skills.rest
i-bebsi
i-bebsiCOMMUNITY
Explore all skills by this author →
GitHub

llm-wiki

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

Updated Jun 17, 2026
Search Tags:#markdown#research#knowledge base#obsidian#ingestion#wiki#rag-alternative
One-click install
npx skills add https://github.com/i-bebsi/hermes-agent --skill llm-wiki-i-bebsi
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: llm-wiki
Source: https://github.com/i-bebsi/hermes-agent/tree/main/hermes-config/skills/research/llm-wiki
Command: npx skills add https://github.com/i-bebsi/hermes-agent --skill llm-wiki-i-bebsi

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 extract entities and concepts into cross-linked wiki pages. - Query & Synthesis: Answer domain questions by reading the wiki index and relevant pages, citing sources, and filing valuable answers back as query or comparison pages. - Lint & Health Checks: Audit the wiki for orphan pages, broken wikilinks, stale content, tag taxonomy violations, and unresolved contradictions. - Use Case: A researcher tracking AI/ML developments ingests arxiv papers and articles weekly; the agent updates entity and concept pages, maintains the index and log, and surfaces contradictions between sources for review. ## 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?▼

Set the WIKI_PATH environment variable, then ask the agent to initialize a wiki for your domain. It creates SCHEMA.md, index.md, log.md, and raw/, entities/, concepts/, comparisons/, and queries/ directories, then ingests sources into cross-linked pages.

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, contradiction flags, and synthesis persist across sessions instead of being recomputed each time.

Does the wiki work with Obsidian?▼

Yes, the wiki directory works as an Obsidian vault out of the box with wikilinks, graph view, and YAML frontmatter. On headless servers, obsidian-headless can sync the vault via Obsidian Sync without a GUI.

How does the wiki detect changed or duplicate sources?▼

Each raw source stores a sha256 hash of its body content in frontmatter. On re-ingest of the same URL, the hash is recomputed: identical content is skipped, and changed content is flagged as drift and updated.

When should I not create a new wiki page?▼

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

Related Skills

Explore More Education & Research Skills→
wzh4464wzh4464
3

extract-paper-images

Extract authentic paper images from arXiv sources and PDFs into an indexed list.

Community
Advanced
fralapofralapo

llm-wiki

Compile source documents into an interlinked Obsidian-style wiki with append-only logs.

Community
Advanced
917Dhj917Dhj
1.0k

paper-glossary

Generate reviewed Obsidian glossary notes from paper source manifests with provenance validation.

Community
Advanced
jhl-labsjhl-labs
50

RAG & Vector Search

Retrieve relevant documents and augment LLM prompts with vector search.

Official
Advanced