- COOLDEEP AI
- Posts
- The thing Claude knew all along (that I kept retyping)
The thing Claude knew all along (that I kept retyping)
A two-character shortcut that replaced five sentences of setup.
In partnership with
Are you looking to get in front of 170,000+ AI readers? Sponsor CoolDeep AI Newsletter.
Was this email forwarded to you? Subscribe here!
Today’s Sponsor
1,000+ Proven ChatGPT Prompts That Help You Work 10X Faster
ChatGPT is insanely powerful.
But most people waste 90% of its potential by using it like Google.
These 1,000+ proven ChatGPT prompts fix that and help you work 10X faster.
Sign up for Superhuman AI and get:
1,000+ ready-to-use prompts to solve problems in minutes instead of hours—tested & used by 1M+ professionals
Superhuman AI newsletter (3 min daily) so you keep learning new AI tools & tutorials to stay ahead in your career—the prompts are just the beginning
Hey
For the first six months of using Claude, I wrote the same things over and over.
Every single session. Every single conversation.
"You are an expert marketer." "Write in a casual, punchy tone." "Do not use bullet points." "Keep it under 200 words."
I typed these out like a ritual. Like Claude had amnesia each time and I had to re-introduce myself from scratch.
And honestly? I did not think twice about it. I just assumed that was the job. You prompt Claude, Claude responds. Prompt again. Repeat forever.
Then one morning I was 40 conversations deep in a project, re-typing my setup instructions for what felt like the hundredth time, and something inside me just snapped. There has to be a faster way to do this, I thought.
I went digging. And I found something that made me feel genuinely foolish.
Not because it was complicated. Because it was sitting right there in Claude the entire time, and I had simply never looked.
Claude has slash commands.
Not hidden. Not in beta. Not behind a Pro wall. Just there, available to anyone who types a forward slash.
I had been writing paragraphs of setup text when a two-character shortcut could do the same job in less than a second.
That is the day my Claude usage changed completely.
BTW, have you joined CoolDeep AI daily alert? Keep getting AI updates the moment they drop on your Phone. It hardly takes 5 seconds to opt in. Get CoolDeep AI Alerts.
Most people are still using Claude like it is 2023.
They open Claude. They type a long preamble. They explain the context. They set the tone. They specify the format.
Every. Single. Time.
I see this across the DMs I get from readers. People who use Claude for hours a day are still manually rebuilding their working environment from scratch in each session.
The worst part is that Claude does not complain. It just takes whatever you give it and works with it. So the habit never gets flagged. There is no error message. No warning that says "hey, there is a faster way to do this."
You just keep wasting time in silence.
And then people wonder why they are not getting dramatically better results despite using Claude more. The problem is not the prompts.
The problem is they are spending 20% of their Claude time re-explaining things Claude is perfectly capable of remembering, managing, and organising on its own.
The #1 most realistic voice AI. Text to speech, voice cloning, voice changer & more and that too all in one editor. Try now.
✅ The most realistic audio AI platform, now with video support
✅ Scale your productions with less editing
✅ Expand your reach globally with instant translations
Trusted by 1,000,000+ creators, including Andrew Huberman & Arianna Huffington.
Now, you can go viral without ever filming yourself. See why 1,000,000+ creators use ElevenLabs for content creation.
Here is how slash commands actually work. Step by step.
This is simpler than you think.
Step 1: Open any Claude conversation in claude.ai.
Step 2: At the very beginning of your prompt, type a forward slash ( / ).
Step 3: A menu appears. You will see available commands listed.
Step 4: Select the command you want or type its name directly.
Step 5: Hit enter. Claude executes the command instantly, no additional explanation needed from you.
That is it. No special setup. No developer tools. No API required. Just a slash, a command name, and Claude handles the rest.
The key insight is this: these commands are not prompts. They are instructions to Claude's interface itself.
When you type /CLEAR, you are not asking Claude to forget things in conversation. You are actually clearing the context window.
When you type /MEMORY, you are editing a persistent file that Claude reads at the start of every session.
That is a fundamentally different kind of power than anything you can achieve through a prompt alone.
The 10 slash commands worth bookmarking right now.
You do not need to memorize all of them. Just know they exist so you reach for them instead of typing five sentences.
1. /CLEAR — Wipes conversation history and resets the context. Use this when you switch topics mid-session and do not want old context bleeding into the new task.
2. /COMPACT [instructions] — Compresses the conversation while letting you specify exactly what to keep. The instructions part is the hidden gem. You can tell Claude what context matters before it summarises.
3. /MEMORY — Edits your CLAUDE.md memory files. This is where you teach Claude your preferences, writing style, tools, and working patterns once, and it carries across every future session.
4. /INIT — Sets up your project with a CLAUDE.md guide. The foundation step for any serious project work inside Claude.
5. /MODEL [model] — Switches between Sonnet, Opus, and Haiku without leaving the chat. Use Haiku for quick lookups, Sonnet for most daily work, Opus for the heaviest thinking tasks.
6. /COST — Shows your token usage for the current session. Keep an eye on spend without ever leaving the chat.
7. /RESUME [session] — Reopens a previous conversation by name or ID. No more scrolling through history looking for that one thread from three days ago.
8. /BRANCH [name] — Creates a new branch from the current conversation. Explore a tangent without losing your main flow.
9. /PLAN [description] — Drops Claude into planning mode before any work begins. Forces a thought-out approach before code gets written or a strategy gets executed.
10. /SECURITY-REVIEW — Scans pending changes for security issues. If you are shipping code, this one alone makes the whole list worth saving.
10 AI Stocks to Lead the Next Decade
AI isn’t a tech trend – it’s a full-blown, multi-trillion dollar race, and 10 companies are already pulling ahead.
These are the innovators driving real revenue, attracting institutional attention, and positioning for massive growth.
Get all 10 tickers in The 10 Best AI Stocks to Own in 2026, free today.
*Partnered
My honest take on all of this.
The real frustration is not that these commands exist and most people do not know about them.
The real frustration is what this pattern reveals.
Most people treat Claude like a search engine. Type a question, get an answer, close the tab. Every interaction is isolated. Every session starts cold.
But Claude is not a search engine. It is a work environment. And like any work environment, you can set it up well or set it up poorly.
The /MEMORY command alone, when used properly, turns Claude from a tool you use into a system that knows how you work.
The people getting dramatically better output from Claude are not necessarily writing better prompts. They are building better environments. They understand the context window. They manage their sessions intentionally. They use commands to remove friction instead of writing around it.
That is the shift. From using Claude reactively to using it architecturally.
Start with /MEMORY this week. Write down your working style, your preferences, the formats you use, the tone you write in. Save it. Watch how differently Claude responds in your next session when it already knows who you are.
You have been re-introducing yourself to Claude for months.
It is time to stop.
Stay curious, talk to you tomorrow.
CoolDeep AI
Helping you stay ahead with AI & productivity
AI is fueling the Fourth Industrial Revolution and these 10 stocks are front and center.
One of them makes $40K accelerator chips with a full-stack platform that all but guarantees wide adoption.
Another leads warehouse automation, with a $23B backlog – including all 47 distribution centers of a top U.S. retailer – plus a JV to lease robots to mid-market operators.
From core infrastructure to automation leaders, these companies and other leaders are all in The 10 Best AI Stocks to Own in 2026.
ICYMI Last Newsletters:
How did you like today's newsletter? |
Was this email forwarded to you? Subscribe here.
P.S. If CoolDeep AI helps you in your AI skills, I am running m daily email newsletter too. its about Digital Product Business, email marketing, automations, Instagram growth and much more. Click here to join for f’ree.
P.P.S. Reply to this email and let me know what else you want me to cover in the next edition. Keep getting AI updates the moment they drop on your Phone. It hardly takes 5 seconds to opt in. Get CoolDeep AI Alerts.
Get the AI Edge Before Everyone Else
The best AI opportunities and stock ideas move fast. Get our research, AI tool picks, and market insights delivered straight to your phone, so you never miss what's moving next. Our text alerts keep you updated on the AI stocks and tools that matter, whether you're in a meeting, commuting, or away from your desk.
*Disclosure: Some of the content in our free newsletter and on our website includes paid placements, marked as “Sponsored”, “Partnered” or “Ad”, and may contain affiliate links. If you choose to click or make a purchase, we may earn a small commission. We are not directly connected to the brands we feature. This helps us keep the newsletter free for you.
If you find our work valuable, your support through these links truly helps us continue creating it.
Reply