install
source · Clone the upstream repo
git clone https://github.com/mdbabumiamssm/LLMs-Universal-Life-Science-and-Clinical-Skills-
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/mdbabumiamssm/LLMs-Universal-Life-Science-and-Clinical-Skills- "$T" && mkdir -p ~/.claude/skills && cp -r "$T/Skills/AI_Providers/Cloud_AI_Operations_AWS_Azure_2026" ~/.claude/skills/mdbabumiamssm-llms-universal-life-science-and-clinical-skills-cloud-ai-operation && rm -rf "$T"
manifest:
Skills/AI_Providers/Cloud_AI_Operations_AWS_Azure_2026/SKILL.mdsource content
<!--
# COPYRIGHT NOTICE
# This file is part of the "Universal Biomedical Skills" project.
# Copyright (c) 2026 MD BABU MIA, PhD <md.babu.mia@mssm.edu>
# All Rights Reserved.
#
# This code is proprietary and confidential.
# Unauthorized copying of this file, via any medium is strictly prohibited.
#
# Provenance: Authenticated by MD BABU MIA
-->
name: cloud-ai-operations-aws-azure-2026 description: Operate AI workloads on AWS Bedrock and Azure AI/Azure OpenAI with production-focused cloud controls. Use when selecting managed model providers, implementing enterprise auth, and designing resilient cloud-native inference pipelines. measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools:
- read_file
- run_shell_command
Cloud AI Operations: AWS + Azure (2026)
Workflow
- Choose cloud target (AWS, Azure, or both) and capture compliance constraints.
- Verify current service docs and SDK references in
.references/sources.md - Implement auth first (IAM/STS or Entra/service principal).
- Add observability hooks before scaling traffic.
- Validate with low-volume staged inference tests.
Output Requirements
- Name selected cloud AI service and reason.
- Specify auth pattern and secret-handling approach.
- Include one failover strategy across regions or providers.