llm-wiki

Maintain a persistent interlinked markdown knowledge base from URLs, PDFs, and pasted text.

1|Updated Apr 24, 2026
One-click install
npx skills add https://github.com/automatedigital/spark --skill llm-wiki-automatedigital
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: llm-wiki
Source: https://github.com/automatedigital/spark/tree/main/skills/research/llm-wiki
Command: npx skills add https://github.com/automatedigital/spark --skill llm-wiki-automatedigital

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Traditional RAG systems re-discover and re-process raw knowledge from scratch for every query, leading to redundant work, inconsistent cross-references, and missed synthesis of accumulated insights. This Skill eliminates that overhead by maintaining a persistent, pre-compiled knowledge base that grows smarter with every source you ingest.

Core Features & Use Cases

  • Persistent Compounding Knowledge: Ingest sources (web articles, PDFs, transcripts, pasted text) once, then query synthesized, cross-referenced answers indefinitely without re-reading raw material.
  • Automated Consistency Maintenance: Lint for orphan pages, broken wikilinks, stale content, and tag taxonomy violations to keep your knowledge base clean and navigable.
  • Seamless Tool Integration: Works out of the box with Obsidian, VS Code, and any markdown editor, with optional headless sync for server-based agents and desktop vaults.
  • Use Case: A researcher studying AI safety can ingest 50 arxiv papers and blog posts once, then instantly query for comparisons between alignment techniques, with all cross-references and contradictions already flagged.

Quick Start

Use the llm-wiki skill to ingest the provided article on large language model scaling laws and update the relevant wiki pages with new findings and cross-references.

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 for research notes instead of using standard RAG?

Build a persistent markdown wiki by ingesting sources like URLs and PDFs once, then querying synthesized, cross-referenced answers indefinitely without re-reading raw material. This avoids the redundant re-processing and inconsistent cross-referencing typical of standard RAG systems.

How does automated wikilink cross-referencing work for interlinked knowledge bases?

Automated wikilink cross-referencing works by creating and updating markdown pages with new findings, flagging contradictions, and maintaining an index. It compiles ingested sources into a persistent, interlinked structure that grows smarter with each query.

Can I sync my interlinked markdown wiki with an Obsidian vault?

Yes, you can sync your interlinked markdown wiki with an Obsidian vault. The system supports optional headless sync for server-based agents and desktop vaults, working seamlessly with Obsidian, VS Code, and any markdown editor.

What is the best way to find broken links and orphan pages in a markdown wiki?

The best way to find broken links and orphan pages is to run an automated consistency audit. This lints your markdown wiki for orphan pages, broken wikilinks, stale content, and tag taxonomy violations to keep the knowledge base navigable.

Does this knowledge base tool support ingesting PDFs and web articles?

Yes, this knowledge base tool supports ingesting PDFs and web articles. It handles end-to-end source ingestion from URLs, PDFs, transcripts, and pasted text to pre-compile domain-specific research notes and insights.