add-karpathy-llm-wiki

Build a structured wiki knowledge base for NauggieClaw groups.

1|2|Updated Apr 8, 2026
One-click install
npx skills add https://github.com/jboothomas/nauggieclaw --skill add-karpathy-llm-wiki
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: add-karpathy-llm-wiki
Source: https://github.com/jboothomas/nauggieclaw/tree/main/.claude/skills/add-karpathy-llm-wiki
Command: npx skills add https://github.com/jboothomas/nauggieclaw --skill add-karpathy-llm-wiki

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

NauggieClaw groups often lack a structured, long-lived knowledge base, leaving insights locked in chat history or scattered sources; this Skill turns every group into a disciplined wiki so valuable domain knowledge is captured, connected, and queryable.

Core Features & Use Cases

  • Collaborative Design: Guides a conversation to define the wiki's domain, sources, and conventions before creating the necessary directories, log, and schema descriptions.
  • Rigorous Schema Construction: Builds the container skill and CLAUDE.md guidance that enforces single-file ingestion discipline, clarifies operations (ingest, query, lint), and points to the wiki/index/log files.
  • Capability Check & Automation: Reviews required file-handling skills (PDF, images, voice, URLs), adds missing helpers, and optionally installs scheduled lint tasks to keep the wiki healthy.

Quick Start

Tell Auggie to run add-karpathy-llm-wiki and answer the setup prompts to build your wiki framework.

Frequently Asked Questions about add-karpathy-llm-wiki

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build a persistent knowledge base for a group workflow?

You can build a persistent knowledge base by following the Karpathy LLM wiki pattern, which creates structured wiki and source directories with schema descriptions for disciplined ingestion. This captures scattered domain knowledge into a queryable format.

What is the Karpathy LLM wiki pattern for structuring a knowledge base?

The Karpathy LLM wiki pattern is a structured approach to building a knowledge base that enforces single-file ingestion discipline through container schema skills. It establishes wiki, source, index, and log files to keep domain knowledge connected and queryable.

How do I set up bulk source ingestion for a Claude LLM wiki?

Bulk source ingestion is set up by collaboratively defining the wiki domain and sources, then building a container skill with CLAUDE.md guidance. This enforces single-file ingestion discipline and clarifies operations like ingest, query, and lint.

Can I automate lint workflows to keep a wiki knowledge base healthy?

Yes, you can optionally install scheduled lint tasks to automatically maintain your wiki knowledge base. The setup process reviews required file-handling skills and adds missing helpers before enabling these automated health checks.

Do I need specific file-handling skills to ingest PDFs and images into a wiki?

Yes, ingesting diverse formats requires specific file-handling skills for PDFs, images, voice, and URLs. The wiki setup reviews your environment for these capabilities and adds missing helper skills before completing the framework.

What is the best way to capture domain knowledge from scattered chat history?

The best way to capture scattered domain knowledge is creating a structured wiki using the Karpathy LLM pattern. It turns conversation insights into a disciplined knowledge base with index updates and lint workflows, making valuable information queryable.