skills.rest
Araara7
Araara7COMMUNITY
Explore all skills by this author →
GitHub

llm-wiki

Build and maintain an interlinked markdown knowledge base from ingested sources.

1|Updated Jun 1, 2026
Search Tags:#markdown#research#knowledge base#obsidian#ingestion#wiki#wikilinks
One-click install
npx skills add https://github.com/Araara7/hermes-skills --skill llm-wiki-araara7
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: llm-wiki
Source: https://github.com/Araara7/hermes-skills/tree/main/research/llm-wiki
Command: npx skills add https://github.com/Araara7/hermes-skills --skill llm-wiki-araara7

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Traditional RAG rediscovers knowledge from scratch on every query, losing cross-references and synthesis. This Skill builds a persistent, compounding markdown wiki where sources are ingested once, cross-linked, and kept current, so answers reflect everything ever ingested. ## 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 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 maintains entity pages for models and labs, flags contradictions between sources, and the whole wiki opens directly in Obsidian. ## Quick Start Ask the agent to create a new wiki for your research domain, then provide your first source URL or file to ingest.

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 the schema, index, and log, then ingests sources you provide into cross-linked markdown pages.

How is an LLM wiki different from RAG?▼

RAG retrieves and re-derives knowledge from raw documents on every query, while the wiki compiles knowledge once into interlinked pages. Cross-references, contradictions, and synthesis persist between sessions instead of being recomputed.

Does the markdown wiki work with Obsidian?▼

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

How do I check a markdown wiki for broken links and orphan pages?▼

Ask the agent to lint the wiki. The lint operation scans for orphan pages with no inbound wikilinks, broken links, missing index entries, invalid frontmatter, stale content, contradictions, and source drift, then reports findings grouped by severity.

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 it gets its own page.

Related Skills

Explore More Education & Research Skills→
SebasArenSebasAren
2

obsidian-wiki-ingest

Classify raw materials and generate wiki pages from PDFs, notes, and URLs.

Community
Advanced
Abulfadl-AhmadiAbulfadl-Ahmadi

wiki-dashboard

Automate dynamic Obsidian vault dashboards using Bases or Dataview.

Community
Intermediate
xqinagxqinag

citation-audit

Verify manuscript citations against authoritative sources with per-entry verdicts.

Community
Advanced
davron-designdavron-design

wiki-generator

Scaffold a wiki vault with raw, wiki, and output directories.

Community
Intermediate