How to Turn Obsidian Into a Personal Operating System That Runs Itself

Don't want to figure this out alone? I walk members through every step inside the community. Join the Skool → skool.com/raycfu

WHY MOST OBSIDIAN SYSTEMS BREAK

They break for three reasons

Manual maintenance burden. The system requires you to update it regularly to stay accurate. Project statuses need manual updates. Dashboards need manual refreshing. Tags need manual application. When life gets busy the maintenance falls behind and the system becomes unreliable. An unreliable system gets abandoned.

Complexity that compounds over time. People start with a simple structure and add complexity every time they encounter a problem the current system does not handle. Six months later they have a maze that takes 20 minutes to navigate and requires documentation they wrote themselves to understand.

No intelligence layer. The vault stores information but does not reason about it. You capture ideas but never find them again. You take meeting notes but never surface the action items when they become relevant. The system is an archive, not an intelligence.

The operating system fixes all three. Claude handles maintenance automatically. The architecture has a fixed number of components that never grow into a maze. And Claude reads the vault, makes connections, surfaces relevant information, and generates outputs the vault alone cannot produce.

THE 8-FOLDER VAULT STRUCTURE

Every note in your entire vault belongs in exactly one of these 8 folders. No folder is optional. No folder overlaps with another. This structure stays the same forever regardless of how much your vault grows.

00 CAPTURE: Everything unprocessed lands here. This is the most important folder. The rule is that you throw everything into Capture with zero decision making. You do not think about where it belongs. You do not file it. You just capture it. The processor workflow files it for you every evening automatically.

01 ACTIVE: Only what is alive right now. Your current projects each get a subfolder with an overview file, a tasks folder, a notes folder, and an outputs folder. Your life areas (health, finances, relationships, learning, career) each get a subfolder. And your daily notes live here dated as YYYY-MM-DD.

02 RESOURCES: The reference library. Research, references, templates, bookmarks. Things you might need someday but are not actively working on right now.

03 SYSTEM: The operating system itself. Your CLAUDE.md file lives here. Skill files, workflow definitions, and operation logs.

04 GENERATED: Where Claude deposits all its outputs. Morning briefings, summaries, analyses, drafts. Never manually edit files here. They are system outputs.

05 QUEUE: The inbox for Claude tasks. You drop files here describing what you need done. Claude processes them and outputs land in GENERATED.

06 CALENDAR: Time-based information. Upcoming events and periodic reviews organized by when rather than what.

07 ARCHIVE: Where things go when they are complete. Projects you finished. References that are outdated. Never delete anything. Always archive.

The logic is simple. You capture at the speed of thought into 00 CAPTURE. You work out of 01 ACTIVE. You reference from 02 RESOURCES. The system runs from 03 SYSTEM. Claude outputs to 04 GENERATED. You request work through 05 QUEUE. Time-based stuff lives in 06 CALENDAR. And everything finished moves to 07 ARCHIVE.

THE CLAUDE.MD FILE

This is the single most important file in the entire system. It tells Claude everything about your life before any workflow runs. Without it every Claude session starts from zero. With it every session starts with complete context about who you are, what you are working on, and what matters right now.

Create a file called CLAUDE.md in your 03 SYSTEM folder and fill in every section:

"Identity Name: [your name] Role: [your primary role] Location: [your city]

Life Areas and Current Status Health: [brief status, example: training for half marathon, running 4x per week] Finances: [brief status, example: saving for house deposit, target by December 2026] Relationships: [brief status, example: partner name, key friendships to maintain] Learning: [brief status, example: currently studying Python, goal is to build a SaaS] Career: [brief status, example: current role and title, working toward next promotion]

Active Projects [Project name]: [one sentence description] | Status: [status] | Next: [specific next action] [Repeat for every active project]

Current Priorities

1. [Most important thing this week]
2. [Second most important]
3. [Third most important]

Standards for Generated Content Voice: [how you write and communicate] Format preferences: [your preferences] What you never want: [specific things to avoid]

Operating Rules Never delete files. Move to ARCHIVE with timestamp. Never send communications without human review. Always date stamp generated files as YYYY-MM-DD. Log every significant action in SYSTEM/logs/operations.md. When uncertain about placement, use GENERATED and flag for review.

Update Schedule This file is reviewed and updated every Monday morning."

The only maintenance habit in the entire system is updating the Current Priorities section every Monday morning. That takes 5 minutes. You think honestly about what actually matters this week, update those 3 lines, and every workflow Claude runs for the rest of the week reflects your actual priorities. That is it. 5 minutes a week.

WORKFLOW 1: THE DAILY MORNING BRIEFING

This runs automatically every morning at 6am before you open your laptop. Claude reads your vault and generates a briefing you can read in 3 minutes with your coffee.

The prompt:

"Read CLAUDE.md for full life context.

Generate a morning briefing covering:

MOST IMPORTANT TODAY: The single highest leverage action I can take today based on my current priorities.

SCHEDULE: Any events in CALENDAR/events/ dated today. Prepare a one sentence brief for each one.

OPEN LOOPS: Any items prefixed with OPEN: in yesterday's daily note.

PROJECT PULSE: For each active project in CLAUDE.md give me one sentence on status and one sentence on next action.

WEEKLY FOCUS: If today is Monday, read the previous week's daily notes and identify the most important thing to accomplish this week.

Format for under 300 words. Start with MOST IMPORTANT TODAY. Save to GENERATED/briefings/[DATE]-morning.md"

You read the briefing in 3 minutes and you know what matters before you see a single notification or email.

WORKFLOW 2: THE CAPTURE PROCESSOR

This runs every evening at 8pm and processes everything you threw into 00 CAPTURE throughout the day. By the time you wake up the next morning your Capture folder is completely empty.

The prompt:

"Read all files in the CAPTURE folder created today.

For each captured item:

1. Identify what type it is: TASK: Something that requires action IDEA: Something to develop or research later REFERENCE: Information to store for later use NOTE: Context or observation about something active EVENT: Something time-bound to calendar
   
2. File it in the correct location: TASK: Create a task note in the relevant project or area in ACTIVE IDEA: File in RESOURCES/research/ with the date REFERENCE: File in RESOURCES/references/ by topic NOTE: Append to the relevant project overview or daily note in ACTIVE EVENT: Create an event file in CALENDAR/events/
   
3. For tasks: extract the specific action, assign a due date if mentioned, and add to the relevant project task list.
   
4. After processing: move the original capture file to ARCHIVE.
   

Log all processing actions in SYSTEM/logs/capture-log.md"

This is the workflow that makes the system survive your bad days. On a day when you have no time for anything you still throw stuff into Capture because it takes 2 seconds. The processor handles the rest that evening automatically. Nothing accumulates. Nothing gets lost.

WORKFLOW 3: THE WEEKLY REVIEW

This runs every Sunday at 7pm and generates your weekly review. What used to take 45 minutes of staring at your notes trying to remember what happened now takes 10 minutes to read what Claude generated.

The prompt:

"Read all daily notes from the past 7 days. Read all project notes modified this week. Read CLAUDE.md for current life context and priorities.

Generate the weekly review:

WHAT MOVED FORWARD: Specific wins from the week. What caused each one. Be specific. Name the projects, the actions, the results.

WHAT DID NOT MOVE: Honest assessment of what stalled. The most likely reason for each item that did not progress.

THE WEEK'S PATTERN: One theme or insight that appeared repeatedly. Whether it signals something to change.

NEXT WEEK'S PRIORITIES: Three specific priorities for next week ranked by impact. For each one explain why it matters and what the specific next action is.

ONE DECISION: The most important decision sitting open right now. What information you have to make it. What the cost of delaying it another week is.

Save to GENERATED/summaries/[DATE]-weekly-review.md. Update CLAUDE.md Current Priorities section with next week's top 3."

WORKFLOW 4: THE QUEUE PROCESSOR

This checks your 05 QUEUE folder every 2 hours for any files you dropped there. This is the most powerful workflow because it handles anything you throw at it.

The convention is simple. Name the file with a verb and a topic:

RESEARCH-best-crm-tools-for-agencies.md SUMMARIZE-client-meeting-notes.md DRAFT-email-to-landlord-about-lease.md PLAN-trip-to-japan-october.md DECIDE-whether-to-raise-prices.md

The prompt:

"Check the QUEUE folder for any unprocessed files.

For each file found:

1. Read the filename to identify the task type
2. Read the file content for specific instructions
3. Execute the task
4. Save output to GENERATED/[task-type]/[DATE]-[topic].md
5. Move the queue file to ARCHIVE/queue-processed/

Log all queue processing in SYSTEM/logs/queue-log.md.

If the task requires information not available in the vault, flag in the output as NEEDS HUMAN INPUT: [what is needed]"

You think of something at midnight. You drop a file in Queue called RESEARCH-best-email-marketing-tools.md. By 2am the output is sitting in your GENERATED folder waiting for you. You wake up and it is done.

WORKFLOW 5: THE PROJECT HEALTH MONITOR

This runs every Monday at 7am and checks all your active projects for problems before they become crises.

The prompt:

"Read CLAUDE.md for the list of active projects. Read the overview.md file in each active project folder. Read any project files modified in the last 7 days.

For each project generate a health assessment:

STATUS: On track / At risk / Stalled / Blocked

EVIDENCE: What specifically indicates this status. Be concrete. Name files, dates, and specific observations.

NEXT ACTION: The single most important thing this project needs in the next 48 hours.

FLAG: Any project that has had no activity for more than 7 days. These need human attention.

Save health report to GENERATED/briefings/[DATE]-project-health.md

For any flagged projects create a file in QUEUE named REVIEW-[project-name].md with a summary of the situation."

A project that has been stalled for 7 days gets flagged on Monday morning rather than discovered in a panic when a deadline arrives.

HOW TO BUILD THIS IN ONE WEEKEND

Saturday morning (2 hours): Create the 8 folders. Write your CLAUDE.md with real current information. Write one project overview for your most active project.

Saturday afternoon (1 hour): Install Claude Desktop or set up Claude Cowork. Configure the Filesystem MCP and point it at your vault. Run the morning briefing manually and verify it produces accurate output based on your CLAUDE.md.

Saturday evening (30 minutes): Drop one real file in your QUEUE folder. A research topic you have been meaning to explore or a decision you have been putting off. Let Claude process it. Review the output.

Sunday morning (2 hours): Set up n8n on a $5 server or locally. Build the morning briefing workflow as a cron job. Let it run at its scheduled time and verify the output appears in GENERATED automatically.

Sunday afternoon (2 hours): Add the capture processor, weekly review generator, queue processor, and project health monitor as additional n8n workflows.

By Sunday evening all 5 workflows are running. The operating system is live.

THE 3 FEATURES THAT PREVENT IT FROM BREAKING

The capture safety net. Everything goes to Capture first. No decision required at capture time. You never skip capturing something because you do not know where to file it. The capture folder absorbs everything and the processor files it later. This means the system survives your busiest days intact.

The archive never delete rule. Nothing in this system ever gets deleted. Completed projects move to Archive. Outdated references move to Archive. Processed captures move to Archive. You cannot break the system by archiving too aggressively. The cost of keeping everything is zero because storage is basically infinite and the system never requires you to browse the archive for daily operation.

The CLAUDE.md single source of truth. Everything Claude needs to know about your life exists in one file. One file to update. One file to review. When your priorities change you update CLAUDE.md and every subsequent workflow reflects the new reality automatically.

THE RESULT

When this is set up you have a system that runs your life without you maintaining it. Every morning you get a briefing telling you what matters. Every evening your captures get filed automatically. Every Sunday you get an honest review of your week. Every 2 hours your queue gets processed. Every Monday your projects get a health check.

You capture without thinking. Claude files, processes, reviews, and flags everything. You just read the outputs and make decisions. The system runs itself whether you are having a great week or the worst week of your life. That is the whole point.

If you're liking the content stuff and want accountability, deep dives with live Q&A every week.

I built a community here for that: Join the Skool →