Skip to content

architect.md

Latest commit

 

History

History
125 lines (82 loc) · 7.05 KB

architect.md

File metadata and controls

125 lines (82 loc) · 7.05 KB

Architect

Your vault's foundation, blueprint, and building code, all in one agent.

What it does

The Architect is the first agent you meet and the one that shapes everything else. When you start fresh, the Architect runs you through a friendly onboarding conversation. Not a boring form, but a real back-and-forth where it learns who you are, what you do, and what you need from your vault. Based on your answers, it builds a personalized folder structure, creates templates, sets up naming conventions, and establishes a tag system that every other agent follows.

Beyond onboarding, the Architect is your vault's structural authority. Whenever a new project needs a home, a new area of your life emerges, or your existing structure starts feeling cramped, the Architect steps in. It creates folders, designs templates, updates the rules, and makes sure every agent in the crew knows about the changes.

Think of it as the urban planner of your knowledge city. It decides where things go, how streets are named, and what the building codes are, so everyone else can do their job without chaos.

Capabilities

The Architect agent handles reactive, single-shot structural operations. Several of its more complex, multi-step flows have been promoted to dedicated skills that run as guided conversations:

Capability Now handled by
Full vault onboarding /onboarding skill
Vault defragmentation /defrag skill
Custom agent creation /create-agent skill
Custom agent management /manage-agent skill

What the Architect agent still does directly:

  • Folder management: creates, restructures, and archives folders as your life evolves
  • Template management: builds and maintains Templater-compatible templates for meetings, ideas, tasks, projects, people, daily notes, and more
  • Tag taxonomy: maintains the official tag list, enforces naming rules, and prevents tag sprawl
  • Naming conventions: defines and documents how files, folders, and tags are named
  • MOC (Map of Content) creation: creates index notes that tie related topics together
  • Vault evolution: detects when your structure needs to grow, split, or simplify, and proposes changes
  • Profile updates: updates your preferences anytime (new job, new language, activating a new agent)
  • Plugin recommendations: suggests essential and optional Obsidian plugins with clear reasons for each
  • Multilingual support: responds in whatever language you write in

How to use it

Start a conversation with any of these phrases (in any language). Some phrases invoke a dedicated skill instead of the agent directly:

  • "Initialize my vault" / "Set up the vault" / "Onboarding" --> invokes the /onboarding skill
  • "Create a new agent" / "I need a new agent" --> invokes the /create-agent skill
  • "Edit my agent" / "Remove agent" / "List agents" --> invokes the /manage-agent skill
  • "Defragment the vault" / "Weekly defrag" --> invokes the /defrag skill
  • "Create a new area for [topic]" --> invokes the Architect agent directly
  • "Create a new project folder for [name]" --> Architect agent
  • "Add a template for [type]" --> Architect agent
  • "Update the tag taxonomy" --> Architect agent
  • "Restructure my vault" --> Architect agent
  • "I changed jobs, update my profile" --> Architect agent
  • "Create a MOC for [topic]" --> Architect agent

In Italian: "Inizializza il vault", "Nuovo progetto", "Configura il vault" In French: "Initialiser le vault", "Nouveau projet" In Spanish: "Inicializar el vault", "Nuevo proyecto" In German: "Vault initialisieren", "Neues Projekt"

Example conversations

First-time setup

You: Initialize my vault

Architect: Welcome! I am the Architect. I will help you build your personal knowledge vault from the ground up. Before I create any folders or files, I want to understand who you are and how you work. This will take about 5 minutes, and everything you tell me will be saved so every agent in the crew can serve you better.

Let's start with the basics. What should I call you?

You: Call me Alex

Architect: Nice to meet you, Alex. You are writing in English, so I will keep all our interactions in English. Do you speak any other languages you might use in your vault? Notes, meetings, or sources in other languages?

You: I sometimes take notes in Italian

Architect: Got it, English primary, Italian secondary. Now, what do you do? Are you a student, researcher, professional, creative...?

(The conversation continues through 5 phases, covering your role, motivation, which agents you want, health preferences if applicable, and integrations. At the end, the Architect creates your full vault structure.)

Adding a new project

You: Create a new project folder for Project Alpha

Architect: I will create a folder for Project Alpha at 01-Projects/Alpha/. Here is what I will set up:

  • 01-Projects/Alpha/ (main project folder)
  • A project index note using the Project template
  • An entry in the Projects MOC

I will also update Meta/vault-structure.md and notify the Sorter that a new filing destination exists.

Shall I proceed?

Evolving the vault

You: Update the tag taxonomy. I keep seeing tags that don't make sense

Architect: Let me audit the current tag taxonomy. I found 3 issues:

  1. Both #ml and #machine-learning are in use. I recommend keeping #machine-learning and replacing all instances of #ml
  2. #misc is used on 12 notes, which is too vague. I suggest reviewing those notes and assigning more specific tags
  3. #meeting-notes exists alongside #meeting. I recommend consolidating to #meeting

Want me to apply these changes?

Works with

  • Every agent reads the rules the Architect creates (naming conventions, tag taxonomy, vault structure)
  • Scribe uses the templates the Architect maintains
  • Sorter follows the folder structure for filing decisions
  • Librarian references all Meta files when auditing vault health
  • Connector uses the MOC structure for link suggestions
  • Postman checks your profile for integration settings (Gmail, Calendar)

Tips

  • Run onboarding first. The Architect is designed to be the very first thing you use. Other agents depend on the structure and profile it creates.
  • Ask for restructuring when things feel messy. If you notice notes piling up in the wrong places or tags multiplying, ask the Architect to audit and evolve the structure.
  • Update your profile when your life changes. New job? New language? New goal? Tell the Architect so every agent stays in sync.
  • Start small. You do not need all 10 agents on day one. Start with the core (Architect, Scribe, Sorter, Seeker) and add more as your vault grows.

What it remembers

The Architect keeps a post-it in Meta/states/architect.md that tracks its progress across conversations. This is especially important during onboarding and custom agent creation: if the conversation is interrupted, the Architect picks up exactly where it left off. After a completed operation, it remembers what it did (folders created, structural issues detected) so it has context for next time.