llm-wiki

Ingest sources into a persistent Markdown wiki with YAML frontmatter and wikilinks.

Updated Apr 21, 2026
One-click install
npx skills add https://github.com/samuelmukoti/myai-agent --skill llm-wiki-samuelmukoti
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: llm-wiki
Source: https://github.com/samuelmukoti/myai-agent/tree/main/skills/research/llm-wiki
Command: npx skills add https://github.com/samuelmukoti/myai-agent --skill llm-wiki-samuelmukoti

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Karpathy's LLM Wiki helps researchers and agents build a persistent, interlinked Markdown knowledge base by ingesting sources, enabling fast recall and consistent cross-referencing across sessions.

Core Features & Use Cases

  • Ingest sources (articles, papers, transcripts) into a structured wiki.
  • Cross-link concepts and entities with wikilinks for durable, navigable knowledge.
  • Run linting and schema-aligned checks to maintain consistency and quality.
  • Use the compiled knowledge to answer questions, perform analysis, and synthesize insights across sources.

Quick Start

Ingest your first source and query the knowledge base to see cross-referenced results.

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 wiki from multiple research sources?

Build an interlinked Markdown wiki by ingesting articles, papers, and transcripts into a structured directory. The system applies YAML frontmatter, maintains wikilinks for cross-referencing, and organizes content to enable fast recall across research sessions.

What is the best way to organize research notes with cross-references for long-term recall?

Organize research notes by ingesting sources into a schema-guided directory layout with optional raw sources and references. Enforced YAML frontmatter and wikilinks ensure durable, navigable cross-referencing for consistent long-term recall.

Can I run linting and schema checks on a Markdown knowledge base to maintain consistency?

Yes, you can run linting and schema-aligned checks on a Markdown knowledge base. The system performs quality checks to maintain consistency across pages, validating YAML frontmatter and wikilink structures during ingestion.

Does this Markdown wiki approach work for ingesting raw articles, papers, and transcripts?

Yes, this approach works for ingesting raw articles, papers, and transcripts. The wiki structure includes optional raw sources and references directories, allowing you to organize and cross-link ingested content into navigable pages.

How do I query a compiled knowledge base to synthesize insights across multiple sources?

Query a compiled knowledge base by searching the interlinked Markdown pages after ingestion. Cross-referenced wikilinks connect concepts and entities across sources, enabling you to answer questions and synthesize insights from the organized content.

When should I not use a schema-guided Markdown wiki for note-taking?

Avoid a schema-guided Markdown wiki if your note-taking requires no cross-referencing or if your sources cannot be structured with YAML frontmatter. The system enforces schema alignment, which adds overhead for simple, unstructured notes.