add-karpathy-llm-wiki

Ingest documents into a persistent wiki knowledge base for NanoClaw groups.

Updated Apr 13, 2026
One-click install
npx skills add https://github.com/nrupala/nanoclaw --skill add-karpathy-llm-wiki-nrupala
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: add-karpathy-llm-wiki
Source: https://github.com/nrupala/nanoclaw/tree/main/.claude/skills/add-karpathy-llm-wiki
Command: npx skills add https://github.com/nrupala/nanoclaw --skill add-karpathy-llm-wiki-nrupala

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps NanoClaw groups escape knowledge drift by building and maintaining a persistent wiki knowledge base that interlinks sources, summaries, and concepts.

Core Features & Use Cases

  • Persistent knowledge base: converts scattered sources into a structured wiki to retain insights over time.
  • Three-layer architecture: raw sources, wiki pages, and a schema that governs ingestion, querying, and maintenance.
  • Ingest, query, and lint: end-to-end workflows for adding content, answering questions with cross-references, and keeping the wiki healthy.

Quick Start

Ingest your first source into the wiki group to initialize the three-layer pattern.

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 from scattered group documents?

You can build a persistent knowledge base by ingesting documents into a three-layer wiki architecture that separates raw sources, wiki pages, and a governing schema. This structure interlinks sources and concepts to retain long-term insights and prevent knowledge drift.

What is the three-layer wiki architecture for managing group knowledge?

The three-layer wiki architecture consists of raw sources, wiki pages, and a defined schema. The schema guides ingestion, querying, and maintenance, ensuring that accumulated knowledge is properly condensed, cross-referenced, and linked over time.

How do I ingest and cross-reference sources into a wiki knowledge base?

You ingest sources through a per-source ingestion discipline that feeds into the wiki layer. The system then applies cross-referencing and condensation to interlink the new content with existing summaries and concepts, maintaining a healthy and structured knowledge base.

Does building a cross-referenced wiki require a defined schema file?

Yes, building this wiki requires a defined CLAUDE.md schema to guide ingestion, querying, and maintenance. This schema enforces the three-layer architecture and per-source ingestion discipline necessary for long-term knowledge linkage.

What is the best way to maintain a wiki knowledge base and prevent knowledge drift?

The best way to maintain a wiki and prevent knowledge drift is through end-to-end workflows that include ingesting content, querying with cross-references, and running lint checks. This keeps the wiki healthy and ensures sources remain properly interlinked.