skills.rest
jakubbartnik
jakubbartnikCOMMUNITY
Explore all skills by this author →
GitHub

llm-wiki

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

Updated Aug 19, 2026
Search Tags:#markdown#research#knowledge base#obsidian#wiki#ingest#rag-alternative
One-click install
npx skills add https://github.com/jakubbartnik/honey-barrel-finale --skill llm-wiki-jakubbartnik
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: llm-wiki
Source: https://github.com/jakubbartnik/honey-barrel-finale/tree/main/honey-barrel-finale/workspace/hermes/skills/research/llm-wiki
Command: npx skills add https://github.com/jakubbartnik/honey-barrel-finale --skill llm-wiki-jakubbartnik

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Traditional RAG rediscovers knowledge from scratch on every query, losing cross-references and synthesis. This Skill maintains a persistent, compounding markdown knowledge base where sources are ingested once, cross-referenced, and kept current over time. ## 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 pages, and filing valuable answers back into the wiki. - Lint & Health Checks: Audit the wiki for orphan pages, broken wikilinks, stale content, contradictions, tag taxonomy violations, and source drift. - Use Case: A researcher tracking AI/ML developments ingests arxiv papers and articles weekly; the agent updates entity pages, flags contradictions between sources, and keeps an Obsidian-compatible vault synced across devices. ## Quick Start Create a new wiki at ~/wiki for AI research and ingest this article 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?▼

Set the WIKI_PATH environment variable or use the default ~/wiki directory, then ask the agent to initialize a wiki for your domain. The agent creates SCHEMA.md, index.md, and log.md, then ingests sources into interlinked entity and concept pages.

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

RAG retrieves and re-derives knowledge from raw documents on every query, while the wiki compiles knowledge once into cross-referenced markdown pages. Contradictions are flagged at ingest time and synthesis persists across sessions.

Does the llm-wiki skill work with Obsidian?▼

Yes, the wiki directory functions as an Obsidian vault out of the box, with wikilinks, YAML frontmatter for Dataview, and graph view. On headless servers, obsidian-headless can sync the vault via Obsidian Sync.

How does the wiki detect when a source has changed?▼

Each raw source stores a sha256 hash of its body in frontmatter. On re-ingest of the same URL, the agent recomputes the hash and skips unchanged content or flags drift when the content differs.

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 two or more sources, or be central to one source, before warranting a page.

Related Skills

Explore More Education & Research Skills→
cryptopaficryptopafi

llm-wiki

Ingest sources into a persistent Markdown wiki with Obsidian-style wikilinks.

Community
Advanced
RonanCodesRonanCodes

slides

Generate Marp-format slide decks from wiki content.

Community
Intermediate
NirajkashyapNirajkashyap

wiki-ingest

Ingest documents into an Obsidian wiki as interconnected wiki pages.

Community
Advanced
jhl-labsjhl-labs
50

RAG & Vector Search

Retrieve relevant documents and augment LLM prompts with vector search.

Official
Advanced