skills.rest
photonics-dhl
photonics-dhlCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

llm-wiki

Ingest unstructured knowledge into a persistent markdown wiki with cross-links and linting.

Updated Apr 30, 2026
Search Tags:#markdown#wiki#lint#knowledge-base#ingest#wikilinks
One-click install
npx skills add https://github.com/photonics-dhl/Hermes --skill llm-wiki-photonics-dhl
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: llm-wiki
Source: https://github.com/photonics-dhl/Hermes/tree/main/hermes-home/skills/research/llm-wiki
Command: npx skills add https://github.com/photonics-dhl/Hermes --skill llm-wiki-photonics-dhl

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Karpathy's LLM Wiki pattern enables a persistent, interlinked markdown knowledge base that avoids re-ingesting data for each query, accelerating research and knowledge synthesis.

Core Features & Use Cases

  • Builds a connected markdown wiki with layers for raw sources, entities, concepts, and queries.
  • Ingests sources, auto-generates cross-links, and lint-checks for consistency across pages.
  • Use Case: researchers curate sources and retrieve synthesized knowledge without reprocessing all data.

Quick Start

Create or load a wiki at the configured path and ingest an initial source to populate the 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 a persistent markdown wiki from unstructured research sources?▼

A markdown wiki ingests unstructured sources and organizes them into layered folders for raw data, entities, and concepts. It auto-generates wikilinks and lint-checks pages to maintain a consistent, interlinked knowledge base.

Can I use this markdown wiki with Obsidian and Dataview?▼

Yes, the generated markdown wiki is compatible with Obsidian and Dataview. It enforces frontmatter-based metadata and a specific folder structure so you can immediately query and visualize your interconnected knowledge base.

What is the best way to organize markdown knowledge bases to avoid re-ingesting data?▼

The best way to avoid re-ingesting data is using a persistent markdown wiki with layered folders for sources, entities, concepts, and queries. This structure retains ingested knowledge so you can retrieve and synthesize information without reprocessing.

How do wikilinks and frontmatter linting work in a markdown knowledge base?▼

Wikilinks and frontmatter linting enforce cross-linking rules and schema-based metadata validation across the wiki. The linter checks interlinked pages to ensure all references and frontmatter fields meet the required documentation structure.

Does this knowledge base tool require any external dependencies to function?▼

No external dependencies are required to function. The markdown wiki tool operates independently to ingest sources, apply frontmatter schemas, generate wikilinks, and lint knowledge base files without needing additional packages.

Related Skills

Explore More Education & Research Skills→
Astro-HanAstro-Han
1.8k

karpathy-llm-wiki

Compile raw source materials into structured markdown wiki pages.

Community
Advanced
markwang2658markwang2658
31

llm-wiki

Ingest sources into a persistent interlinked markdown wiki with schema compliance.

Community
Advanced
cdeistopenedcdeistopened
2

obsidian-markdown

Standardize Obsidian-specific Markdown syntax for wikilinks, embeds, dataview, and callouts.

Community
Basic
handsomelong922handsomelong922

chroma

Store and retrieve embeddings with metadata using a vector database.

Community
Intermediate