llm-wiki

Create and maintain a persistent interlinked markdown knowledge base.

Updated Sep 1, 2021
One-click install
npx skills add https://github.com/unclehowell/unclehowell --skill llm-wiki-unclehowell
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: llm-wiki
Source: https://github.com/unclehowell/unclehowell/tree/main/skills/research/llm-wiki
Command: npx skills add https://github.com/unclehowell/unclehowell --skill llm-wiki-unclehowell

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It replaces ad‑hoc, per‑query retrieval with a persistent, compounding markdown knowledge base that stays consistent, cross‑referenced, and auditable over time.

Core Features & Use Cases

  • Ingest Sources: Capture raw articles, papers, and transcripts into a structured raw/ layer.
  • Schema‑Driven Wiki: Enforce conventions, front‑matter, and taxonomy via SCHEMA.md.
  • Cross‑Linking & Indexing: Automatically create interlinked entity, concept, and comparison pages and keep index.md up to date.
  • Query & Lint: Retrieve synthesized answers from the wiki and run health‑checks for orphan pages, broken links, and stale content.
  • Use Case: A researcher can build a living AI/ML wiki, continuously ingest new papers, and instantly query the accumulated knowledge without re‑reading every source.

Quick Start

Ask the llm-wiki skill to create a new wiki at ~/my-wiki and ingest the article https://example.com/ai-overview.md.

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 knowledge base from research papers?

To build a persistent markdown knowledge base, you can ingest raw articles and papers into a structured directory, enforce schema conventions, and automatically generate cross-linked entity pages to create a compounding, auditable wiki.

What is the best way to maintain cross-references and consistency in a local wiki directory?

Maintaining consistency in a local wiki directory involves using a schema-driven approach to enforce front-matter and taxonomy, while running automated linting health-checks to detect orphan pages, broken links, and stale content.

How can I query accumulated markdown research sources without re-reading every document?

You can query accumulated markdown research sources by using built-in retrieval scripts to synthesize answers from the ingested knowledge base, retrieving specific information instantly without manually re-reading the original documents.

Does this markdown wiki approach work for continuously ingesting new research transcripts?

Yes, this markdown wiki approach supports continuously ingesting new research transcripts into a raw source layer, automatically updating the index and interlinked concept pages to keep the compiled knowledge base current.

How do I find broken links and orphan pages in an interlinked markdown wiki?

To find broken links and orphan pages in an interlinked markdown wiki, you can run a built-in linting health-check that audits the directory structure and flags inconsistencies or stale content for review.

When do I need a schema-driven markdown wiki instead of ad-hoc per-query retrieval?

You need a schema-driven markdown wiki instead of ad-hoc per-query retrieval when your research project requires a compounding knowledge base that stays consistently cross-referenced, auditable, and structured over time.