npx claudepluginhub diegouis/provectus-marketplace --plugin proagent-aws-aiWant just this skill?
Then install: npx claudepluginhub u/[userId]/[slug]
Building AI Solutions on AWS - Bedrock AgentCore agents, MCP server development and deployment, Knowledge Bases RAG with S3 Vectors, generative AI architecture patterns, CDK/CloudFormation infrastructure, and AWS AI service integration. Use when designing, building, deploying, or reviewing any AI system on Amazon Web Services including chatbots, copilots, multi-agent orchestration, content generation pipelines, and enterprise knowledge systems. Do NOT use for general backend development (use backend-assistant), frontend work (use frontend-assistant), or non-AI AWS infrastructure.
This skill uses the workspace's default tool permissions.
references/agentcore-patterns.mdreferences/architecture-patterns.mdreferences/cdk-iac-patterns.mdreferences/knowledge-bases-rag.mdreferences/mcp-server-patterns.mdBuilding AI Solutions on AWS
Comprehensive AWS AI skill covering the full lifecycle of AI solution development on Amazon Web Services — from architecture design through agent building, MCP server creation, knowledge base setup, and production deployment.
When to Use This Skill
- Designing AI architectures on AWS (chatbots, agents, copilots, content generators)
- Building AI agents with Amazon Bedrock AgentCore
- Creating and deploying Model Context Protocol (MCP) servers on AWS
- Setting up RAG systems with Amazon Bedrock Knowledge Bases
- Deploying AI infrastructure with CDK, CloudFormation, or Terraform
- Integrating AWS AI services (Bedrock, SageMaker, Comprehend, Rekognition, etc.)
- Reviewing AWS AI architectures for Well-Architected compliance
- Implementing responsible AI with Bedrock Guardrails
- Optimizing AI workload costs on AWS
- Selecting foundation models (Claude, Nova, Llama, Mistral) for specific use cases
- Configuring Cedar policies for agent access control
- Setting up agent evaluation and observability
CRITICAL: Ask First, Load Later
DO NOT read reference files, run environment detection commands, or load mode files until the user has told you what they want to do.
MANDATORY: You MUST call the AskUserQuestion tool — do NOT render these options as text:
AskUserQuestion( header: "AWS AI", question: "What AWS AI topic would you like help with?", options: [ { label: "Bedrock AgentCore", description: "Build agents with AgentCore, Cedar policies, and evaluations" }, { label: "MCP Servers on AWS", description: "Create and deploy Model Context Protocol servers on AWS" }, { label: "RAG / Knowledge Bases", description: "RAG systems, Knowledge Bases, chunking, vector storage" }, { label: "AI Architecture", description: "AI architecture design, service and model selection, Well-Architected" } ] )
If the user selects "Other", offer CDK/IaC infrastructure for AI workloads.
Reference Routing
CONTEXT GUARD: Load reference files only when the user's request matches a specific topic below. Do NOT load all references upfront.
| User Intent | Reference File |
|---|---|
| Building agents with Bedrock AgentCore, Cedar policies, evaluations | references/agentcore-patterns.md |
| Creating or deploying MCP servers on AWS | references/mcp-server-patterns.md |
| RAG systems, Knowledge Bases, chunking, vector storage | references/knowledge-bases-rag.md |
| AI architecture design, service selection, model selection | references/architecture-patterns.md |
| CDK infrastructure, CloudFormation, IaC for AI workloads | references/cdk-iac-patterns.md |
Core Principles
- Follow the AWS Well-Architected Generative AI Lens (six pillars)
- Use AgentCore for production agent deployments with session isolation
- Prefer S3 Vectors for cost-optimized vector storage (90% savings)
- Always apply Bedrock Guardrails and Cedar policies for safety
- Deploy infrastructure as code — never ClickOps
Visual Diagramming
Use Excalidraw MCP for AWS AI architecture diagrams, agent flow diagrams, RAG pipeline topology, and multi-agent orchestration visualizations.
Reference Assets
See AWS Bedrock AgentCore Docs, AWS MCP Servers, Gen AI CDK Constructs, and the Well-Architected Generative AI Lens.
Similar Skills
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.