Prompting is the worst way to use Claude.
Here's what the top 1% do instead:
__
1. Open the Claude desktop app.
2. Click "Cowork" (not Chat).
2. Point it to a folder with your context files.
3. Create 3 files: about-me, my-voice, my-rules.
4. Use this setup guide: claude-co.work
Claude now reads your brain. Every session.
__
But here's where it gets powerful:
Before you prompt, change these 2 settings:
1. Turn on "Extended Thinking"
It forces Claude to think before answering.
2. Select "Opus 4.6" model.
It is the best model for deep, multi-step work.
__
Then stop writing prompts. Paste this instead:
I want to [TASK]. Read all files first. Ask me questions using AskUserQuestion before you execute. Do not guess.
Claude generates clickable buttons. It executes.
__
The secret was never the prompt.
It was the setup. But to go even deeper,
use my full playbook: claude-co.work
I wrote 2 free guides so you can copy my system:
✦ My full Cowork setup guide: claude-co.work
✦ Quit ChatGPT guide: ruben.substack.com/p/qu…
(save this to be the top 1% Claude user)