skills.rest
JaviMontano
JaviMontanoCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

metodologia-ai-architecture-implementation

Design end-to-end AI architectures with phased implementation blueprints and ADRs.

Updated Mar 31, 2026
Search Tags:#mlops#observability#ci-cd#ai-architecture#data-pipeline#model-registry#serving-inference
One-click install
npx skills add https://github.com/JaviMontano/metodologia-propuesta-agent-public --skill metodologia-ai-architecture-implementation
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: metodologia-ai-architecture-implementation
Source: https://github.com/JaviMontano/metodologia-propuesta-agent-public/tree/main/.claude/skills/ai/ai-architecture-implementation
Command: npx skills add https://github.com/JaviMontano/metodologia-propuesta-agent-public --skill metodologia-ai-architecture-implementation

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps organizations plan and implement end-to-end AI architecture projects, translating architectural decisions into production-ready infrastructure and workflows that scale from discovery to monitoring.

Core Features & Use Cases

  • Technology selection guidance for AI systems (ML pipelines, model serving, CI/CD)
  • Phase-based implementation playbooks (Foundation to Monitoring)
  • Guardrails, RAG, and agent-framework considerations for production-grade AI
  • Create implementation blueprints, ADRs, and governance artifacts for repeatable delivery

Quick Start

Prototype a phased AI architecture implementation plan from foundation to monitoring.

Frequently Asked Questions about metodologia-ai-architecture-implementation

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

FAQPage Schema
How do I design an end-to-end AI architecture for production?▼

To design an end-to-end AI architecture, translate architectural decisions into production-ready infrastructure, data pipelines, and governance artifacts like ADRs across phased deliverables from foundation to monitoring.

What is included in MLOps workflows for model serving and inference?▼

MLOps workflows for model serving and inference include CI/CD gates, drift monitoring, feature store considerations, and a model registry to ensure scalable and governed deployment of AI systems.

How do I implement guardrails for RAG and agent frameworks?▼

Implementing guardrails for RAG and agent frameworks involves translating architectural decisions into production-ready workflows with phased delivery, ensuring comprehensive governance and observability across the AI architecture.

Can I use this approach to upgrade existing data pipelines and model registries?▼

Yes, this approach applies to projects building or upgrading AI systems, mapping phased implementation playbooks to existing data pipelines, model registries, and serving infrastructure to achieve production-grade architecture.

What's the best way to create an AI architecture implementation playbook?▼

The best way to create an AI architecture implementation playbook is to generate phased deliverables spanning foundation to monitoring, incorporating ADRs, blueprints, and governance artifacts for repeatable delivery.

Related Skills

Explore More Software Engineering Skills→
bacchus-labsbacchus-labs
4

brainstorming

Transform raw ideas into validated design specifications through structured questioning.

Official
Intermediate
belokonmbelokonm
8

machine-learning-engineer

Deploy ML models to production with infrastructure-as-code templates and monitoring.

Community
Advanced
aRustyDevaRustyDev
1

ml-pipeline-workflow

Design and manage end-to-end MLOps pipelines with DAG-based orchestration.

Community
Advanced
TeoSlayerTeoSlayer
7

pilot-ci-cd-pipeline-setup

Deploy a decentralized CI/CD pipeline across three agents with role-based coordination.

Community
Advanced