llm-wiki

Build persistent interlinked markdown knowledge bases from sources.

Updated May 16, 2026
One-click install
npx skills add https://github.com/jaredcroxton/hermes-mirror --skill llm-wiki-jaredcroxton
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: llm-wiki
Source: https://github.com/jaredcroxton/hermes-mirror/tree/main/agents/skills/research/llm-wiki
Command: npx skills add https://github.com/jaredcroxton/hermes-mirror --skill llm-wiki-jaredcroxton

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill solves the problem of turning scattered research notes into a durable, interlinked knowledge base that grows over time instead of being relearned from scratch.

Core Features & Use Cases

  • Persistent LLM Wiki architecture: Creates and maintains an interlinked three-layer markdown system (raw sources, curated wiki pages, and a controlling schema).
  • Guided ingestion and curation: Converts new sources into entities, concepts, comparisons, and queryable sections while enforcing conventions, cross-links, and provenance.
  • Quality control via linting: Audits wikilinks, index completeness, frontmatter validity, staleness, contradictions, orphans, and raw-content drift.

Quick Start

Tell the skill to initialize a new LLM Wiki at your desired path, define the domain-specific schema, and ingest your first source into the correct layer-appropriate pages.

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 scattered research notes?

You can build a persistent markdown knowledge base by ingesting sources and compiling them into interlinked entities, concepts, and comparisons. This structure enforces provenance and wikilink cross-referencing so your knowledge compounds across sessions.

How does wiki linting work for broken wikilinks and frontmatter schema violations?

Wiki linting audits your markdown files to detect orphans, broken wikilinks, frontmatter schema violations, staleness, contradictions, and source drift. This quality control mechanism ensures your knowledge base remains accurate and internally consistent.

What is the best way to organize raw research sources into a curated wiki?

The best way to organize raw sources is using a three-layer markdown system: raw sources, curated wiki pages, and a controlling schema. This architecture separates original artifacts from compiled knowledge while maintaining strict provenance.

Can I use a markdown wiki as a RAG alternative for knowledge management?

Yes, a markdown wiki serves as a RAG alternative by reading compiled wiki pages to answer questions instead of retrieving raw chunks. It enforces entity linking and provenance, creating a self-compounding knowledge base that grows over time.

How do I configure a wiki directory path for ingesting URLs and files?

You configure the wiki directory by setting the WIKI_PATH environment variable, which defaults to ~/wiki. The system uses SCHEMA.md, index.md, and log.md for session orientation when processing URLs, files, or pastes into raw artifacts.

Why does my markdown wiki have orphan pages and source drift?

Orphan pages and source drift occur when raw content changes without updating curated wiki pages. Running a wiki linting audit detects these issues, along with broken wikilinks and contradictions, ensuring your knowledge base maintains strict provenance.