llm-wiki

Build and maintain an interlinked markdown knowledge base with ingest, query, and lint operations.

Updated Sep 20, 2026
One-click install
npx skills add https://github.com/GreenyZA/neo-light --skill llm-wiki-greenyza
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: llm-wiki
Source: https://github.com/GreenyZA/neo-light/tree/main/.hermes-home/skills/research/llm-wiki
Command: npx skills add https://github.com/GreenyZA/neo-light --skill llm-wiki-greenyza

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Scattered research notes and one-off AI answers lose context over time, forcing you to rediscover the same knowledge repeatedly. This Skill maintains a persistent, cross-referenced markdown wiki where sources are ingested once, contradictions are flagged, and synthesis compounds across sessions. ## Core Features & Use Cases - Source Ingestion: Capture URLs, PDFs, and pasted text into an immutable raw/ layer with sha256 drift detection, then synthesize entity, concept, and comparison pages with wikilinks and provenance markers. - Query & Synthesis: Answer domain questions by reading the index and relevant pages, citing wiki sources, and filing valuable answers back as query or comparison pages. - Wiki Linting: Audit for orphan pages, broken wikilinks, stale content, contradictions, tag taxonomy violations, and source drift with severity-grouped reports. - Use Case: A researcher tracking AI/ML developments ingests arxiv papers and articles weekly; the agent updates entity pages for models and labs, cross-links concepts, and the wiki stays navigable via index.md and Obsidian. ## Quick Start Ask the agent to create a new wiki for your research domain and ingest your first source URL into it.

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 markdown knowledge base with an AI agent?▼

Initialize a wiki directory with SCHEMA.md, index.md, and log.md, then ingest sources one at a time. The agent creates entity and concept pages with wikilinks, updates the index, and logs every action so knowledge compounds across sessions.

What is the difference between an LLM wiki and RAG?▼

RAG rediscovers knowledge from scratch per query, while the wiki compiles knowledge once into interlinked markdown pages. Cross-references, contradictions, and synthesis persist between sessions instead of being recomputed each time.

Does the llm-wiki skill work with Obsidian?▼

Yes, the wiki directory works as an Obsidian vault out of the box. Wikilinks render as clickable links, YAML frontmatter powers Dataview queries, and obsidian-headless enables sync on servers without a display.

How do I set the wiki location for this skill?▼

Set the WIKI_PATH environment variable in your Hermes .env file. If unset, the skill defaults to ~/wiki as the knowledge base directory.

Why does my wiki accumulate duplicate or orphan pages?▼

Duplicates happen when orientation reads are skipped before ingesting; always read SCHEMA.md, index.md, and recent log entries first. Orphans are pages with no inbound wikilinks, which the lint operation detects and reports.

When should I not create a new wiki page?▼

Do not create pages for passing mentions or minor details outside the domain. The schema's page thresholds require an entity or concept to appear in 2+ sources or be central to one source before warranting a page.