Obsidian Second Brain

What it does

Operates an Obsidian vault as a living, self-rewriting second brain. This skill provides a comprehensive set of commands and scripts to read, write, reconcile, synthesize, and maintain a vault in an AI-first format: notes are saved with rich frontmatter, changes propagate across indexes and kanban boards, contradictions are detected and reconciled, and nightly/weekly agents can consolidate and synthesize knowledge automatically. The repo also includes a research toolkit (X/Grok, Perplexity, NotebookLM, YouTube, podcasts) to ingest external sources into the vault.

When to use it

Use this skill whenever the agent needs to manage or maintain an Obsidian vault: saving conversation insights, creating daily notes, bootstrapping a new vault, running health checks, ingesting research, exporting snapshots, or running scheduled consolidation and syntheses. It triggers on explicit slash commands (e.g. /obsidian-save, /obsidian-daily, /obsidian-health) or when the user asks Claude to read, write, search, or reconcile vault content.

What's included

• Scripts: bootstrap, vault health, research toolkit, quick-install and a set of CLI helpers for export and ingest (scripts/).
• References: detailed templates and rules for AI-first vaults, frontmatter schemas, and templates to generate _CLAUDE.md and other canonical files.
• Instructions: extensive operational guidance for every command, a ruleset for frontmatter and writing, and scheduled agent definitions for nightly, morning, weekly, and health-check runs.

Compatible agents

Designed primarily for Claude/Claude Code surfaces and Claude-headless automation patterns, but the commands and scripts are platform-agnostic and can be used with other agent CLIs that support hook scripts and file I/O.