You're using Claude wrong.

Here's my (exact) setup before I even prompt:

Step 1. Download Claude and open Cowork

→ Go to Claude. com/ download.

→ Install the desktop app.

→ Click the Cowork tab at the top.

→ You need a Pro plan ($20/mo). Worth it.

Step 2. Select the right model (don't skip this)

→ Click the model dropdown.

→ Select "Opus 4.6."

→ Turn on "Extended Thinking."

→ Never change these. Wrong model = bad output.

Step 3. Build your folder

→ Create one master folder on your computer.

→ Inside it, create 4 subfolders:

✦ ABOUT ME - who you are + how you write

✦ PROJECTS - one subfolder per live project

✦ TEMPLATES - your best work as structures

✦ OUTPUTS - where Claude saves finished files

→ Upload this folder. That's how it reads you.

Step 4. Create 3 context files inside ABOUT ME

→ These replace prompting. This is the setup.

→ Create them as .md files. Plain text, saved as .md

✦ about-me.md - what you do day-to-day.

✦ my-voice.md - tone, phrases you hate, 3 example

✦ my-rules.md - ask first, show a plan, get approval

(check these inside the guide)

Step 5. Set Global Instructions (once, forever)

Go to Settings → Cowork → Edit Global Instructions.

→ Paste: "I'm [Name], [Role]. Read my files before every task. Ask clarifying questions before executing. Show a plan before acting. Never delete without my approval."

→ You set this once. It runs every session.

→ Your prompts can now be 10 words long.

Before your next Cowork session, check these:

1. Am I in Cowork (not Chat)?

2. Is Opus 4.6 + Extended Thinking on?

3. Did I point it to my folder with context files?

Set these first. Then prompt.

Top 1% of Claude users do this. Now you can too.

(all prompts are mentioned in the article)