LLM Wiki
Builds and maintains a persistent Obsidian-based personal knowledge base, ingesting sources incrementally into entity and concept pages with maintained cross-references.
Before & after
Same prompt, same agent — the only difference is the skill.
Building a personal knowledge base is a great idea. Many people use tools like Obsidian to organize notes and then manually link ideas together. You could set up a folder structure, create pages for key concepts, and gradually build out connections between them. The challenge is keeping it updated and making sure the relationships stay meaningful over time. You might also look into existing second-brain templates to get started. It's really more about your personal workflow—what matters is finding a system that works for you and sticking with it.
SECOND BRAIN SETUP VAULT STRUCTURE → Create an Obsidian vault with three folders: entities (people, companies, concepts), sources (papers, articles, interviews), and synthesis (your compiled insights and cross-references) INCREMENTAL INGESTION → Send Claude a link or text block; it extracts key claims, entities mentioned, and connections to existing pages → Claude auto-proposes new entity pages or updates to existing ones → You review before pages commit to the vault KNOWLEDGE GRAPH GROWTH → Each source ingestion adds backlinks: "data consistency (see also: database integrity, CAP theorem)" → Synthesis pages pull from multiple sources: "Why databases choose consistency over availability—three case studies" → Obsidian graph view shows your emerging clusters of related concepts QUERY FROM MEMORY → Instead of re-reading sources, ask Claude questions grounded in your vault → Claude cites which entity or synthesis pages answer your question → Example: "Which databases handle write conflicts best?" → Claude returns your schema comparison page + linked sources
About this skill
name: llm-wiki description: Use when Use when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references...
Llm Wiki
Use when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
What you get
- Public GitHub repo (alirezarezvani/claude-skills)
- the llm-wiki skill folder with SKILL.md. Part of a 337-skill / 30-agent / 70-command install.
Customize your output
- Fork the repo and adapt the skill's instructions and references to your workflow.
Example output
Activates automatically when your request matches Llm Wiki; chains with the other skills, agents, and commands in the collection.
Best for
Creators, builders, and teams using Claude Code.
SKILL.md preview
---
name: llm-wiki
description: Use this skill when building or maintaining a persistent personal knowledge base in Obsidian where sources are incrementally ingested into cross-referenced entity and concept pages.
version: 1.0.0
category: Development / Engineering
author: AgentVolt
license: proprietary
tags:
- development
- engineering
---
# LLM Wiki
Builds and maintains a persistent Obsidian-based personal knowledge base, ingesting sources incrementally into entity and concept pages with maintained cross-references instead of re-deriving knowledge from scratch each session.
## When to use
… (sign up to view the full skill)More development skills
View all Development skills →Generate
Scaffold code, tests, and boilerplate from a short spec.
Performance Profiler
Systematic performance profiling for Node.js, Python, and Go applications.
Threat Detection
Use when hunting for threats in an environment, analyzing IOCs, or detecting behavioral anomalies in telemetry.
Agent Harness
Turns a domain folder of skills into a bounded agentic loop: compile a goal into a task plan, execute with the domain's tools, verify every task, retry within a budget.