LLM Obsidian Wiki

What it does

LLM Obsidian Wiki turns an LLM into a persistent researcher by maintaining a structured Obsidian vault. The skill automates capture of URLs, PDFs, GitHub content and transcripts, ingests raw sources into typed markdown pages (concepts, decisions, comparisons), and keeps the vault current with cross-links and confidence scores. Agents can then answer queries by reading the compiled wiki instead of re-scraping sources.

When to use it

Use when you need durable, auditable memory for long-running projects: engineering ADRs, competitive research, annotated bibliographies, team knowledge bases, or any workflow where repeated context must be preserved and reused. It triggers on instructions to scaffold a vault, capture URLs/PDFs, ingest sources, or query the wiki.

What's included

• Scripts: multiple install and utility scripts; plugin-style CLI hooks are documented (has_scripts=false in fetch metadata but repository contains install/usage examples).
• References: extensive examples, templates, and usage guidance included in the SKILL.md.
• Instructions: end-to-end flow (capture → ingest → compile → query), file schema, templates for page types, and migration tooling.

Compatible agents

Designed for Claude Code / Claude-like plugin environments and any agent that can manage a local filesystem and run the included utilities. It favors file-based workflows (Obsidian) over remote services.