best way to lint a Markdown wiki for consistency?

The best way to lint a Markdown wiki is to run consistency checks that validate frontmatter metadata, schema conventions, and cross-references. This process audits the knowledge base to find contradictions and enforce structural integrity.

Can I use a Markdown wiki to answer complex domain questions?

Yes, you can use a Markdown wiki to answer complex domain questions. By cross-referencing pages and querying the ingested concepts layer, the system retrieves interlinked knowledge to provide traceable answers.

When do I need frontmatter metadata in my knowledge base?

You need frontmatter metadata in your knowledge base when ingesting sources to enforce schema conventions and provenance markers. This structured metadata is required to maintain consistency and traceability across long-lived research notes.