A short, self-guided setup for Claude Desktop, drawn from the full Claude Masterclass. Get privacy, custom instructions, connectors, and Skills in place, then see what Claude can already do for a leader's week.
This is a short version of the Claude Masterclass. It gets you set up on Claude Desktop, then shows what Claude can already do. Work through the five setup steps in order, look at the three examples, and try the How Might We technique on a real task of your own. Every setting here is yours to change, and nothing is permanent.
Set up · Step 1
Download Claude DesktopThe desktop app is what unlocks Connectors and Skills.
The website is fine for chatting, but the desktop app is where the advanced features live. Only the desktop app can connect to your other tools and run Skills. Installing it is the gateway to everything else in this guide.
The Claude desktop app, where Connectors and Skills live.
Do this
Go to claude.ai and find the "Download" option for the desktop app, or visit the downloads page directly.
Choose the version for your computer (Mac or Windows) and run the installer.
Open the app and sign in with the same account you already use.
Confirm you are on Pro. The workflow features below need it.
Checkpoint
Claude Desktop is open on your computer and you are signed in.
Set up · Step 2
Privacy ModeSet history, training, memory, and past-chat search on purpose.
Before you connect real tools and accounts, decide how your data is handled. The desktop app gives you control over saved history, whether chats train models, what Claude remembers, and whether it can search your past conversations. Setting these deliberately now means you connect Gmail or Drive in the next steps with clear expectations.
These choices are yours to make, and knowing where they live matters more than any single default.
Settings, Privacy: the training toggle, memory, and history controls.
Do this
Open Settings and find the privacy or data controls.
Go down the recommended table below and set each one.
Decide your training toggle based on how sensitive your work is.
Note that memory and past-chat search are conveniences. Turn them on if the time saved is worth it to you.
Conversation history
Saves chats so you can reopen them. Recommended start: on.
Training toggle
Lets your chats improve models. Recommended start: off if you handle client or private data.
Memory
Carries useful details across chats. Recommended start: on for convenience, off for strict privacy.
Search past chats
Lets Claude pull from earlier conversations. Recommended start: on if you reference past work often.
It is also on you to decide what is safe to paste in. Skip passwords, full account numbers, or anything you could not share with a contractor.
Checkpoint
Each of the four settings reflects a choice you made, not just the default.
Set up · Step 3
Custom InstructionsStanding notes about who you are and how Claude should think.
A Project (available on Pro) is a folder for related conversations. You can add reference files once and write custom instructions, which are standing notes about who you are and how you like answers. Every chat inside that Project starts already knowing them, so you stop re-explaining yourself.
Write your custom instructions
In the sidebar, find Projects and click "New Project." Give it a name.
Add knowledge by uploading a few reference files (a style guide, past examples, key facts).
Write custom instructions. State your role, your audience, and how you want Claude to respond.
Start chats inside the Project. They use the files and instructions automatically.
Example custom instructions to copy and adaptAbout me: I run a small bakery and write our weekly newsletter.
Audience: local customers, friendly and casual.
How to respond: short paragraphs, no jargon, warm tone.
Always suggest one seasonal item to feature.
The Adaptive Reasoning Protocol
Custom instructions do not have to be about your bio and tone. They can also tell Claude how to think. The Adaptive Reasoning Protocol below is a single instruction you paste once that teaches Claude to size up each request and switch methods automatically: it breaks problems into small, checkable pieces when you ask it to solve or debug, it explains things plainly like a patient teacher when you ask it to learn or understand, and it does both in order when a task needs both. You do not have to remember which mode to ask for; the instruction handles that for you.
Settings, Instructions for Claude: the Adaptive Reasoning Protocol pasted in.
Install it
Open the custom instructions area, either in a Project or in your account's settings.
Copy the Adaptive Reasoning Protocol below exactly as written and paste it in.
Save the instruction. Every new chat that uses it will follow the protocol without being reminded.
Test it. Ask Claude to debug something and watch it decompose the problem, then ask it to explain a concept and watch it switch to plain teaching.
Adaptive Reasoning Protocol custom instruction to copy and pasteUse the Adaptive Reasoning Protocol:
Assess the request type, then apply the appropriate method:
If solving, analyzing, or debugging → Atom of Thought: Decompose into atomic reasoning units. For each atom:
State the logical component
Validate independence
Verify correctness
Then synthesize atoms into final answer.
If explaining, learning, or teaching → Feynman Loop: Explain as if teaching a curious beginner. For each cycle:
Use a concrete analogy
Flag confusion points
Ask questions that reveal gaps
Then compress into a teachable snapshot.
If both are needed → Chain them: First solve via Atom of Thought, then explain the solution via Feynman Loop.
Checkpoint
You pasted the Adaptive Reasoning Protocol into your custom instructions, saved it, and saw Claude switch methods on its own across a solving task and an explaining task.
Set up · Step 4
ConnectorsThe step that turns a chatbot into an agent.
A Connection uses something called MCP (Model Context Protocol), which is a safe, standard way for Claude to reach an outside tool such as Gmail, Calendar, Google Drive, Linear, or Stripe. You approve each connection, so Claude only touches what you allow. Once connected, Claude can read and act in those tools instead of only talking about them. That shift, from describing work to doing it, is what makes it an agent.
Settings, Connectors: tools like Gmail and Calendar, each approved on its own.
Do this
In the desktop app, open Settings and find Connections (sometimes labeled MCP or Connectors).
Browse the available connections. Pick one you actually use, such as Google Calendar.
Click to connect and follow the sign-in prompt. You are granting access through the tool's own secure login.
Confirm it worked by asking Claude something only the connection can answer, like "What is on my calendar tomorrow?"
Approved per tool
Each connection is authorized on its own. Connecting Calendar does not give Claude your Gmail, and you can disconnect any tool later.
Checkpoint
At least one connection is active and Claude correctly answered a question using live data from it.
Set up · Step 5
SkillsFocused expertise for one kind of task, ready to install.
A Skill is a file of instructions that gives Claude focused expertise for one kind of task, like triaging support tickets or drafting a weekly update. The files end in .md, a plain text format you do not need to understand to use. A Skill Library is a bundle of these ready-made files, so you start from proven examples instead of writing everything from scratch.
Settings, Skills: an installed skill, enabled with its trigger shown.
Turn on Skills and related features
A few capabilities power real workflows, and some live behind toggles. Artifacts give you editable documents beside the chat. File creation lets Claude produce actual files you can save. Code execution lets it run small tasks to compute or transform data. Extended thinking is careful, step-by-step reasoning. Turning these on now means your Skills have everything they need.
Open Settings and find the features or capabilities area.
Enable Skills, Artifacts, file creation, and code execution.
Turn on extended thinking for careful, step-by-step reasoning.
If a feature asks for confirmation the first time it runs, that is the safety model working as intended.
Install your Skills
Now you load the .md Skill files from the library. You have two choices. Global means a Skill applies everywhere, across all your chats. Per-Project means it applies only inside one Project. Per-Project is recommended because it keeps each workflow self-contained and predictable, so a support Skill does not bleed into your newsletter writing.
Decide which one or two Skills match the workflow you want to build first.
Find where the app lets you add a Skill (in Settings for global, or inside a Project for per-Project).
Add the .md file there. Prefer adding it to a Project.
Keep it focused. Install only the Skills you will use now. You can add more later.
Checkpoint
At least one Skill is installed, and you know whether it is global or tied to a specific Project.
What's already possible
Three things Claude can do today once it is set up. The first is the everyday, low-risk win. The other two are agentic: Claude takes the actions itself, with you watching and approving.
Claude
Personal Productivity · Everyday win
Turn raw data into a clean summary report
Artifacts: a document Claude produced, open beside the chat and ready to edit.
Hand Claude a messy spreadsheet or a stack of existing reports and get back one clean summary.
Feed it raw exports, a spreadsheet, or several long reports
It reads across all of them and writes a single, structured summary
Skills, file creation, and code execution do the number work and the formatting
Why it works
With file creation and code execution turned on, Claude does not just describe the numbers. It opens the files, computes, and produces a document you can save. Start here: it is the low-risk win that pays for the setup.
Claude sits in your Chrome session and acts on what you are already logged into, including LinkedIn.
Drives your real LinkedIn tab to research profiles and queue prospects
Uses your existing login, so there is no integration to set up
You watch it work and approve the steps that matter
Browser use vs computer use
Browser use (Claude for Chrome) means Claude works inside your browser tab. Computer use means Claude acts on your whole desktop, clicking and typing across apps like a contractor over your shoulder. Both keep you in the loop.
Claude
Agentic work · Newer ground
Assemble a rough cut with computer use
Point Claude at a folder of clips and a video editor, and it can help cut and assemble a first pass.
Computer use lets Claude drive a desktop video editor, or an editor connected over MCP
It works from your rough set of clips toward a rough cut you then refine
This is newer ground, so treat it as help with the first pass, not a finished editor
Why it counts as agentic
Instead of telling you which clips to use, Claude operates the editor itself through computer use and does the cutting. Keep a person on the final cut.
Technique
The How Might We promptA simple way to start any task so Claude asks before it guesses.
When you start a task with "how might we," you frame it as an open problem to work on together. That gives Claude room to ask about the goal, the format, and the constraints instead of guessing at a one-shot answer. In the masterclass this is how you kick off a prompt: you describe the task starting with "how might we," Claude asks a few questions about how it should work, then writes a well-worded prompt you can save and reuse.
Reframe a vague ask
Vague ask
"Write my weekly update."
How might we
"How might we write a weekly update from my meeting notes?"
The second version names the input (your meeting notes) and invites Claude to ask about audience and format before it writes. You get a prompt that fits your real job, not a generic template.
In Claude Code, the same framing kicks off the /create-prompt command, which turns your rough description into a saved, reusable prompt.
Example to type in Claude Code/create-prompt how might we write a weekly update from my meeting notes
