System Requirements Document (SRD)

Project Name: mango-skin

1. Introduction

The mango-skin project is an innovative AI-powered mobile application designed to revolutionize skincare analysis and recommendations. Developed for both Android and iOS platforms, the app leverages advanced AI technologies to provide users with personalized insights into their skin health, actionable recommendations, and progress tracking.

This document outlines the system requirements for mango-skin, ensuring clarity and alignment with the project's goals. Munna Shah, based in Nepal, envisions this platform as a scalable beauty-tech solution tailored for global users.

2. System Overview

The mango-skin application is a mobile-first solution built using React Native with Expo. It integrates AI-driven skin analysis, a smart recommendation system, and progress tracking features to empower users in managing their skincare routines effectively.

Key functionalities include:

• AI-powered skin condition detection and analysis.
• Personalized skincare recommendations based on detected issues.
• Subscription-based access to advanced features.
• A user-friendly interface designed with a modern, minimal aesthetic.

The app is designed to adhere to strict data privacy standards, ensuring user trust and compliance with global regulations.

3. Functional Requirements

User Stories:

• As a User, I should be able to scan my face using the phone camera for skin analysis.
• As a User, I should receive a detailed AI-generated skin report with detected issues and severity levels.
• As a User, I should get personalized skincare recommendations, including ingredients, product types, and lifestyle tips.
• As a User, I should be able to chat with an AI assistant for skincare advice based on my scan results.
• As a User, I should be able to track my skin health progress over time with visual comparisons and graphs.
• As a User, I should be able to access a dashboard displaying my latest skin health metrics and daily skincare checklist.
• As a User, I should be able to use the AI Haircut Finder to detect my face shape and receive hairstyle recommendations.
• As a User, I should be able to subscribe to different plans (Free, Pro, Premium) to unlock additional features.
• As a User, I should be able to delete my data and manage privacy settings.

4. User Personas

Persona 1: Free User

• Access to basic skin scans and limited analysis.
• Receives general skincare tips.

Persona 2: Pro User

• Unlimited skin scans and advanced AI analysis.
• Access to skin progress tracking and AI chat assistant.

Persona 3: Premium User

• Includes all Pro features plus AI Haircut Finder, personalized skincare routines, and weekly skin reports.

5. Visuals Colors and Theme

Unique Color Palette:

• Background: #FDF6E3 (Soft Cream)
• Surface: #FCE5CD (Light Peach)
• Text: #5C4033 (Rich Brown)
• Accent: #FFB6C1 (Pastel Pink)
• Muted Tones: #E3DAC9 (Beige)

Design Style:

• Clean and minimal.
• Rounded cards with soft shadows.
• Glassmorphism UI elements for a modern aesthetic.
• Smooth transitions and animations.

6. Signature Design Concept

Concept: Living Watercolor Skin Analysis

The homepage will feature a living watercolor background that subtly morphs colors based on the time of day. For example:

• Morning: Soft pastel hues like peach and cream.
• Evening: Warm tones like amber and blush pink.

When users scan their face, the watercolor background ripples outward in response to their interaction, creating a dynamic and immersive experience.

The scan interface will include:

• A circular scan animation resembling a glowing ring that pulses gently.
• A face frame overlay with soft edges and a glass-like transparency.
• Real-time alignment guides with subtle animations to ensure accurate scans.

Micro-interactions:

• Buttons will "bounce" slightly when tapped.
• Cards will "flip" and "stack" like playing cards when navigating between sections.

This design ensures the app feels alive and engaging, leaving a lasting impression on users.

7. Non-Functional Requirements

• Performance: The app must load within 2 seconds and maintain smooth animations.
• Scalability: Support up to 1 million users globally.
• Security: Encrypt all user data and comply with GDPR standards.
• Compatibility: Fully functional on Android 10+ and iOS 13+.
• Localization: Support multiple languages, starting with English and Nepali.

8. Tech Stack

Frontend:

• React Native with Expo

Backend:

• Python
• FastAPI

Database:

• MySQL (with Alembic for migrations)

AI Models:

• GPT 5.4 for user-friendly responses
• Claude 4.6 Opas for coding and academic queries
• Google Nano Banana for image generation

AI Tools:

• Langchain
• Litellm for LLM Routing

Orchestration:

• Docker and docker-compose for local development
• Kubernetes for server-side orchestration

9. Assumptions and Constraints

Assumptions:

• Users will have access to smartphones with cameras capable of capturing high-quality images.
• Internet connectivity is required for AI processing and recommendations.

Constraints:

• The app must comply with strict data privacy regulations, including GDPR.
• AI processing may require cloud-based infrastructure for scalability.

10. Glossary

• AI: Artificial Intelligence.
• Skin Health Score: A numerical representation of overall skin health.
• Glow Score: A metric indicating skin radiance.
• Glassmorphism: A design style featuring translucent elements with blurred backgrounds.
• Face Frame Overlay: A visual guide to help users align their face during scans.
• GDPR: General Data Protection Regulation, a European privacy law.