skills.rest
afel6
afel6COMMUNITY
Explore all skills by this author →
GitHub

llm-wiki

Build and maintain an interlinked markdown knowledge base with YAML frontmatter and SCHEMA-driven organization.

Updated Mar 25, 2026
Search Tags:#markdown#obsidian#wiki#lint#knowledge-base#ingest#rag-alternative
One-click install
npx skills add https://github.com/afel6/scal-ai-pipeline --skill llm-wiki-afel6
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: llm-wiki
Source: https://github.com/afel6/scal-ai-pipeline/tree/main/hermes_skills_library/research/llm-wiki
Command: npx skills add https://github.com/afel6/scal-ai-pipeline --skill llm-wiki-afel6

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The LLM Wiki skill removes repeated rediscovery and fragile single-query retrieval by building a persistent, interlinked markdown knowledge base that accumulates, cross-references, and flags contradictions over time. It prevents duplicate work, preserves provenance, and makes synthesized knowledge instantly queryable for research and engineering workflows.

Core Features & Use Cases

  • Structured Ingest: Capture raw sources (articles, PDFs, transcripts) into a read-only raw layer and convert salient content into agent-managed wiki pages.
  • Consistent Organization: Enforce a SCHEMA-driven structure with YAML frontmatter, index.md navigation, and an append-only log to maintain provenance and discoverability.
  • Query & Synthesis: Read index and relevant pages, synthesize answers from compiled knowledge, and optionally file substantial results back into queries or comparison pages.
  • Health & Linting: Programmatic checks for orphan pages, broken links, frontmatter validation, staleness, contradictions, and log rotation to keep the vault healthy.
  • Obsidian-Compatible: Works as a plain-folder vault for Obsidian, supporting wikilinks, Dataview-friendly frontmatter, and headless sync on servers.
  • Use Case: Ingest a set of arXiv papers and meeting notes, automatically update entity and concept pages, run a lint to find broken links, then answer a cross-paper synthesis question citing the wiki pages used.

Quick Start

Point the skill at your wiki directory (default ~/wiki), perform the orientation reads of SCHEMA.md, index.md, and recent log entries, then ingest the source you want added to the wiki.

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 and transcripts?▼

To build a persistent markdown knowledge base, ingest raw sources like articles, PDFs, and transcripts into a read-only raw layer, then convert salient content into agent-managed wiki pages with YAML frontmatter and cross-referenced links. This prevents duplicate work and preserves provenance.

Can I use Obsidian with a markdown wiki generated by an LLM?▼

Yes, the generated markdown wiki is Obsidian-compatible and works as a plain-folder vault. It supports wikilinks, Dataview-friendly YAML frontmatter, and allows headless sync on servers, enabling seamless integration with your existing Obsidian workflow.

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 programmatic health and linting checks. These checks validate frontmatter, detect staleness, flag contradictions, manage log rotation, and ensure your markdown wiki remains healthy and navigable.

How does a persistent interlinked wiki compare to standard RAG for knowledge retrieval?▼

Unlike standard RAG's fragile single-query retrieval, an interlinked markdown wiki accumulates, cross-references, and flags contradictions over time. It removes repeated rediscovery by making synthesized knowledge instantly queryable while preserving source provenance.

Do I need a specific folder structure to maintain a markdown wiki with YAML frontmatter?▼

You need a SCHEMA-driven folder structure to maintain a markdown wiki. This structure enforces consistent organization using YAML frontmatter, an index.md file for navigation, and an append-only log to maintain provenance and discoverability across all ingested content.

Related Skills

Explore More Education & Research Skills→
MarbleSodasMarbleSodas

llm-wiki

Build and maintain interlinked markdown knowledge bases with schema-aligned metadata.

Community
Advanced
HelloWorldSunginHelloWorldSungin

wiki-query

Query Obsidian vaults with tiered retrieval across multiple backends and citations.

Community
Advanced
markwang2658markwang2658
31

llm-wiki

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

Community
Advanced
danmartinez78danmartinez78

llm-wiki

Ingest sources into a persistent Markdown wiki with wikilinks and frontmatter.

Community
Advanced