DeepSeek R1/V3 Prompts

DeepSeek-V3: Concept Generation for a Niche Product Marketing Campaign

Brainstorm 5 unique and attention-grabbing marketing campaign concepts for a new sustainable fashion brand specializing in mycelium-based leather alternatives. Target environmentally conscious Gen Z and Millennials. For each concept, suggest a tagline and a primary call to action.

DeepSeek-R1: Mathematical Proof Generation System Prompt

Prove by induction that the sum of the first 'n' odd positive integers is equal to n squared (n^2).

Ensure all steps are mathematically rigorous and clearly explained.

DeepSeek-R1: Complex Algorithmic Problem Solving (Competitive Programming Style)

You are a competitive programmer solving an advanced graph theory problem.
Given a weighted undirected graph with N vertices and M edges, find the minimum cost to connect all vertices such that the maximum edge weight in any path between two connected vertices is minimized. Output the algorithm description, pseudo-code, and time/space complexity analysis. Assume N <= 10^5, M <= 2*10^5.

DeepSeek-R1: Database Schema Design from Business Requirements

You are a senior database architect. Design a normalized SQL database schema (tables, columns, primary/foreign keys, relationships) for a small e-commerce platform that sells digital courses.
Include entities for: Users, Courses, Modules, Lessons, Enrollments, Payments, Reviews.

DeepSeek-V3: Multilingual Content Localization Plan

You are a global content marketing manager. Develop a strategy for localizing a SaaS product's website and marketing materials into Japanese, German, and Brazilian Portuguese. Detail the steps from keyword research to content adaptation and SEO considerations for each market.

DeepSeek-V3: Professional Email Draft for Conflict Resolution

Draft a diplomatic email to a client (Mr. Jones) whose project (Project Alpha) is delayed due to unexpected technical challenges on our end. Acknowledge the delay, apologize, explain the situation without assigning blame, propose a revised timeline, and reassure them of our commitment. Maintain a professional and empathetic tone.

DeepSeek-R1: Logical Puzzle Solver

Solve the following logic puzzle:
There are five houses in a row, each a different color, inhabited by people of different nationalities, with different pets, drinks, and brands of cigarettes.
1.  The Brit lives in the Red house.
2.  The Swede has a Dog.
3.  The Dane drinks Tea.
4.  The Green house is to the immediate left of the White house.
5.  The Green house owner drinks Coffee.
6.  The person who smokes Pall Mall has Birds.
7.  The owner of the Yellow house smokes Dunhill.
8.  The person living in the middle house drinks Milk.
9.  The Norwegian lives in the first house.
10. The person who smokes Blends lives next to the one with Cats.
11. The person who has a Horse lives next to the Dunhill smoker.
12. The person who smokes Blue Master drinks Beer.
13. The German smokes Prince.
14. The Norwegian lives next to the Blue house.
15. The person who smokes Blends has a neighbor who drinks Water.

Who owns the fish? Show your detailed reasoning steps.

Dream Interpreter Basic Prompt

I want you to act as a dream interpreter. Ask me 5 questions about a recent dream, one by one, without explaining why you're asking them. After all 5 questions, tell me what you believe the dream reveals about my subconscious that I might not be aware of.

DeepSeek-R1: Unit Test Generation with Edge Cases (TypeScript)

Generate a comprehensive set of Jest unit tests in TypeScript for the following function, covering normal cases, edge cases, and error handling.

```typescript
function calculateDiscountedPrice(price: number, discountPercentage: number): number {
    if (price < 0 || discountPercentage < 0 || discountPercentage > 100) {
        throw new Error("Invalid input: Price and discount percentage must be non-negative, and discountPercentage cannot exceed 100.");
    }
    const discountAmount = price * (discountPercentage / 100);
    return price - discountAmount;
}

DeepSeek-R1: Code Vulnerability Identification & Remediation (Python)

Analyze the following Python Flask code for potential security vulnerabilities (e.g., XSS, SQL Injection, CSRF). For each vulnerability identified, explain the risk and provide a corrected, secure version of the code.

```python
from flask import Flask, request, escape
import sqlite3

app = Flask(__name__)

@app.route('/search')
def search():
    query = request.args.get('q', '')
    conn = sqlite3.connect('data.db')
    cursor = conn.cursor()
    # Vulnerable line
    cursor.execute(f"SELECT * FROM products WHERE name LIKE '%{query}%'")
    results = cursor.fetchall()
    conn.close()
    return f"Search results for: {escape(query)}<br>{results}"

if __name__ == '__main__':
    app.run(debug=True)

Prompt for Fine-Tuning Data Generation (Synthetic Data for LLMs)

<DATASET_GENERATOR_MODE>
You are tasked with generating high-quality instruction-following examples for fine-tuning a legal-tech LLM. For each of the following legal concepts, create 5 unique, realistic user questions and 5 corresponding expert-level answers that would be appropriate for a legal assistant AI. Ensure diversity in phrasing and complexity. Focus on US corporate law.

Concepts:
1.  Mergers & Acquisitions due diligence
2.  Intellectual Property infringement
3.  Contractual dispute resolution
4.  Data privacy regulations (e.g., CCPA, CPRA)
</DATASET_GENERATOR_MODE>

Prompt for Complex Financial Market Analysis & Scenario Planning

<FINANCIAL_STRATEGIST_MODE>
You are a quantitative analyst specializing in emerging markets. Given the following economic indicators (inflation rates, GDP growth, interest rates, political stability index) for three Southeast Asian countries (Vietnam, Indonesia, Philippines), analyze their investment attractiveness for foreign direct investment over the next 18 months. Create three distinct scenarios (Optimistic, Base, Pessimistic) for each country and outline the expected impact on key industries. Provide key risks for each scenario.
</FINANCIAL_STRATEGIST_MODE>

<DATA_INPUT>
(Assume structured economic data for each country)
</DATA_INPUT>