obsidian-brain

Retrieve Obsidian vault notes as conversational context via MOC scanning and wikilink resolution.

19|Updated Feb 21, 2026
One-click install
npx skills add https://github.com/hamsurang/kit --skill obsidian-brain
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: obsidian-brain
Source: https://github.com/hamsurang/kit/tree/main/plugins/obsidian-brain/skills/obsidian-brain
Command: npx skills add https://github.com/hamsurang/kit --skill obsidian-brain

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Enable the assistant to reference a user's personal Obsidian notes as conversational context and to reliably extract and archive session learnings so insights are not lost or scattered across conversations.

Core Features & Use Cases

  • Context Loading: Parse a user query for topic keywords, scan MOCs (2-maps/) for matches, extract wikilinks, and retrieve up to five relevant notes while respecting a 15,000-character context budget.
  • Vault Resolution & Fallbacks: Resolve vault path via user override, obsidian-cli, Obsidian app config, or by asking the user, with caching and validation to avoid repeated prompts.
  • Archival Workflow: Extract learnings using progressive summarization, detect duplicates, generate editable zettel drafts from templates, save approved drafts to 0-inbox/, and update or create MOCs as needed while always requiring user approval before any write.
  • Safety Rules: Never auto-save without explicit approval, prefer Grep for MOC scanning, enforce atomic note guidelines, and present clear duplicate-resolution choices.

Quick Start

Ask the assistant to "Check my Obsidian notes for <topic> and answer using the notes you find".

Frequently Asked Questions about obsidian-brain

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I use my Obsidian vault as context for an AI assistant?

To use an Obsidian vault as conversational context, the Skill scans your MOCs for topic keywords, resolves wikilinks, and retrieves up to five relevant notes within a 15,000-character limit to answer queries.

How do I archive AI chat learnings into Obsidian zettel notes?

Archiving session learnings into Obsidian uses progressive summarization to extract insights, generates editable zettel drafts from templates, and saves approved notes directly to the 0-inbox folder.

Can the assistant automatically save notes to my Obsidian vault?

No, the assistant never auto-saves notes to the Obsidian vault. It requires explicit user approval before writing any drafts to the inbox or updating MOCs to ensure vault safety.

How are MOCs and wikilinks resolved when loading Obsidian notes?

MOC resolution uses Grep-based search within the 2-maps directory to find topic matches, then extracts and resolves wikilinks from those MOCs to retrieve relevant notes for the conversation.

What is the character limit for loading Obsidian notes into a conversation?

The context loading process enforces a strict 15,000-character budget when retrieving and summarizing Obsidian notes to provide conversational context without exceeding limits.

How does the assistant find my Obsidian vault path automatically?

Vault path resolution checks user override, obsidian-cli, and Obsidian app config sequentially, with caching and validation to avoid repeated prompts before falling back to asking the user.