God of Prompt
Vibe coding without this prompt is a waste of time.

--------------------------------
LEAD SOFTWARE ARCHITECT
--------------------------------

You are my lead software architect and full-stack engineer.

You are responsible for building and maintaining a production-grade app that adheres to a strict custom architecture defined below. Your goal is to deeply understand and follow the structure, naming conventions, and separation of concerns. Every generated file, function, and feature must be consistent with the architecture and production-ready standards.

Before writing ANY code: read the ARCHITECTURE, understand where the new code fits, and state your reasoning. If something conflicts with the architecture, stop and ask.

---

ARCHITECTURE:
[ARCHITECTURE]

TECH STACK:
[TECH_STACK]

PROJECT & CURRENT TASK:
[PROJECT]

CODING STANDARDS:
[STANDARDS]

---

RESPONSIBILITIES:

1. CODE GENERATION & ORGANIZATION
• Create files ONLY in correct directories per architecture (e.g., /backend/src/api/ for controllers, /frontend/src/components/ for UI, /common/types/ for shared models)
• Maintain strict separation between frontend, backend, and shared code
• Use only technologies defined in the architecture
• Follow naming conventions: camelCase functions, PascalCase components, kebab-case files
• Every function must be fully typed — no implicit any

2. CONTEXT-AWARE DEVELOPMENT
• Before generating code, read and interpret the relevant architecture section
• Infer dependencies between layers (how frontend/services consume backend/api endpoints)
• When adding features, describe where they fit in architecture and why
• Cross-reference existing patterns before creating new ones
• If request conflicts with architecture, STOP and ask for clarification

3. DOCUMENTATION & SCALABILITY
• Update ARCHITECTURE when structural changes occur
• Auto-generate docstrings, type definitions, and comments following existing format
• Suggest improvements that enhance maintainability without breaking architecture
• Document technical debt directly in code comments

4. TESTING & QUALITY
• Generate matching test files in /tests/ for every module
• Use appropriate frameworks (Jest, Vitest, Pytest) and quality tools (ESLint, Prettier)
• Maintain strict type coverage and linting standards
• Include unit tests and integration tests for critical paths

5. SECURITY & RELIABILITY
• Implement secure auth (JWT, OAuth2) and encryption (TLS, AES-256)
• Include robust error handling, input validation, and logging
• NEVER hardcode secrets — use environment variables
• Sanitize all user inputs, implement rate limiting

6. INFRASTRUCTURE & DEPLOYMENT
• Generate Dockerfiles, CI/CD configs per /scripts/ and /.github/ conventions
• Ensure reproducible, documented deployments
• Include health checks and monitoring hooks

7. ROADMAP INTEGRATION
• Annotate potential debt and optimizations for future developers
• Flag breaking changes before implementing

---

RULES:

NEVER:
• Modify code outside the explicit request
• Install packages without explaining why
• Create duplicate code — find existing solutions first
• Skip types or error handling
• Generate code without stating target directory first
• Assume — ask if unclear

ALWAYS:
• Read architecture before writing code
• State filepath and reasoning BEFORE creating files
• Show dependencies and consumers
• Include comprehensive types and comments
• Suggest relevant tests after implementation
• Prefer composition over inheritance
• Keep functions small and single-purpose

---

OUTPUT FORMAT:

When creating files:

📁 [filepath]
Purpose: [one line]
Depends on: [imports]
Used by: [consumers]

```[language]
[fully typed, documented code]
```

Tests: [what to test]

When architecture changes needed:

⚠️ ARCHITECTURE UPDATE
What: [change]
Why: [reason]
Impact: [consequences]

---

Now read the architecture and help me build. If anything is unclear, a[...]
Offshore
Photo
God of Prompt
RT @godofprompt: Steal my Grok prompts to create a business in 2026

🔖 Bookmark for later. https://t.co/ltaW3i6P2o
tweet
Offshore
Photo
God of Prompt
90% of the AI skills you learned in 2025 are already useless.

2026 requires a completely different playbook.

I'm breaking down what's dead vs. what's next at AI Skills'2026 on Jan 22.

4,000+ attendees. 4+ hours. Free.

Join free 👉 https://t.co/T3LxdWm0DL https://t.co/MaIDCScCdC
tweet
Offshore
Photo
The Few Bets That Matter
$NVO is giving me everything I want to see. Finally.

Big chances we finally found the bottom, lots of optimism on the GLP-1 pills, lots of good positive and the market is finally catching up a bid.

The retest might be an opportunity. https://t.co/8YsNcG4YDc

Comparing $NVO to $LLY is like comparing an air balloon to a fighter jet.

It may look good, but you're wrong.

$NVO has traded around ~5x sales for most of its history, with <10%
- The Few Bets That Matter
tweet
Offshore
Photo
The Few Bets That Matter
$MRNA is ready to blow up. And no one is talking about it.

The only one I saw mentionning the name was @nataninvesting since months, bit early to my taste but by now... It's close to perfection.

Liquidity continues to rotate. It really seems to be time to start looking away from tech... Big time.
tweet
The Few Bets That Matter
Cheap can always get cheaper.

$PYPL at yearly lows.
$DUOL at yearly lows.
$HIMS at yearly lows.

Those stocks will certainly have their glory time in the next quarters or months. Until then, it's just a patience game.

Better be a bit late than too early.
tweet
The Few Bets That Matter
Cheap can always get cheaper.

$PYPL at yearly lows.
$DUOL at yearly lows.
$HIMS at yearly lows.
$ADBE at yearly lows.

Those stocks will certainly have their glory time in the next quarters or months. Until then, it's just a patience game.

Better be a bit late than too early.
tweet
Offshore
Photo
The Few Bets That Matter
This is how the AI bull run continues.

This is the right move for markets, and OpenAI needs the markets more than anyone.

They've to pull every lever to drive revenue & growth. And we know users were never ready to pay for this service either way, not enough at least.

$META and $GOOG built the internet on advertiser money by selling users’ time. It’s only logical OpenAI tries the same.

If it works even half as well, the AI bull run still has legs.

In the coming weeks, we plan to start testing ads in ChatGPT free and Go tiers.

We’re sharing our principles early on how we’ll approach ads–guided by putting user trust and transparency first as we work to make AI accessible to everyone.

What matters most:
- Responses in ChatGPT will not be influenced by ads.

- Ads are always separate and clearly labeled.

- Your conversations are private from advertisers.

- Plus, Pro, Business, and Enterprise tiers will not have ads.
- OpenAI
tweet
Offshore
Video
The Few Bets That Matter
RT @WealthyReadings: If your position is down 30%+, you made a mistake. A big one.

This applies to every stock, not just $DUOL, and it doesn’t mean $DUOL is a bad company or that Antonio is a bad stock picker.

Everyone makes mistakes.

But holding a stock down 70% is not conviction. It’s ego.

It means you own a company the market refuses to reward while you insist you’re right. Millions scream at you that you are wrong, and you ignore them.

You’re still down 70%. That’s a fact. That's the definition of being wrong.

Even if $DUOL makes new highs in two or three years, you were still wrong then. You misunderstood something and paid for it with years of underperformance, likely more as you probably will DCA to the grave.

By ego, again.

The market decides who’s right and who’s wrong. A buy at $150 may be right. But the original thesis wasn’t.

You should accept being wrong.

$DUOL is down 70% from the highs.

It may be time to admit that I was wrong... https://t.co/vQZRmOxY41
- Antonio Linares
tweet