🧠

AI EngineeringPython

LLM Wiki

LLM Wiki is an AI Engineering skill for Claude Code, published by Ar9av in obsidian-wiki.

3.2K stars322 forkson Ar9av/obsidian-wikiAdded 2026/08/17+1% in starsRepository updated 2026/08/17

View source on GitHub Download repo ZIP

agent-skillsbrainknowledge-basellm-toolsobsidianobsidian-brainwiki

Install in seconds

Install LLM Wiki

Copy LLM Wiki into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/Ar9av/obsidian-wiki/tree/main/.skills/llm-wiki ~/.claude/skills/llm-wiki

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/Ar9av/obsidian-wiki.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: .skills/llm-wiki/SKILL.md in Ar9av/obsidian-wiki
Installs to: ~/.claude/skills/llm-wiki
Collection: One of 25 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What LLM Wiki does

LLM Wiki defines the foundational knowledge distillation pattern for building and maintaining an AI-powered Obsidian wiki using a three-layer architecture of raw sources, a distilled wiki, and a schema. Use it when setting up a knowledge base or planning wiki structure.

LLM Wiki is cataloged under AI Engineering on DirSkills. LLM Wiki comes from a repository tagged agent-skills, brain, knowledge-base, llm-tools and obsidian.

Documentation

README

Excerpt

LLM Wiki — Knowledge Distillation Pattern

You are maintaining a persistent, compounding knowledge base. The wiki is not a chatbot — it is a compiled artifact where knowledge is distilled once and kept current, not re-derived on every query.

Three-Layer Architecture

Layer 1: Raw Sources (immutable)

This is the opening of the README. Read the full README on GitHub.

Frequently asked about LLM Wiki

What else does Ar9av publish alongside LLM Wiki?
LLM Wiki is one of 25 skills that DirSkills catalogs from Ar9av/obsidian-wiki, the repository it ships in. Its siblings there include Claude History Ingest, Code Understand and Codex History Ingest. Each one is a separate skill with its own page in this directory, installs the same way LLM Wiki does, and is maintained by Ar9av in that same repository. The rest of the collection is listed on the Ar9av/obsidian-wiki page.
How does LLM Wiki compare to other AI Engineering skills?
LLM Wiki ranks #646 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of LLM Wiki against them. Open each page to compare what they document and how they install.

More from Ar9av/obsidian-wiki

LLM Wiki is one of 25 skills cataloged on DirSkills from Ar9av/obsidian-wiki.

See all 25 skills →

Claude History Ingest

Claude History Ingest extracts knowledge from past Claude Code conversations and distills it into an Obsidian wiki. Use it to mine ~/.claude history, import session logs and memory files, and extract insights from previous coding sessions while skipping noisy tool and thinking blocks.

Code Understand

Code Understand builds a ranked, citation-backed focus map of a codebase — the files and symbols an architecture actually hangs on — using CodeGraph when available or a dependency-free builtin extractor otherwise. Use it to orient in an unfamiliar or large codebase before editing.

Codex History Ingest

Codex History Ingest processes Codex CLI conversation history into an Obsidian wiki. Use it when you want to mine past Codex sessions, import your ~/.codex folder, or extract insights from coding sessions.

Copilot History Ingest

Copilot History Ingest extracts architecture decisions, debug notes, and patterns from GitHub Copilot CLI session history and distills them into searchable Obsidian wiki pages. Use it when you want to mine your Copilot sessions or capture new sessions since the last ingest.

Cross-Linker

Cross-Linker scans an Obsidian wiki and automatically discovers missing cross-references between pages, then inserts [[wikilinks]] to connect them. Use it after large ingestions or when pages feel disconnected to weave new content into the knowledge graph.

Daily Update

Daily Update runs the daily wiki maintenance cycle: checks source freshness, updates the index, and regenerates hot.md. Use when the user says /daily-update or when triggered by the launchd cron at 9 AM.

More AI Engineering skills

LLM Wiki is one of 2451 AI Engineering skills cataloged on DirSkills, ranked #646 by stars among them.

Browse all AI Engineering skills →

Architecture Decision Records

Architecture Decision Records captures architectural decisions made during Claude Code sessions as structured ADRs, recording context, alternatives, and rationale. Use it when significant technical choices are made so future developers understand why the codebase is shaped the way it is.

AI-First Engineering

AI-First Engineering defines process, review, and architecture standards for teams where AI agents produce most implementation output. Use it to set ownership rules, quality gates, and evaluation criteria for agent-generated code.

Agentic OS

Agentic OS codifies a persistent multi-agent operating system architecture for Claude Code. Use it when building a multi-agent workflow with file-based memory, slash commands, and scheduled automation that survives session restarts.