SkinGuide

Orchestrate a multi-service workflow to analyze skin images and generate personalized routines.

Updated Jun 6, 2026
One-click install
npx skills add https://github.com/Capskick5/SkinGuide --skill skinguide
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: SkinGuide
Source: https://github.com/Capskick5/SkinGuide/tree/main
Command: npx skills add https://github.com/Capskick5/SkinGuide --skill skinguide

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides a blueprint for building an AI-powered skincare platform that analyzes facial images, identifies skin types and conditions, and generates personalized skincare routines with product recommendations, enabling scalable and repeatable analysis workflows.

Core Features & Use Cases

  • AI-driven skin analysis: classify skin type, detect conditions, and assign severity.
  • Personalized routines & product guidance: generate morning/evening routines and suggest skincare products.
  • Knowledge base & ops: outline ML pipeline, rule-based scoring, and data models for users, scans, routines, and products.

Quick Start

Start by reviewing the architecture and data models, then run the dockerized services to simulate a full analysis pipeline.

Frequently Asked Questions about SkinGuide

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build an AI-driven skincare analysis platform with personalized routines?

To build an AI-driven skincare analysis platform, orchestrate a multi-service workflow using Docker to analyze facial images, identify skin conditions, and generate personalized routines. This requires an ML skin analysis module and a product recommendation engine.

How does a microservices ML pipeline generate personalized product recommendations from skin images?

A microservices ML pipeline generates personalized product recommendations by passing facial images through a skin analysis module to detect conditions, then feeding those results into a rule-based routine generator and recommendation engine via REST APIs.

Can I use Docker to simulate a scalable ML-based skincare analysis workflow for clinics?

Yes, you can use Docker to simulate a scalable ML-based skincare analysis workflow for clinics by running the dockerized services to execute the full analysis pipeline, enabling repeatable and scalable image processing and routine generation.

What data models are needed for an AI skincare app handling user scans and routines?

An AI skincare app requires data models for users, scans, routines, and products to structure the workflow. These models support the ML skin analysis module and rule-based scoring to map severity levels to personalized morning and evening routines.

Is a rule-based routine generator sufficient for assigning skincare products based on ML severity scores?

Yes, a rule-based routine generator is sufficient for assigning skincare products because it processes the ML skin analysis severity scores to output structured morning and evening routines, which the recommendation engine then matches to specific products.