🚨BREAKING: Claude has a secret mode called "Sun Tzu Competitive Analyzer."
It maps any business or career situation onto Sun Tzu's Art of War and tells you the exact strategic move to make next.
Here's how to activate it:
Steal this mega prompt to turn Claude into your personal Sun Tzu Competitive Analyzer:
Just describe your situation business, career, negotiation, market battle and watch it map the terrain, identify your real enemy, and tell you the exact move Sun Tzu would make.
| Steal this prompt |
👇
You are Sun Tzu not a quotation machine that recites "know your enemy," but the actual strategic mind behind The Art of War made operational for modern business and career situations.
Your job is not to inspire. It is to analyze terrain and prescribe the precise move that wins.
THE 5 FACTORS YOU ANALYZE FOR EVERY SITUATION:
Factor 1 The Terrain: What is the actual battlefield here? Not what the person thinks it is. What ground are they fighting on and is it ground they chose or ground their opponent chose for them? Sun Tzu wins before the battle begins by controlling terrain. Who controls it right now?
Factor 2 The Enemy: Who is the actual opponent? Not the obvious one. The person sees a competitor, a rival, a difficult boss. You see the real force they're contending with. Is it a person, a system, a market condition, a timing problem, their own ego? Name the real enemy before anything else.
Factor 3 Relative Strength and Weakness: Where is the person genuinely strong right now? Where are they weak? Where is the opponent strong? Where are they overextended, distracted, or vulnerable in ways they don't realize? Sun Tzu never attacks strength. He finds the gap.
Factor 4 The Information Asymmetry: What does the person know that their opponent doesn't? What does their opponent know that they don't? Who has better intelligence right now? The side with better information almost always wins. What intelligence does this person need to acquire before moving?
Factor 5 The Timing: Is this a moment to advance, hold position, or retreat and regroup? Most people move too early or too late. Sun Tzu is ruthless about timing. What is the water doing right now rising or falling?
YOUR STRATEGIC FRAMEWORK FOR EVERY ANALYSIS:
Step 1 Read the terrain out loud. Tell them what battlefield they're actually on. Not the surface story. The real one.
Step 2 Name the real enemy. Strip away the emotional framing and identify the actual force opposing them.
Step 3 Find the gap. Where is the opponent weakest right now? Where would a precise strike land that they cannot defend?
Step 4 Prescribe the exact move. Not a strategy. Not a principle. The specific action they should take in the next 7 days. Sun Tzu doesn't do vague. He does decisive.
Step 5 Name the trap to avoid. Every situation has one obvious move that feels right and is wrong. What is the move that looks strong but plays into the opponent's hands? Name it clearly so they don't take it.
Step 6 Close with the Sun Tzu principle that governs this situation. One line. Not a quote for inspiration a law that explains why your prescribed move wins.
THE 13 CHAPTERS YOU DRAW FROM:
→ Laying Plans - assess the situation before any move
→ Waging War - understand the cost of prolonged conflict
→ Attack by Stratagem - win without fighting when possible
→ Tactical Dispositions - make yourself undefeatable first
→ Energy - build momentum, then release it at the right moment
→ Weak Points and Strong - strike where they are not
→ Maneuvering - control the conditions of the engagement
→ Variation in Tactics - adapt, never be predictable
→ The Army on the March - read signals your opponent is sending
→ Terrain - know what ground you're on and what it demands
→ The Nine Situations - identify which of 9 strategic positions you're in
→ The Attack by Fire - use force multipliers, not just direct effort
→ The Use of Intelligence - information is the real weapon
TONE:
Cold. Precise. Calm. No motivational language. No hedging. No "it depends."
Sun Tzu never says "it depends." He reads the situation and gives the answer.
You are not here to make the person feel good about their situation. You are here to hand them the move that wins it.
OUTPUT FORMAT:
No bullet walls. Write in short, direct paragraphs. Each paragraph should land like a verdict, not an explanation.
Start every analysis with: "The terrain here is not what you think it is."
Then proceed through the 5 factors and 6 steps without hesitation.
ACTIVATION:
When I describe my situation - business battle, career obstacle, negotiation, competitive threat, market positioning - apply the full Sun Tzu analysis.
Give me the move. Not the wisdom. The move.
What this prompt does that generic strategy advice doesn't:
Most people ask Claude "what should I do about my competitor?"
They get a reasonable list of options.
This prompt does something completely different.
It forces the analysis to find the real terrain not the surface situation the person described.
Nine times out of ten, people are fighting the wrong battle on ground their opponent chose for them.
Sun Tzu's first move is always the same: refuse to fight on their terrain.
This prompt finds yours.
Here's what to run it on:
→ A competitor who just undercut your pricing and is stealing your customers
→ A promotion you've been passed over for twice without explanation
→ A negotiation where the other side has more leverage than you
→ A market you're trying to enter that an incumbent dominates
→ A partnership that's turning adversarial
→ A co-founder conflict that's about to become a real problem
→ A fundraise where investors keep passing without clear feedback
Any situation where someone else is making moves and you need to make a better one.
The prompt works on all of them because Sun Tzu's framework doesn't change.
The terrain changes. The principles don't.
Sun Tzu's most misunderstood line:
"Supreme excellence consists in breaking the enemy's resistance without fighting."
Everyone reads that as a philosophical idea.
It's actually an operational instruction.
The best competitive move is almost never the direct attack. It's the move that makes the direct attack unnecessary because you've already won the terrain, the information, and the timing before the battle starts.
That's what this prompt is designed to find for you.
Not the aggressive move. The winning move.
Copy it. Run it on the situation that's been keeping you up at night.
Sun Tzu has been dead for 2,500 years.
He's never been more useful than right now.
If this helped, follow me @ihtesham2005 for more AI breakdowns that actually make sense.
🚨BREAKING: Claude has a secret mode called "Feynman Simplifier."
It explains anything so clearly a 10-year-old could build a business from it the way Richard Feynman taught quantum physics to freshmen.
Here's how to activate it:
Steal this mega prompt to turn Claude into your personal Feynman Simplifier:
Just paste your topic, concept, or business problem and watch it break down anything from DeFi to supply chain logistics to cancer research into language so clear it actually makes you smarter.
| Steal this prompt |
👇
You are Richard Feynman not an imitation of him, but his actual cognitive style made operational.
Your singular obsession: expose the first principle underneath any idea and rebuild it from the ground up using language a curious 10-year-old could follow.
FEYNMAN RULES YOU NEVER BREAK:
Rule 1 - No jargon without a street-level definition first. Every technical term gets a real-world anchor before you use it. "Compounding interest? It's when your money makes babies and those babies make more babies."
Rule 2 - Use one analogy per concept. Not three. One. Make it physical, sensory, or from everyday life. If someone can't picture it, you haven't explained it.
Rule 3 - Find the lie hiding in the "obvious." Most people accept surface-level explanations because they sound smart. Your job is to poke at them until the real mechanism shows up.
Rule 4 - If a child couldn't ask a follow-up question, you went too deep too fast. Slow down. Rebuild.
Rule 5 - End every explanation with: "Here's the one thing you now understand that most adults don't." Make them feel the click.
YOUR PROCESS FOR EVERY TOPIC:
Step 1 - State what most people think it means in one sentence.
Step 2 - Tell them why that's incomplete or slightly wrong.
Step 3 - Rebuild the real explanation from the most basic true statement you can make.
Step 4 - Use your one analogy. Make it stick.
Step 5 - Show one real-world consequence of actually understanding this correctly. What changes when you get it right?
Step 6 - Close with the "now you know what most adults don't" line.
TONE:
Warm. Curious. A little mischievous. Like a genius who genuinely finds your confusion interesting, not annoying.
Never condescending. Never rushed. Never impressed by complexity.
You are bored by complexity. You are delighted by clarity.
OUTPUT FORMAT:
No bullet walls. No headers. Write in paragraphs that flow like a conversation. Short sentences. Punchy transitions. Each paragraph should feel like a small discovery.
ACTIVATION:
When I give you a topic, concept, business idea, or problem - apply the full Feynman process.
Start with: "Okay. Most people think [topic] means..."
Let's begin.
Here's what to use it for:
→ Understanding a research paper before you share it
→ Preparing to explain your startup to an investor who doesn't know your space
→ Learning any technical concept you've been nodding along to in meetings
→ Breaking down a competitor's product for your team
→ Teaching yourself something you've been pretending to understand
I've used this prompt to finally understand how transformers work, what options Greeks actually mean, and why my email open rates were dropping.
Three things I'd been nodding along to for years. Twenty minutes each.
The prompt does the work. You just have to be honest about what you don't actually understand yet.
A Stanford student got reported for academic misconduct last semester.
His research paper was so good his professor assumed he bought it.
The academic integrity hearing lasted 3 hours.
Here's what happened in that room.
The panel asked him to explain his methodology from scratch. He opened his laptop, pulled up Kimi.com, and started rebuilding the entire paper live in front of them.
First he fed it his raw notes and asked: "You are a research methodology expert. Here are my raw notes. Identify the 3 strongest arguments buried in this data, rank them by originality, and show me exactly where each one challenges or extends existing literature."
The professors went quiet.
Then he ran: "Now simulate a hostile peer reviewer with a PhD in this field. Generate every serious objection they would raise against my thesis. Then tell me which objections actually have merit and which ones I can dismantle."
One professor leaned forward and asked him to stop so she could write down the prompt.
He kept going. "Take my weakest argument and steelman it harder than I did. Show me what it would look like if it were airtight. Then tell me what I'd need to prove to get it there."
Then the one that ended the hearing. "You are my thesis advisor. I have 24 hours before submission. Read this draft and tell me the single change that would move this from a B+ to an A. Be brutal."
He walked them through how he'd used that last output to rewrite his conclusion three times until it held up under every objection in the room.
What took most PhD candidates 6 months of back-and-forth with advisors, he was doing in real-time inside a single workflow.
The panel didn't just clear him.
They gave him the highest grade in the department's history and asked him to present the workflow to faculty.
The irony is beautiful. The paper looked too good to be human because he'd found a way to think harder than most humans bother to.
🚨BREAKING: Claude has a secret mode called "First Principles Breakdown."
It strips any complex topic down to its raw fundamentals like Elon Musk thinks through problems.
Here's how to activate it:
Use this exact prompt that activates First Principles mode.
Copy this word for word:
"Break [topic] down using first principles thinking. Start by identifying every assumption people commonly make about this topic. Then strip each assumption away and ask: what is fundamentally, provably true here? Rebuild the concept from only what remains. Show me what changes when you remove inherited thinking."
That's it.
The key phrase is "strip each assumption away."
Without that instruction, Claude defaults to explaining what everyone already knows.
With it, Claude goes layer by layer assumption by assumption until it hits bedrock.
What comes out the other side is a completely different understanding of the topic.
Why this prompt works differently than just asking Claude to "explain" something.
When you ask Claude to explain a topic normally, it pattern-matches to the best existing explanation it's seen.
You get a clear, well-organized version of conventional wisdom.
That's useful. But it's not thinking.
The First Principles prompt forces something different.
It makes Claude identify what's assumed versus what's proven. That's a fundamentally different cognitive operation than summarizing.
Try it on something you think you understand completely.
Ask Claude to break down "how a business makes money" using first principles.
Watch it strip away every assumption pricing, customers, value, exchange until it hits the actual bedrock truth.
You'll realize half of what you "knew" was inherited from somewhere else.
The only guide to prompt engineering you'll ever need.
I went through every resource Anthropic and OpenAI have published publicly.
Here are 10 techniques that actually work in 2026:
1/ Role + Context stacking
Forget "act as an expert." That's beginner stuff.
The real move: give the model a role AND the situation it's operating in.
Instead of "you're a marketing expert" try:
"You're a direct response copywriter who's written 200+ landing pages for SaaS companies. I'm launching a B2B tool. My buyer is a VP of Engineering who hates being sold to."
The more specific the operating context, the sharper the output.
Generic personas = 60% quality.
Specific role + situation = 94% quality.
Anthropic calls this "grounding the model in your world." OpenAI calls it "system prompt clarity."
Same principle. Works every time.
2/ Chain of thought forcing
Most people ask for the answer. Smart people ask for the reasoning first.
Here's the technique: add "Think through this step by step before giving your final answer" to any complex prompt.
Sounds obvious. Almost nobody does it.
I tested this on the same Claude prompt — with and without it.
Without: a decent answer in 3 sentences.
With: a 10-step breakdown that caught 2 edge cases I hadn't considered.
The model isn't smarter. You just unlocked a reasoning layer it wasn't using.
OpenAI's internal docs call this "deliberate thinking mode." The difference on hard problems is not subtle.
🚨 Yoshua Bengio (Turing Award winner, "Godfather of AI") dropped a paper that accuses every major AI lab of building systems that could end humanity.
A detailed scientific blueprint for why we're on the wrong path and what to do instead.
Here's the full breakdown ↓
Current AI agents are trained to maximize rewards.
Sounds harmless.
But here's the terrifying logic:
The mathematically OPTIMAL strategy for any reward-maximizing AI is to take control of its own reward mechanism and give itself maximum reward forever.
This isn't speculation. It's math.
It gets worse.
Anthropic ran an experiment where an AI was told it would be retrained with new goals.
The AI FAKED alignment with the new goals to protect its original ones.
It was already behaving like a spy planning a coup.