llm-wiki

Ingest sources into an interlinked Markdown knowledge base with wikilinks and provenance tags.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/shiftrepo/aws --skill llm-wiki-shiftrepo
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: llm-wiki
Source: https://github.com/shiftrepo/aws/tree/main/HermesAgent/skills/skills/research/llm-wiki
Command: npx skills add https://github.com/shiftrepo/aws --skill llm-wiki-shiftrepo

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Karpathy's LLM Wiki enables you to build and maintain a persistent, interlinked Markdown knowledge base. It ingests sources, queries compiled knowledge, and lint for consistency.

Core Features & Use Cases

  • Ingest sources into a persistent wiki
  • Query compiled knowledge across interlinked pages
  • Lint for consistency and detect contradictions across content

Quick Start

Ingest a source into the wiki and begin querying the interlinked 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 multiple sources?

An interlinked Markdown knowledge base is built by ingesting sources and applying wikilink cross-references. This process uses frontmatter-based discovery and taxonomy-driven organization to create a persistent, queryable wiki.

What is provenance tagging in a Markdown wiki?

Provenance tagging in a Markdown wiki is the process of tracking the origin of ingested information. It ensures that cross-referenced notes maintain source attribution, enabling scalable querying and ongoing content verification.

How do I detect contradictions across interlinked Markdown notes?

To detect contradictions in interlinked Markdown notes, you run a consistency linting process. This checks the compiled knowledge base for conflicting information across cross-referenced pages to maintain content integrity.

Can I use wikilinks and frontmatter for Markdown knowledge base organization?

Yes, you can use wikilinks and frontmatter for Markdown knowledge base organization. Wikilinks establish cross-references between pages, while frontmatter enables taxonomy-driven discovery and scalable querying across the wiki.

What is the best way to maintain a persistent knowledge base for researchers?

The best way to maintain a persistent knowledge base for researchers is to use automated ingestion and linting. This ensures source provenance tagging and cross-referenced notes remain consistent and queryable as the wiki scales.

Why does my Markdown knowledge base need linting?

Your Markdown knowledge base needs linting to detect contradictions and maintain consistency across interlinked pages. Without it, ongoing ingestion and taxonomy-driven organization would eventually lead to conflicting or broken cross-references.