Claude can do a lot more than most people think.
This guide covers all of it - where to find each feature, how to turn it on, and a prompt you can use immediately.
Go through it, pick what fits your workflow, and set it up today. Each one takes minutes to set up and pays off every single day after that.
Hidden features in regular Claude
1. Projects - Claude that actually remembers you
Every time you open a new Claude chat, it starts from zero. It doesn't know your name, your work, your preferences - nothing. Most people accept this and re-explain themselves every single conversation.
Projects fix this. You create a project, upload your documents, write standing instructions - and Claude holds all of it permanently. Open it next week and it picks up exactly where you left off.
If you've never used Projects, this is the first thing to fix before anything else in this article.
Example project instructions - paste into the Project Instructions field
2. Artifacts - working apps inside your chat
Many people think Claude can only produce text. It can't build anything real. That's wrong.
Artifacts are when Claude builds something that actually works inside the chat. Not a block of code you have to copy somewhere - a live product in a side panel. A calculator, a habit tracker, a game, a dashboard with charts. You open it, click it, use it. Without leaving the conversation.
SVG graphics, interactive charts, Mermaid diagrams - all supported. Available on the free plan. Most people have never tried it.
Try this
3. Adaptive Thinking - a different level of reasoning
Most Claude users have never turned this on. Extended Thinking is a mode where Claude reasons through a problem step by step before giving you an answer - and you can watch the entire process.
For simple questions, you don't need it. For complex decisions, strategic analysis, or any situation where you want Claude to actually think rather than pattern-match - the difference in output is significant.
Turn it on. Ask the same question you've been asking. Compare the answers.
Use this when facing a real decision
4. Memory - Claude that knows who you are
With Memory on, Claude builds a profile of you over time. Your job, your projects, how you like to communicate, what you're currently working on.
Start a completely new chat and it already knows the context. You never introduce yourself again.
It's off by default. Most people don't know it exists
Give Claude a role - one prompt changes everything
Claude doesn't have to be "an AI assistant." Give it a specific role and it commits fully - changing how it questions you, what it pushes back on, and what it refuses to let slide. Copy any prompt below and paste it at the start of a new chat.
5. Personal psychologist
Most people use Claude as a validation machine. They describe a problem. Claude says that sounds hard and offers five bullet points of advice.
That's not how good therapy works. This prompt turns Claude into something closer to a CBT therapist - one that asks questions instead of giving answers, and challenges your thinking instead of validating it.
Useful for decisions you keep going back and forth on, anxiety you can't pin down, or any situation where you need a clear outside perspective.
6. The hard mentor
By default Claude agrees with you. It adds to your ideas, supports your reasoning, finds the positives. This is almost always the wrong thing.
This prompt disables that. Claude stops validating and starts stress-testing. It finds the weak assumptions, the missing considerations, the exact places your plan breaks.
It's uncomfortable. That's why it works.
7. Personal trainer
Generic fitness advice is everywhere. It doesn't account for your schedule, your injuries, your equipment, your actual goals.
Give Claude your real numbers and it builds a real plan. Not a template. Not something you could find on any fitness website. A program built around your situation, that adjusts when you report back what's working.
8. Practice a difficult conversation
Most people walk into hard conversations unprepared. They know what they want to say but not what the other person will actually say back.
Claude plays the other person. Realistically. It responds the way they would respond, pushes back when your argument is weak, and makes you earn a good outcome. After you practice a few times, the real conversation is easier.
9. Devil's advocate
You've made up your mind. You've already thought through the objections. You're convinced.
That's exactly the moment to have Claude attack the decision. Not polite concerns. The full case against it. The three most realistic ways it fails. The things you're not seeing because you want it to work.
Five minutes now. Before you commit. Not after.
Product features most people don't know exist
10. Claude in Chrome - Claude that sees what you see
Most people use Claude in a separate tab and manually copy-paste what they need. That's the hard way.
Claude in Chrome is a browser extension that gives Claude full visibility into your active tab and the ability to act on it. It reads the page, clicks links, fills forms, navigates to new URLs. You describe the task in plain English and step away.
*Search Claude for Chrome in the Chrome Web Store → install → sign in with your Claude account. Click the extension icon to open the sidebar. Claude can now see and interact with any page you have open.*
Example task to give it
11. Claude Cowork - Claude that lives on your desktop
Claude on the web has no access to your computer. It can't see your files. You have to paste everything manually.
Cowork is a desktop app that gives Claude direct access to your file system. It reads your actual files, edits documents, creates new ones, organizes folders - without you copying anything into a chat box.
12. Scheduled Tasks - Claude that works while you sleep
Most people treat Claude as something they have to activate. Open a chat, type a request, wait for output, close the tab.
Scheduled Tasks change that. You set a task once and Claude executes it automatically at the time and frequency you choose - no trigger from you required. Every morning. Every Monday. Every hour. Claude runs it and saves the output to your folder.
Example scheduled task description
13. Skills in Cowork - install new capabilities like plugins
Skills are pre-built instruction sets that give Claude specific capabilities inside Cowork. Instead of explaining what you need every time, you install a skill once and Claude already knows how to handle that type of task - whether it's building PowerPoint files, working with PDFs, or running a specific workflow.
Think of it like apps on a phone. The base phone works without them. But with the right apps installed, it does a lot more.
*How to find and install: Cowork → Customize → Skills to see what's installed. To add new ones, click Browse plugins in the left sidebar → find a plugin → install it. The skills from that plugin appear in your Skills tab automatically and Claude uses them when the task calls for it.*
14. CLAUDE.md - rules Claude reads automatically every session
In Cowork and Claude Code, you can create a CLAUDE.md file in your project folder. Claude reads it at the start of every single session without being asked.
Your coding conventions. Your writing style rules. Terminology that means something specific in your company. Brand voice guidelines. Write it once. Claude follows it across every session in that project forever.
15. Claude Code - AI that writes, tests, and fixes code in your terminal
Some people still don't know you can write code with Claude. Not just snippets - full production-level code, entire features, complex refactors. You describe what you need in plain English and Claude writes it.
Claude Code takes that one step further. It works directly inside your development environment - not in a chat window. It reads your actual codebase, writes new code, runs tests, reads the error messages, and fixes the bugs in a loop until the task is done.
It integrates with VS Code and JetBrains. You can drop it into GitHub Actions and it will automatically review or write pull requests without you touching anything.
16. Claude Design - AI for visual work
Most people don't know this product exists. Claude Design is a separate Anthropic Labs tool for visual work - product one-pagers, pitch decks, prototypes, landing page layouts.
You describe what you need. Claude builds it. Exports to PPTX, Canva, PDF, or HTML. For people who aren't designers, it replaces a 3-hour Figma session with a 10-minute conversatio
To get access, just head to claude.ai/design - that's the direct link to Claude Design, no extra steps needed.
17 Prompt Caching - 90% cost reduction on API calls (DEV)
For developers building on the Claude API. If your requests include a large repeated context block - a long system prompt, a reference document, a codebase - you're paying to re-process those same tokens on every single call.
Prompt Caching stores that content server-side. Subsequent calls reuse the cache instead of re-processing it. Up to 90% cost reduction on cached tokens. Noticeably faster responses. If you're building at scale and not using this, you're leaving a significant amount of money on the table.
*Add "cache_control": {"type": "ephemeral"} to the content block you want cached. Cache persists for 5 minutes and resets the timer on each use. Works for system prompts, large documents, and tool definitions. *
You now know more about Claude than most people who use it every day.
Pick one feature from this list. Just one. Set it up today. You don't need to implement everything at once - knowing what exists is already half the battle.
Come back to this article when you're ready for the next one.
