Skill Detail

Operate an Obsidian vault as an agent-maintained second brain

Let agents ingest sources, update Obsidian notes, reconcile contradictions, search vault context, and maintain a living knowledge base through documented commands.

Calendar, Email & ProductivityMulti-Framework
Calendar, Email & Productivity Multi-Framework Security Reviewed
⭐ 3.4k GitHub stars
COPY SKILL INSTRUCTIONS (OPTIONAL)
npx skills add agentskillexchange/skills --skill operate-an-obsidian-vault-as-an-agent-maintained-second-brain Copy
Uses the third-party skills CLI, not an ASE-owned installer. Check your agent’s compatibility. This copies instructions; complete the upstream tool setup below separately.
At a glance
Tools required
Obsidian vault, Claude Code or another supported CLI agent, optional MCP server, optional research/API integrations for web and media commands
Install & setup
Run the repository quick install script or copy the bundled SKILL.md and supporting files into the supported agent skill directory, then point the skill at the target Obsidian vault and run the first-time discovery/bootstrap flow.
Author
Eugeniu Ghelbur
Publisher
Individual
Last updated
Jul 19, 2026
Quick brief

Use Obsidian Second Brain when the operator job is to make an Obsidian vault useful to agents, not just to browse notes manually. The agent can ingest meetings, audio, screenshots, web pages, X posts, YouTube links, and research topics, then update existing vault pages instead of appending disposable summaries. It can search vault context before answering, create AI-first notes with recency markers, reconcile contradictions, run synthesis passes, and maintain daily or project context for future sessions. A user should invoke this when continuity, sourced knowledge capture, and vault-aware reasoning matter more than ordinary note taking. The scope boundary is the Obsidian vault operating workflow: ingest, search, update, reconcile, and export agent-ready knowledge. It is not a generic Obsidian plugin card or a broad knowledge-management product listing.

How it works

What this skill actually does

Inputs and prerequisites: Obsidian vault, Claude Code or another supported CLI agent, optional MCP server, optional research/API integrations for web and media commands.

Setup notes: Run the repository quick install script or copy the bundled SKILL.md and supporting files into the supported agent skill directory, then point the skill at the target Obsidian vault and run the first-time discovery/bootstrap flow.

Source and verification boundary: use https://github.com/eugeniughelbur/obsidian-second-brain as the canonical reference before running the workflow; keep commands, API calls, CLI usage, and generated outputs reviewable against that upstream source.

Framework fit: publish this as a Multi-Framework workflow only when the operator can invoke the documented toolchain directly, rather than treating the upstream project as a generic product listing.