CtrlK
BlogDocsLog inGet started
Tessl Logo

aws-architecture-implementation

Guides implementation of AI/GenAI architectures on AWS — Bedrock setup, SageMaker pipelines, OpenSearch vector stores, API Gateway configuration, security hardening, cost controls, and deployment automation. This skill should be used when the user asks to 'implement AI on AWS', 'set up Bedrock', 'deploy SageMaker pipeline', 'configure OpenSearch for RAG', 'implement AWS AI security', 'set up AWS AI monitoring', or mentions AWS AI deployment, Bedrock Knowledge Base setup, SageMaker endpoint deployment, AWS GenAI implementation, or AWS AI CI/CD pipeline. [EXPLICIT]

SKILL.md
Quality
Evals
Security

AWS Architecture Implementation for AI/GenAI Workloads

Generic, brand-neutral engineering capability; deep, sourced playbooks live in references/ and knowledge/. [DOC]

Generic, brand-neutral engineering capability; sourced playbooks in references//knowledge/. [DOC]

TL;DR

Guiar la implementación de arquitecturas AI/GenAI en AWS — desde la configuración de servicios (Bedrock, SageMaker, OpenSearch Serverless) hasta deployment automation, security hardening, y cost controls. Produce guías de implementación paso-a-paso, templates de IaC, patrones de deployment, y configuración de monitoreo con servicios AWS nativos [EXPLICIT]

When to Use

  • Implementar arquitectura Bedrock RAG (Knowledge Base + OpenSearch + Guardrails)
  • Configurar pipeline SageMaker completo (training → registry → endpoint → monitoring)
  • Desplegar sistema de agentes Bedrock con action groups y knowledge bases
  • Implementar multi-model routing con cost controls en AWS
  • Configurar security stack completo para AI en AWS (IAM, VPC, WAF, Guardrails, KMS)
  • Implementar CI/CD para modelos en AWS (CodePipeline, Step Functions)
  • Configurar monitoring y observabilidad para AI en AWS (CloudWatch, X-Ray, Model Monitor)
  • Ejecutar roadmap de remediación de una auditoría AWS AI

When NOT to Use

  • Diseñar la arquitectura AWS (antes de implementar) → aws-architecture-design
  • Auditar implementación existente → aws-architecture-audit
  • Implementar arquitectura AI cloud-agnostic → ai-architecture-implementation
  • Diseñar patrones de arquitectura AI → ai-design-patterns
  • Implementar infraestructura AWS general (no AI) → infrastructure-architecture

Sub-capabilities (resource map)

Deep, evidence-tagged playbooks — open the one the task needs (ICM Layer 3, on-demand). [INFERENCE]

Reference
references/aws-deployment-patterns.md
references/aws-iac-templates.md
references/aws-service-setup.md
references/full-playbook.md

Procedure

  1. Resolve the sub-capability; open the matching references/ playbook. [EXPLICIT]
  2. Apply its decision tables; pick the strategy explicitly. [EXPLICIT]
  3. Validate against the Quality Criteria and tag every claim. [EXPLICIT]

Quality Criteria

  • Sub-capability resolved to one playbook. [INFERENCE]
  • Claims evidence-tagged. [EXPLICIT]

Contract

  • Aceptación: capability resolved to its reference playbook, applied, validated, evidence-tagged. [EXPLICIT]
  • Límites: 1. NO diseña la arquitectura — implementa un diseño existente (ver aws-architecture-design) 2. NO genera IaC completo listo para producción — provee templates y guías conceptua. [EXPLICIT]
  • Casos borde: 1. Región sin Bedrock: Usar cross-region inference profile. Si compliance impide cross-region, implementar con SageMaker (self-hosted model) como alternativa completa. [EXPLICIT]
  • Supuestos: 1. Cuenta AWS con acceso a Bedrock y/o SageMaker en la región target 2. Arquitectura AWS diseñada (output de aws-architecture-design) 3. Equipo con experiencia básica en AWS (IAM,. [SUPUESTO]
  • Trade-off: Decision Enables Constrains When to Use ---------- --------- ------------ ------------- Bedrock (managed) Fast setup, zero-ops inference Limited model customi. [EXPLICIT]

Packet

Capas del packet, cargables bajo demanda (disciplina ICM: una capa por vez, nunca todas juntas): references/ guías de profundidad (cargar UNA por etapa) · knowledge/ cuerpo de conocimiento · prompts/ prompts listos · examples/ salida de ejemplo · agents/ subagentes del packet · assets/ recursos estáticos.

Repository
JaviMontano/claude-plugins
Last updated
First committed

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.