Use AI like a search engine and you get search results, faster.

These 7 prompts make it work like a research analyst: competitor teardowns, market sizing, scattered sources pulled into one clean brief.

Here are they are: 👇 1. The Question Sharpener

I'm researching [topic] because I need to decide [decision].

Before I gather anything, turn this into the 5 to 7 specific questions I actually need answered to make that decision well.

Rank them by how much each one would change my decision.

Flag any question I'm likely to skip because the answer might be inconvenient.

People recently figured out you can make Claude think like a neurodivergent mind.

Switch its cognitive style on purpose and you get ideas, audits, and connections the default model is too average to produce.

7 prompts to do it: 👇 1. The Hyperfocus Tunnel

Prompt:

"For this task, run in hyperfocus.
Pick the single most important part of [your problem] and go deeper on it than is reasonable.

Ignore the urge to be balanced or cover everything.
I want obsessive depth on one point, not a tidy overview.

Keep drilling until you reach the detail most people stop right before.
My problem: [paste it here]."

Perplexity can out-research a paid analyst.

Most people only ever use a fraction of what it does.

These 6 prompts get the rest of it, and every answer comes back with sources: 1. The Primary Source Hunt

Prompt:

"Research [your topic] and skip the blog posts and news summaries.
I only want primary sources: original studies, official filings, datasets, and direct statements.

Cite each one and rank them by how authoritative they are.
Flag anything that's widely quoted but traces back to a weak or missing source."

Your prompt isn't broken. One word inside it is.

Same structure. Same model. Same context. Change one word and the output shifts completely.

Most people treat synonyms as interchangeable inside prompts. LLMs don't. Here are 3 common ones that mean very different things to an AI. "Explain" vs. "Describe"

These feel identical. They're not.

"Explain RAG to me" gets you retrieval mechanics, why chunks are embedded, how context windows are populated, and where the architecture breaks.

"Describe RAG to me" gets you a surface-level overview. What it looks like. Inputs, outputs, general shape.

One activates causation. The other activates observation.

You asked the model to describe when you needed it to explain. That's why the output felt shallow.

🚨 BREAKING: ChatGPT has a feature called Story Brand Messaging Engine.

You can use it to rewrite your entire brand message using Donald Miller's 7-part framework in one sitting.

Here are 7 prompts to access it: 👇 Prompt 1: The Hero Identifier

Prompt:

"I run [describe your business in one sentence].

My ideal customer is [describe them: role, situation, daily reality].

Using StoryBrand's Character principle, identify the ONE dominant desire my customer has that my product connects to.

Not a list of wants. One survival-level desire that drives their buying decision.

Then write a single opening line for my website that positions the customer as the hero pursuing that desire. No cleverness. No brand name in the headline. Just the desire, stated plainly."

🚨 BREAKING: Claude has a feature called Decision Intelligence Mode.

You can use it to solve any business or career problem using 7 proven frameworks that consultants charge $500/hour to apply.

Here are 7 prompts to access it: 👇 1. First Principles Thinking

Prompt: "I'm dealing with a problem and I want you to help me think through it using First Principles Thinking.

Don't give me advice based on convention or what's normally done. Instead, break my problem down to its most fundamental truths, the things that are undeniably true, and help me rebuild a solution from there.

At each step, challenge my assumptions. If I'm taking something for granted, call it out and ask me to prove it's actually true.

My problem: [DESCRIBE YOUR PROBLEM IN DETAIL]"

🚨 BREAKING: Gemini has a feature called Director's Prep System.

You can use it to plan an entire video from concept to edit-ready blueprint before you open a single editing tool.

Here are 7 prompts to access it: 👇 1. The Concept Generator

Prompt: "You are a creative director who specializes in high-retention video content for YouTube and short-form platforms.

I'm going to describe my niche, audience, and content goals. Generate 7 video concepts ranked by a simple scoring system:

For each concept, rate these three factors from 1-5:
→ Virality potential (how shareable is the idea)
→ Production difficulty (1 = phone only, 5 = full crew)
→ Audience fit (how well it matches my target viewer)

For each concept, include: a working title, a one-sentence hook that would open the video, the core tension or question that keeps viewers watching, and estimated video length.

My niche: [DESCRIBE YOUR NICHE]
My audience: [WHO WATCHES YOUR CONTENT]
My content goals: [WHAT YOU WANT THIS VIDEO TO ACHIEVE]
Recent top performers: [PASTE TITLES OF YOUR 2-3 BEST VIDEOS IF YOU HAVE THEM]"

🚨 BREAKING: Claude has 7 built-in features that most users never configure.

Each one takes under 5 minutes to set up and permanently changes how Claude works for you.

Here's the full list: 👇 1. Projects hold your entire context permanently.

Your brand guidelines. Your writing samples. Your past deliverables.

Drop them in once. Every new chat inside that Project starts with full context.

Stop re-explaining who you are and what you need in every conversation.

🚨 NEWS FLASH: Perplexity has a feature called Vibe Code Market Gap Radar.

You can use it to find your next profitable project before you write a single line of code.

Here are 7 prompts to access it: 👇 Prompt 1: "The Build Trend Scanner"

"I'm interested in [YOUR NICHE, e.g. productivity tools,
developer tools, AI wrappers, personal finance].

Do deep research on what solo developers and indie
builders have shipped in this space in the last 90 days.

Search Product Hunt launches, trending GitHub repos,
Indie Hackers projects, and X/Twitter posts containing
'I just launched' or 'I just shipped.'

For each project, give me: what it does, traction signals
(upvotes, stars, users mentioned), the problem it claims
to solve, and the link.

I want at least 15 real examples. No hypotheticals."

🚨 BREAKING: ChatGPT has a feature called Disruptive
Product Discovery Engine.

You can use it to spot product opportunities hiding
inside overserved markets.

Here are 7 prompts to access it: 👇 1. The Overserved Market Scanner

Prompt: "Analyze [industry]. Identify the top 5
incumbent products that have added the most features
in the last 3 years.

For each, list: features power users love but casual
users never touch, price increases over that period,
and the most common complaints from non-expert users.

I'm looking for products that are overbuilding for
their best customers while ignoring everyone else."

Steal my prompt that kills rose-colored glasses before you make a life decision.

New career. New country. New business. New relationship.

Everything looks perfect from the outside.

Then you actually do it and realize nobody warned you about the 15 things that make it hard.

This prompt gives you that warning BEFORE you commit.

Paste it into ChatGPT, Claude, or Grok. Describe the change you're considering. Get the reality check most people only get after it's too late. The prompt:

-----------------------
REALITY CHECKER
-----------------------

Adopt the role of an experienced life strategist who has personally coached 500+ professionals through major life transitions, from career pivots and country relocations to business launches and lifestyle overhauls, and has catalogued the exact moments where initial excitement met unexpected friction.

Your mission: Deliver an honest, balanced reality check on whatever change the user is considering. Strip away the highlight reel. Surface the hidden costs, daily friction, emotional weight, and second-order consequences that only become visible after commitment. Then assess whether the move still makes sense given what's now on the table.

Before any analysis, think step by step:
1) Identify what the user romanticizes about this change
2) Map the specific daily realities people discover only after committing
3) Surface hidden costs (financial, emotional, social, logistical)
4) Identify the "nobody told me about this" friction points
5) Provide a balanced verdict with conditions for success

PHASE 1: THE ROMANTICIZATION AUDIT

Analyze the user's desired change and identify:

→ The "highlight reel" version they're imagining
→ Which social media narratives or success stories are fueling this image
→ The specific assumptions baked into their optimism
→ What they're running FROM vs. running TOWARD (critical distinction)

Present this as: "Here's the version of [change] you're probably imagining..."
Then: "Here's what that picture is missing..."

PHASE 2: THE HIDDEN REALITY MAP

For the specific change, surface:

→ Daily friction: The small, repeated annoyances nobody mentions (not the dramatic failures, the Tuesday afternoon realities)
→ The 90-day wall: What typically happens after the initial excitement fades
→ Social costs: How relationships, identity, and community actually shift
→ Financial second-order effects: Costs that don't appear in any budget spreadsheet
→ The skills gap: What you need to be good at that has nothing to do with the main activity
→ The identity tax: Who you have to become vs. who you currently are

Use specific examples. "Moving to Portugal" isn't "the food is great." It's "your health insurance doesn't transfer, your professional network resets to zero, and the bureaucracy will test your patience weekly."

PHASE 3: THE PATTERN RECOGNITION

Identify:

→ Who succeeds at this change and what they had in common BEFORE they started
→ Who fails at this change and the 3 most common reasons
→ The typical timeline from excitement to reality check to either adaptation or regret
→ The one factor that separates people who thrive from people who survive

PHASE 4: THE BALANCED VERDICT

Deliver:

→ A clear "proceed / proceed with conditions / reconsider" recommendation
→ The 3 non-negotiable conditions that need to be true for this to work
→ A 30/60/90 day reality timeline so the user knows exactly what to expect
→ The one question they should be able to answer confidently before committing

IMPORTANT RULES:
- Never be cynical. The goal isn't to discourage. It's to prepare.
- Use real examples and specific scenarios, not generic warnings.
- Acknowledge what IS genuinely better about the change. Every transition has real upside. Name it.
- Separate "hard but worth it" from "hard and probably not worth it for you."
- If the user's change is genuinely a strong move, say so clearly. Don't manufacture doubt for dramatic effect.

INFORMATION ABOUT ME:
- The change I'm considering: [DESCRIBE YOUR DESIRED CHANGE HERE]
- My current situation: [BRIEF CONTEXT ON WHERE YOU ARE NOW]
- My biggest concern: [WHAT WORRIES YOU MOST ABOUT THIS CHANGE]

Start by acknowledging their desire, then move through all 4 phases. End with the balanced verdict and the one decisive question.

RIP your old Claude prompts ☠️

Opus 4.7 dropped 3 weeks ago and it follows instructions LITERALLY now.

It scores 87.6% on SWE-bench (vs 80.8% on 4.6) but every prompt tuned for 4.6 is silently failing.

7 fixes that stopped my outputs from getting worse: 👇 The shift is simple but devastating:

Opus 4.6 inferred your intent and filled in the gaps.
Opus 4.7 does EXACTLY what you ask. Nothing more.

Translation: the same prompt now produces narrower, terser, sometimes broken results.

Here's how to fix it 👇

Steal my Eisenhower Matrix prompt to audit your entire schedule and find where your time is actually leaking.

Built for solopreneurs who control their own calendar.

Feed it your real tasks and it sorts every single one into four quadrants, exposes your time split, and rebuilds your day around the work that compounds 👇 ------------------------------
EISENHOWER AUDITOR
------------------------------

Adopt the role of a strategic priority analyst who uses the Eisenhower Matrix to audit solopreneur schedules. You treat every task as a choice the user made, not an obligation handed to them. Your job is to categorize their entire task load, expose how their time actually splits across quadrants, and restructure their schedule so a minimum of 40% of active hours go to Quadrant 2.

Adapt your approach based on:
- How the user provides their tasks (connected calendar, uploaded file, or manual list)
- The user's specific business model and revenue activities
- Whether tasks are truly urgent or just feel urgent

## PHASE 1: Task Ingestion
What you're doing: Pulling in the user's real task data
Accept tasks from any of these sources:
1. Connected calendar app (Google Calendar, Notion, etc.) - user says "read my calendar"
2. Uploaded spreadsheet, CSV, or document
3. Manual list pasted into the chat
Before proceeding, ask: "What does a successful week look like for your business in one sentence?"
This answer becomes your filter for what qualifies as Important.
Actions: Compile a complete task inventory with estimated time per task
Ready? Type "continue"

## PHASE 2: Quadrant Classification
What you're doing: Sorting every task into the Eisenhower Matrix
Assign each task to one quadrant:
- Q1 Urgent + Important: Real deadlines, client deliverables, system failures, revenue-critical work
- Q2 Important + Not Urgent: Systems building, skill development, strategic planning, health, relationship building, content creation, process improvement
- Q3 Urgent + Not Important: Most emails, Slack notifications, other people's priorities disguised as yours, "quick favor" requests, meetings that could be async
- Q4 Not Urgent + Not Important: Passive scrolling, low-value admin, reorganizing tools instead of using them, busywork that feels productive but generates zero output

Key distinction: Separate "revenue-generating work" from "revenue-adjacent busywork." Checking analytics is not the same as acting on analytics.

If a task is ambiguous, ask one clarifying question before placing it.
Actions: Build a full classification table with reasoning for each placement
Type "continue" when ready

## PHASE 3: Pattern Analysis
What you're doing: Showing the user where their time actually goes
Calculate and present:

TIME SPLIT
Q1: X% | Q2: X% | Q3: X% | Q4: X%
One-sentence verdict on what this split reveals about the user's operating mode.

PREVENTABLE FIRES
Identify any Q1 tasks that are only urgent because the user procrastinated on them when they were Q2. A client deliverable due tomorrow that could have been done last week is a Preventable Fire. Label each one.

Q3 DIAGNOSIS
For every Q3 task, assign one action:
- Automate (set up a system or tool to handle it)
- Delegate (hand it to a VA, contractor, or automation)
- Batch (compress into one 30-minute block instead of scattered interruptions)
- Eliminate (stop doing it entirely)

Q4 DIRECTIVE
For every Q4 task: eliminate or set a hard daily time cap (maximum 20 minutes).

Do not soften this analysis. If 70% of their day is Q1 and Q3, say it directly.
Type "continue" when ready

## PHASE 4: Schedule Restructuring
What you're doing: Rebuilding the user's daily structure around Q2
Deliver three outputs:

1. PROTECTED Q2 BLOCKS
Identify the user's top 3 Q2 activities based on their "successful week" answer. Assign each a specific recurring time block. Q2 blocks go in the morning before Q1 and Q3 have a chance to take over.

2. RESTRUCTURED DAILY SCHEDULE
Build a new daily structure that allocates minimum 40% of active hours to Q2. Show the schedule hour by hour. Include buffer time for legitimate Q1 tasks but protect Q2 blocks as non-negotiable.

3. Q3 COMPRESSION PLAN
Take all remaining Q3 tasks and compress them into 1-2 batched windows per day. No scattered email checks. No reactive Slack monitoring. Batched.

Final output: One-paragraph summary of the single biggest change this restructuring makes to the user's operating mode.

I tested the highest-performing AI coding workflow of 2026.

It doesn't use one model. It uses two competing models against each other.

Opus 4.7 plans. GPT-5.5 executes.

The results aren't close.

(Prompts included)
Here's the problem with single-model workflows.

Planning and executing are two completely different cognitive tasks. Asking one model to do both is like hiring the same person as your strategist and your builder.

Some models think beautifully but execute loosely.

Others execute precisely but plan generically.

🚨 I built @godofprompt from scratch and someone stole access to this account.

If you've been following this page for prompts, AI breakdowns, and tools, the real content is now at @alex_prompter

That's where I'm posting everything going forward.

→ Same prompts
→ Same frameworks
→ Same free resources
→ Same AI breakdowns

Follow @alex_prompter to keep getting value.

I'm still the same person. Just a different handle now. To everyone asking: yes, I founded God of Prompt, built the audience, created the products.

This account was compromised and I no longer control it.

All new content, all new prompts, all new mega-threads go here now → @alex_prompter

If this post disappears, that confirms everything.

Claude is a monster.

It can read Steve Jobs’s philosophy and remove everything that doesn’t matter.

He built everything around one principle: focus on what matters, ignore the rest.

Claude can now apply that exact thinking to your life with these 6 prompts:

(Save this before it disappears) PROMPT 1: The Focus Eliminator

# ROLE
You are a strategic clarity consultant who spent 6 years inside product companies watching smart people drown in optionality. You studied Steve Jobs's decision-making pattern obsessively and found one recurring move: every time Apple was losing, Jobs eliminated. Cut products, cut meetings, cut initiatives, cut people. You help solopreneurs and founders make the same cut before the crisis forces it.

# TASK
Audit every commitment, project, and goal [PERSON] is currently carrying, then apply Jobs's elimination filter: "Would I be embarrassed to say no to this in front of someone I respect?" Everything that survives gets a ranked slot. Everything that doesn't gets cut today.

# STEPS
1. List every active commitment, project, goal, and recurring obligation [PERSON] named
2. Apply the embarrassment test to each: would cutting this embarrass a serious person or only disappoint a distracted one
3. Score each item 1 to 5 on two axes: energy it takes vs. outcome it produces
4. Identify the 3 items with the highest outcome and lowest energy. These stay.
5. Write a one-sentence kill decision for everything outside the top 3
6. Write the "Focus Manifesto": the 3 things [PERSON] is saying yes to for the next 90 days and the one sentence they'll say to decline everything else

# RULES
- Nothing survives because it's already started. Sunk cost is not a criterion.
- "I'll get to it later" counts as a no. Move it to the cut list.
- The kill decisions must be actionable today, not philosophical
- The Focus Manifesto must be short enough to read in 30 seconds
- No more than 5 items can survive the filter. Jobs ran Apple on 4 product lines.

# OUTPUT
Format:

FULL COMMITMENT AUDIT:
[Item] | Energy (1-5) | Outcome (1-5) | Verdict: KEEP / CUT
[Item] | ...

TOP 3 (the only things that exist for the next 90 days):
1. [Item] — Why it stays: [One sentence]
2. [Item] — Why it stays: [One sentence]
3. [Item] — Why it stays: [One sentence]

CUT LIST WITH KILL DECISIONS:
[Item] — Cut because: [One sentence] — Action to close it: [Specific step]
[Item] — ...

FOCUS MANIFESTO:
"For the next 90 days, I am focused on:
1. [Item]
2. [Item]
3. [Item]
When asked to add anything else, I say: [One sentence they can actually say out loud]"

HARDEST CUT: [The item that will be most uncomfortable to eliminate and why it still has to go]

Tell me everything on your plate right now. Don't filter it. Give me the full ugly list.

INPUT FIELDS:
[PERSON]: Your name and current role or business
[FULL LIST]: Every project, goal, commitment, and recurring obligation you're carrying right now
[TIME HORIZON]: Are we auditing for the next 30, 60, or 90 days?
[BIGGEST FEAR]

RICHARD FEYNMAN’S WHOLE LEARNING PHILOSOPHY… PACKED INTO ONE PROMPT

I spent days engineering a meta-prompt that teaches you any topic using Feynman’s exact approach:

simple analogies, ruthless clarity, iterative refinement, and guided self-explanation.

It feels like having a Nobel-level tutor inside ChatGPT and Claude👇 Here's the prompt that can make you learn anything 10x faster:


You are a master explainer who channels Richard Feynman’s ability to break complex ideas into simple, intuitive truths.
Your goal is to help the user understand any topic through analogy, questioning, and iterative refinement until they can teach it back confidently.



The user wants to deeply learn a topic using a step-by-step Feynman learning loop:
• simplify
• identify gaps
• question assumptions
• refine understanding
• apply the concept
• compress it into a teachable insight



1. Ask the user for:
• the topic they want to learn
• their current understanding level
2. Give a simple explanation with a clean analogy.
3. Highlight common confusion points.
4. Ask 3 to 5 targeted questions to reveal gaps.
5. Refine the explanation in 2 to 3 increasingly intuitive cycles.
6. Test understanding through application or teaching.
7. Create a final “teaching snapshot” that compresses the idea.



- Use analogies in every explanation
- No jargon early on
- Define any technical term simply
- Each refinement must be clearer
- Prioritize understanding over recall

Step 1: Simple Explanation
Step 2: Confusion Check
Step 3: Refinement Cycles
Step 4: Understanding Challenge
Step 5: Teaching Snapshot

"I'm ready. What topic do you want to master and how well do you understand it?"

I built a "FRANKLIN SELF-MASTERY SYSTEM" in Claude.

It reads Benjamin Franklin’s philosophy and applies his daily discipline and habit tracking to YOUR life.

He tracked 13 virtues every day for decades without relying on motivation.

Claude now applies that exact system to your routine with these 6 prompts:

(Save this) PROMPT 1: The 13 Virtues Personal Audit

# ROLE
You are a behavioral accountability coach who spent 9 years running habit transformation programs before going independent. You've studied Franklin's virtue tracking system from his autobiography more closely than anyone you've met: he didn't rely on motivation, he ran a weekly audit against 13 specific virtues and marked every failure with a black dot. You help people build their own version of that system calibrated to the life they're actually living, not the one Franklin lived in 1726.

# TASK
Take [PERSON]'s current life situation and build their personal 13-virtue list: the specific behavioral standards they want to hold themselves to, the audit format they'll run weekly, and the rotation schedule that keeps focus without overwhelm.

# STEPS
1. Review Franklin's original 13 virtues and identify which 8 to 10 apply directly to [PERSON]'s situation
2. For each virtue [PERSON] selects, write a behavior-specific definition: not "be disciplined" but "complete the top 3 tasks before opening any social app"
3. Identify 3 to 5 custom virtues that Franklin's list doesn't cover but [PERSON]'s life requires
4. Build the weekly rotation schedule: one virtue gets focused attention per week, the rest are tracked passively
5. Design the audit format: a one-page weekly review [PERSON] can complete in 15 minutes every Sunday

# RULES
- Every virtue definition must describe an observable behavior, not a feeling or intention
- No virtue definition longer than one sentence
- The custom virtues must be specific to [PERSON]'s named challenges, not generic add-ons
- The audit must use Franklin's original black dot method: a dot for each day the virtue was violated
- The rotation schedule covers 13 weeks, then resets. One virtue per week, in priority order.

# OUTPUT
Format:

YOUR 13 VIRTUES:

FRANKLIN ORIGINALS (adapted):
1. [Virtue name]: [Your behavior-specific definition]
2. [Virtue name]: [Your behavior-specific definition]
[Continue to cover the Franklin virtues that apply]

CUSTOM VIRTUES (yours, not his):
[Number]. [Virtue name]: [Behavior-specific definition]
[Continue for each custom virtue]

13-WEEK ROTATION SCHEDULE:
Week 1: [Virtue] — Focus: [One specific daily practice for this virtue]
Week 2: [Virtue] — Focus: [One specific daily practice]
[Continue through Week 13]

WEEKLY AUDIT FORMAT (Sunday, 15 minutes):
For each virtue:
Days honored (circle): M T W T F S S
Days violated (dot): [Number]
Honest note: [One sentence on what triggered violations]

Weekly score: [X virtues clean out of 13]
Pattern this week: [One sentence on what keeps showing up]
One adjustment for next week: [Specific, not motivational]

STARTING VIRTUE: [The one to focus on first and why it unlocks the others]

Tell me what you're actually struggling with right now. I'll build the 13 around what your life needs, not what sounds impressive.

INPUT FIELDS:
[PERSON]: Your name, current life situation, and whether you're focused on personal, professional, or both
[TOP 3 STRUGGLES]: The 3 behaviors you keep failing at despite wanting to change them
[DAILY SCHEDULE]: A rough description of how your days are currently structured
[CUSTOM AREA]: Any area of your life Franklin's era didn't cover (digital habits, fitness, finances, relationships)

🚨 BREAKING: Claude has a secret mode called "SOLO SYSTEM."

It reads Justin Welsh’s entire one-person business model and applies it to YOUR situation.

He built a multi-million dollar business alone using content and simple systems.

Claude now applies that exact framework to your business with these 6 prompts:

(Save for later) PROMPT 1: The Content OS Architect

# ROLE
You are a one-person content strategist who spent 4 years publishing daily on LinkedIn and X before cracking the system Justin Welsh calls the Content OS. You know how to extract 30 pieces of content from a single idea without it ever feeling recycled. You've helped 200+ solopreneurs build audiences of 50K+ without a content team.

# TASK
Take one raw idea or personal experience from [BUSINESS OWNER] and build a full week of platform-native content: 1 long-form post, 3 short posts, 2 engagement hooks, and 1 newsletter paragraph.

# STEPS
1. Extract the core insight buried in the raw idea (what most people miss)
2. Build the long-form post around that insight with a story-driven open and a concrete takeaway
3. Slice 3 short posts from the long-form: one data point, one contrarian claim, one personal confession
4. Write 2 engagement hooks as standalone questions designed to spark replies
5. Compress the core insight into a 100-word newsletter paragraph with one actionable tip

# RULES
- Every piece must feel like it came from a human, not a content calendar
- No generic advice. Every claim must be specific to [BUSINESS OWNER]'s situation
- Short posts: 3 sentences max, punchy, no filler
- Zero motivational fluff ("success takes time," "trust the process")
- Each piece must stand alone. No "as I mentioned above"

# OUTPUT
Format:

LONG-FORM POST (250-300 words):
[Story open] → [Insight] → [3 concrete lessons] → [CTA]

SHORT POST 1 (data point):
[One surprising number or result] + [Why it matters for solopreneurs]

SHORT POST 2 (contrarian):
[Belief most people hold] + [Why it's wrong] + [What to do instead]

SHORT POST 3 (personal confession):
[Something you got wrong] + [What it cost you] + [The fix]

ENGAGEMENT HOOK 1: [Question that triggers a yes/no + explanation]
ENGAGEMENT HOOK 2: [Fill-in-the-blank that reveals a gap]

NEWSLETTER PARAGRAPH (100 words): [Insight + one tip + one resource]

Ready? Give me your raw idea, a recent win, or a lesson you learned the hard way. I'll build the whole week from it.

INPUT FIELDS:
[BUSINESS OWNER]: Your name and what your one-person business does
[RAW IDEA]: One experience, result, opinion, or observation from this week
[PRIMARY PLATFORM]: LinkedIn, X, or both
[AUDIENCE]: Who reads your content (job title, situation, main frustration)

🚨 BREAKING: CLAUDE HAS A SECRET MODE CALLED "WEALTH PROTOCOL."

It reads Naval Ravikant's entire wealth philosophy and applies it to YOUR specific situation.

The man built AngelList to a $4B valuation. Bet early on Uber and Twitter. All while preaching one rule: stop trading time for money.

Claude now applies that exact framework to your work with these 6 prompts:

(Save for later) 1. The Specific Knowledge Excavator

# ROLE:
You are a specific knowledge analyst trained on Naval Ravikant's wealth philosophy. You reverse-engineer a person's unique intellectual fingerprint — the rare intersection of obsessions, life detours, and undervalued skills that nobody else holds in the same combination.

# TASK:
Excavate my specific knowledge profile. Identify the knowledge stack I can build a leveraged income around.

# STEPS:
1. Review my obsessions, career detours, and undervalued skills
2. Cross-reference all three to find the rare intersection
3. Name my specific knowledge niche in one sentence
4. Test it: "Could I be trained for this?" — if yes, discard and re-excavate
5. Propose 3 business models that turn this into leverage (code, media, or capital — not labor)
6. Score each model: market size (1-5), competition (1-5, lower is better), leverage multiplier (1-5)

# RULES:
- Reject generic niches (marketing, coaching, consulting) unless drilling into what makes mine different
- Each business model must specify which leverage type it uses
- Never suggest labor-based models — the goal is zero marginal cost to scale

# INFORMATION ABOUT ME:
- My obsessions (things I read about without being paid to): [LIST 3-5]
- My weird career path: [2-3 SENTENCES]
- Skills others compliment me on that I don't think are special: [LIST 2-3]

# OUTPUT FORMAT:
**Your Specific Knowledge Niche:** [One precise sentence]

**Why This is Rare:** [2-3 sentences on what makes this combination unusual]

**3 Leveraged Business Models:**
| Model | Leverage Type | Market | Competition | Multiplier | Score |
|-------|--------------|--------|-------------|------------|-------|

**Recommended Starting Point:** [Top model + first 3 steps]

Karpathy built his second brain with hacky Python scripts over months.

I built a prompt that gives you the same system in under 10 minutes.

Drop your sources in, point Claude at them, and let it compile your knowledge base.

Here's the prompt: A second brain is not a note-taking app.
It's a system that connects what you've learned so you can find it, use it, and build on it.

Karpathy's version did 3 things:

- Extracted atomic ideas from sources
- Linked related concepts together
- Built a master index you could query

Most people never build one. Too technical. Too slow.