Aakash Gupta: How to Turn Claude Code into an Operating System with Carl Vellotti. (for product management)

The top users flipped it. They built operating systems. Skills, sub-agents, file structures, hooks. Every prompt benefits from everything built before.

I sat down with Carl Vellotti for the third time. His first episode was the beginner course. His second episode was the advanced masterclass. Together they crossed over a million views across platforms.
Today is the operating system layer.

here is the complete step-by-step guide to building your own Claude Code operating system.

• Fork your starter OS
• The CLAUDE.md file
• The compounding file system
• Mastering context
• Skills that fix weaknesses
• Data you can actually trust
• The daily loop

1. Fork your starter OS

You do not need to build from scratch. Carl open-sourced his personal operating system at github.com/carlvellotti/carls-product-os. I open-sourced mine at github.com/aakashg/pm-claude-code-setup.

2. The CLAUDE.md file

*What goes in it

About me*

# How I work

*# My tools

• GitHub CLI: installed (use for all git operations)
• Vercel CLI*

# Current priorities

# My skills

*# Preferences

• Bold key phrases in documents
• Bullet points for 3+ items
• End sections with a punchy one-liner*

The compounding trick

3. The compounding file system

the AI reads and writes to persistent files. Every conversation makes the files better. Every file makes the next conversation better. That is the compounding loop.

The folder structure

The knowledge folder

People files are where the real compounding happens

Company files hold strategy, positioning, and competitive landscape.

Research files hold user interviews, industry reports

The projects folder Every new task gets its own folder.

4. Mastering context

making sure Claude can actually use it without running out of context.

*Andrej Karpathy confirmed it. The CLIs to install today:

GitHub CLI (gh) - Claude is aggressively competent at it. PRs, issues, repos, zero context cost.*

Andrej Karpathy confirmed it. The CLIs to install today

GitHub CLI ( Etc

5. Skills that fix weaknesses

Tier 1 - Prompt-only skills

Tier 2 - Tool-powered skills

make slides skill

web research skill

Tier 3 - Auto-invoking with hooks

*Skills are supposed to auto-invoke from keywords. It does not work reliably. The fix is a user_prompt_submit hook that runs a lightweight script matching your message against skill keywords. Zero context cost. Instant. Claude still decides whether to use it.

This beats listing skills in CLAUDE.md because it adds no permanent context overhead and auto-updates when you add new skills. Both repos include the hook script ready to use.*

The ask user questions tool

*This was Carl’s favorite Claude Code feature, and one I had never used before this episode.

Tell Claude “use your ask user questions tool” and it generates a custom UI with checkboxes and input fields right inside the terminal. Instead of making assumptions, Claude asks you.*

Skills are what you do. Hooks are how you compound. The ask user questions tool is how you eliminate assumptions.

6. Data you can actually trust

You are presenting numbers to your boss. They ask “where did this come from?” You need proof of work. The answer is Jupyter (or marimo) notebooks. Tell Claude “analyze this data in a Jupyter notebook” and it creates a .ipynb file showing every query as a code cell, every result as output, every chart rendered inline. Renders natively in VS Code or Cursor.

7. The daily loop

Everything from sections 1 through 6 feeds into one daily workflow.

The compounding loop

You have a meeting with Sarah. Granola transcribes it. Your “update people” skill pulls key points into Sarah’s people file. Later, you draft a message to her about the timeline. Claude reads her file. It knows her concerns from the last meeting. The message is specific, not generic.