- AI Business Insights
- Posts
- 32 Claude Prompt Shortcuts
32 Claude Prompt Shortcuts
I Tested Every One
So I'm scrolling LinkedIn and someone drops a list of 32 prompt shortcuts for Claude. Not the usual "be more specific" advice. Actual copy-paste prefixes you put before your request that completely change what comes back.
I tested them over a few days. Some are legit game-changers. Some are fine. Here's the full list, organized by what they actually do for you.
In partnership with
Turn AI Into Extra Income
You don’t need to be a coder to make AI work for you. Subscribe to Mindstream and get 200+ proven ideas showing how real people are using ChatGPT, Midjourney, and other tools to earn on the side.
From small wins to full-on ventures, this guide helps you turn AI skills into real results, without the overwhelm.
Make It Simpler, Make It Structured
These control the shape and length of Claude's response. Less filler, more format.
/ELI5 explains anything like you're talking to a five-year-old. I use this constantly when I need to break down a concept for a client or write a newsletter section that needs to land with everyone.
/TLDR compresses long text into a few core lines. Feed it a 10-page doc, get the point in seconds.
/BRIEFLY forces a short answer. No preamble. No buildup. Just the answer you came for.
/EXEC SUMMARY gives you an executive-level summary. Great for reports and research you don't have time to fully read.
/STEP-BY-STEP breaks reasoning into a clear, numbered flow. Ideal for tutorials, how-tos, and troubleshooting guides.
/CHECKLIST turns any response into a checklist. Project planning, travel prep, launch readiness.
/FORMAT AS forces a specific output format: table, JSON, CSV, bullet list. You decide how the data looks.
/SCHEMA generates a structured outline or data model. Handy for database planning or API design.
/BEGIN WITH / END WITH forces the response to open or close with a specific phrase. Great for templated outputs where consistency matters.
/ROLE: TASK: FORMAT: sets all three dimensions at once. Who Claude acts as, what it does, and how it structures the output. This one alone replaced 3 separate instructions I used to write every time.
Change How It Thinks
These shift the AI's perspective, voice, or depth of analysis. Instead of just answering, Claude approaches from a specific angle.
/ACT AS puts Claude into a role. Lawyer, CFO, fitness coach, product manager. I tested /ACT AS a senior copywriter and the difference in output quality was noticeable on the first prompt.
/TONE shifts the energy. Formal, funny, dramatic, empathetic. You name it.
/AUDIENCE adapts language for a specific reader. Executives get different phrasing than developers or teenagers.
/JARGON switches on technical vocabulary. When you actually want the industry-specific terms, not the dumbed-down version.
/DEV MODE goes full developer. Straight to the code, no hand-holding.
/PM MODE gives you the project manager lens. Timelines, dependencies, risks, deliverables.
/REWRITE AS: takes existing text and rephrases it in any style you want. Academic, casual, persuasive. Your call.
/SWOT produces a strengths, weaknesses, opportunities, and threats breakdown. Drop in a business idea, get instant strategic thinking. I ran this on a product idea last week and it flagged two risks I completely missed.
/COMPARE puts two or more options side by side. Products, tools, frameworks, programming languages.
/MULTI-PERSPECTIVE shows multiple viewpoints on one topic. Solid for decisions where you want to see all sides before committing.
/PARALLEL LENSES analyzes a problem from several angles at the same time. Similar to multi-perspective but built for deeper parallel analysis.
/METRICS MODE replaces vague statements with concrete numbers and indicators. No more "significant improvement." You get actual data points.
/DELIBERATE THINKING forces slower, more thoughtful reasoning. Claude takes its time instead of rushing to the first answer.
/CHAIN OF THOUGHT shows every reasoning step. You see exactly how the AI got from question to conclusion.
/FIRST PRINCIPLES rebuilds the answer from the ground up. Strips away assumptions and starts from base truths. Honestly, this one paired with a business question might be the single most underrated combo on this list.
/CONTEXT STACK keeps multiple layers of context active across turns. Useful for long, multi-part conversations where earlier details matter.
4x faster communication. Zero quality tradeoff.
Most people spend hours every day typing messages they could say in minutes. Wispr Flow fixes that.
Flow turns your voice into clean, polished text inside any app. Speak like you would to a colleague - tangents and all - and get professional output ready to send. 89% of messages go out with zero edits.
Use it for:
Email and Slack responses in seconds
Meeting follow-ups and project updates
Client communication on the go
Long-form writing without staring at a blank page
Millions of people use Flow daily, including teams at OpenAI, Vercel, and Clay. Works on Mac, Windows, iPhone, and now Android -- free and unlimited on Android during launch.
*Ad
Make It Check Itself
Most people skip these. That's a mistake. These force Claude to double-check its own output before you act on it.
/REFLECTIVE MODE makes Claude reflect on its answer after generating it. Built-in second opinion.
/SYSTEMATIC BIAS CHECK asks Claude to flag potential biases in what it just said. Worth using on anything you're publishing or presenting.
/NO AUTOPILOT blocks surface-level responses. Forces the AI to actually engage with complexity instead of giving you the easy version. If you only try one shortcut from this section, make it this one.
/EVAL-SELF triggers a self-evaluation. Claude grades its own response and flags weak spots.
/PITFALLS calls out traps, common mistakes, and errors related to the topic. Like having a built-in devil's advocate on every prompt.
/GUARDRAIL sets strict limits on what the response can include. Define what's off-limits before Claude starts generating.
The Real Power Move: Stack Them
You're not limited to one shortcut per prompt. Combine two or three and the output gets seriously specific.
Some combos worth trying:
/ACT AS a senior data analyst /FORMAT AS table /METRICS MODE: "Compare Q1 vs Q2 performance"
/ELI5 /STEP-BY-STEP: "How does blockchain consensus work?"
/FIRST PRINCIPLES /NO AUTOPILOT /CHAIN OF THOUGHT: "Should we build or buy our CRM solution?"
The analysis shortcuts (/SWOT, /COMPARE, /FIRST PRINCIPLES) hit hardest for business decisions. The quality control ones (/EVAL-SELF, /PITFALLS, /SYSTEMATIC BIAS CHECK) are worth adding to any prompt where the stakes are real.
Your Move
You don't need all 32. Pick the 5 or 6 that match what you actually do every day. Make them muscle memory.
Try one combo on your next Claude prompt. See what changes.
How did you like today's issue? |
Hiring in 8 countries shouldn't require 8 different processes
This guide from Deel breaks down how to build one global hiring system. You’ll learn about assessment frameworks that scale, how to do headcount planning across regions, and even intake processes that work everywhere. As HR pros know, hiring in one country is hard enough. So let this free global hiring guide give you the tools you need to avoid global hiring headaches.
*Ad