Vault Organization logo

Vault Organization

Community
AtlasOmnia
vault-organization

vault-organization — Structure a new Obsidian vault (PARA taxonomy, MOCs, starter folder tree) and audit/clean up/reorganize an existing one — identify bloat, consolidate duplicates, remove empty shells, update MOCs and stale references.

Overview

PublisherAtlasOmnia
Repositorydonna-starter
Skill namevault-organization
Stars
131
Forks
9
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by AtlasOmnia on GitHub. Read the source before you install it.

Installation

Install the Vault Organization AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/AtlasOmnia/donna-starter/tree/main/skills/note-taking/vault-organization
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/AtlasOmnia/donna-starter.git /tmp/donna-starter
mkdir -p .claude/skills
cp -r /tmp/donna-starter/skills/note-taking/vault-organization .claude/skills/vault-organization
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Vault Organization in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Vault Organization on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Vault Organization is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Vault Organization

Audit and reorganize the user's Obsidian vault. Run when asked to organize, clean up, or audit the vault structure — or to set up a sensible structure for a new/empty vault.

Vault path

Confirm the actual vault location first — do not assume ~/Documents/Obsidian Vault. Ask or check Obsidian's settings if the path is not known.

Structuring a vault (new or from scratch)

When the user asks "how should I organize my vault?" or is starting fresh, recommend a structure before touching anything. Use PARA as the default taxonomy — it maps cleanly onto how an assistant actually uses a vault:

  • Projects/ — short-lived efforts with a goal and an end (a trip, a launch, a repair). One folder per project; archive when done.
  • Areas/ — ongoing responsibilities with no end date (Health, Finance, Home, a business, a role). These persist and get maintained.
  • Resources/ — reusable reference material not tied to one project: research, guides, templates, snippets, "how I do X."
  • Archive/ — completed projects and superseded material, kept out of the active tree but searchable.

Conventions that make the vault work for both a human and an agent:

  • MOCs (Maps of Content). Put an MOC.md (or Index.md) at each major folder root that links to its key notes. This is the table of contents the agent reads first to navigate. Keep MOCs updated when notes move.
  • Daily notes live in their own folder (e.g. Journal/ or Daily/) and are capture space, not organization space. Promote anything durable out of a daily note into its PARA home; don't let knowledge rot in dated files.
  • One canonical home per thing. A note lives in exactly one place. Link to it from elsewhere rather than duplicating it — duplicates drift.
  • Names over cleverness. Plain, predictable folder and note names (Areas/Health/, not 02_Health_V2/). The agent finds things by reading names; make them say what's inside.
  • Generated artifacts stay out. The vault stores durable knowledge, not repeatable build/test output (screenshots, renders, Lighthouse runs, backups). Those go under ~/Projects/<project>-artifacts/<date>/ with a pointer note in the vault.

Offer a starter tree and let the user rename/rearrange before creating anything:

text
<vault>/
  Projects/
  Areas/
  Resources/
  Archive/
  Journal/        # daily notes / capture
  MOC.md          # top-level map linking the four PARA roots

Create only the folders the user approves, then write a short top-level MOC.md that links them.

Audit workflow

  1. Map directory tree — find <vault> -maxdepth 3 -type d | sort
  2. Count files/size per top-level dir — Python script walking the tree, skipping hidden dirs (.obsidian, .hermes, .Vault). Sort by file count descending to find where bulk lives.
  3. Identify bloat — Look for:
  • Large projects with venvs/site-packages (Python, Node)
  • Duplicate content across directories
  • Empty shell directories after moves
  1. Execute structural changes — Move files, remove empty dirs, consolidate duplicates.
  2. Update MOCs and mappings — After structural changes, scan all MOC/Index/Indexing files for stale references to moved directories. Update them to reflect current structure. Legacy MOCs at old locations should become redirect stubs pointing to the canonical location.
  3. Audit skills and operational files — Scan Hermes skills (~/.hermes/skills/**/*.md) for vault path references that point to moved directories. Patch stale paths in active files; leave historical records (daily notes, .hermes/plans, audit transcripts) untouched since they document what happened at the time.

Execution rules

  • Always present findings before making changes — show size/file counts, list empty dirs, identify duplicates.
  • If the user authorizes end-to-end execution ("proceed"), present the plan once, then execute to completion. Only pause for genuinely ambiguous decisions where multiple valid approaches exist with different trade-offs.
  • When moving projects out of the vault, leave a markdown note with a link to the new location so Obsidian still references it.
  • Report before/after file counts and sizes when done.

PARA for external knowledge repositories

When a GitHub repository holds maintained guides, comparisons, community research, or website source material, PARA is an appropriate lifecycle system outside the Obsidian vault as well. Distinguish temporary outcomes (Projects) from ongoing editorial responsibilities (Areas), reusable source material and automation (Resources), and superseded editions (Archives). Prefer structured canonical data that generates both GitHub and website output. Preserve old public paths during migrations, and establish the user's editorial authority before assuming that a different public author account makes the material third-party-owned.

Generated-artifact storage rule

The vault stores durable knowledge, reports, decisions, and selected final assets — not repeatable build/test output. Website screenshots, Lighthouse runs, visual-regression matrices, preview renders, backups, and discarded image candidates belong under ~/Projects/<project>-artifacts/<date>/. Leave a pointer note in the canonical vault workspace and retain human-readable reports plus approved production assets there.

When consolidating duplicate business ventures, use a single canonical home (for example Business/Side-Hustles/). Marketing material may link to a venture but should not own a duplicate business plan. Keep root MOC redirect stubs for backlink compatibility.

Frequently asked questions

What does the Vault Organization AI skill do?

vault-organization — Structure a new Obsidian vault (PARA taxonomy, MOCs, starter folder tree) and audit/clean up/reorganize an existing one — identify bloat, consolidate duplicates, remove empty shells, update MOCs and stale references.

Why use Vault Organization on TypingMind?

Because you install it once and use it with any model. Vault Organization is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Vault Organization in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/AtlasOmnia/donna-starter/tree/main/skills/note-taking/vault-organization. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Vault Organization?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Vault Organization?

As many as you like. As long as a model supports skills, you can use Vault Organization with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Vault Organization AI skill free?

Yes. It is published on GitHub by AtlasOmnia under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇