skills.rest
AjayRajan05
AjayRajan05COMMUNITY
Explore all skills by this author →
WebsiteGitHub

llm-wiki

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

5|2|Updated Mar 12, 2026
Search Tags:#markdown#research#knowledge base#obsidian#ingestion#wiki#rag-alternative
One-click install
npx skills add https://github.com/AjayRajan05/VoiceOS --skill llm-wiki-ajayrajan05
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: llm-wiki
Source: https://github.com/AjayRajan05/VoiceOS/tree/main/skills/bundled/community/research/llm-wiki
Command: npx skills add https://github.com/AjayRajan05/VoiceOS --skill llm-wiki-ajayrajan05

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 wiki where sources are ingested once, cross-linked, and kept current, so accumulated knowledge is immediately queryable. ## 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 sources, and filing valuable answers back into the wiki. - Wiki Linting: Audit 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 synchronized 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?▼

Initialize a wiki directory with SCHEMA.md, index.md, and log.md, then ingest sources one at a time. The agent creates cross-linked entity and concept pages, updates the index, and logs every action so knowledge compounds instead of being rediscovered per query.

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

RAG retrieves and reprocesses raw documents on every query, while the wiki compiles knowledge once into interlinked markdown pages. Cross-references, contradictions, and synthesis persist across sessions, so queries read curated pages instead of raw chunks.

Can I use this wiki with Obsidian?▼

Yes, the wiki directory works as an Obsidian vault out of the box since it uses standard wikilinks and YAML frontmatter. On headless servers, the obsidian-headless CLI syncs the vault via Obsidian Sync without a GUI.

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 hash is recomputed and compared; identical content is skipped, while mismatches flag drift for review.

When should the agent not create a new wiki page?▼

Pages are only created when an entity or concept appears in two or more sources or is central to one source. Passing mentions and minor details are skipped to prevent page sprawl, and pages over 200 lines are split into sub-topics.

Related Skills

Explore More Education & Research Skills→
cryptopaficryptopafi

llm-wiki

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

Community
Advanced
jmeier1963jmeier1963
2

ask

Answer natural-language questions from wiki pages with synthesized citations.

Community
Advanced
rigeobenrigeoben

obsidian-vault-maintainer

Maintain Obsidian vaults with wikilinks, frontmatter compatibility, and CLI awareness.

Community
Intermediate
jhl-labsjhl-labs
50

RAG & Vector Search

Retrieve relevant documents and augment LLM prompts with vector search.

Official
Advanced