Amazon Web Services - Labs
Official@awslabs · Seattle, WA
AWS Labs
Agent Skills by Amazon Web Services - Labs
Showing 143 vetted skills indexed across 6 GitHub repositories.
awslabsaws-lambda-microvms
Build, run, and operate Firecracker-isolated Lambda MicroVMs with snapshot-resumable sessions.
awslabsapi-gateway
Design, deploy, and operate Amazon API Gateway REST, HTTP, and WebSocket APIs.
awslabsaws-lambda-managed-instances
Evaluate, configure, and migrate Lambda workloads to Lambda Managed Instances on EC2.
awslabsaws-step-functions
Build AWS Step Functions state machines in Amazon States Language using JSONata expressions.
awslabshyperpod-issue-report
Collects diagnostic logs from HyperPod EKS and Slurm cluster nodes into S3 reports.
awslabshyperpod-version-checker
Detect and report software component versions on SageMaker HyperPod cluster nodes.
awslabsmodel-evaluation
Generates Python code to evaluate SageMaker models using LLM-as-Judge or Custom Scorer workflows.
awslabsfinetuning-technique
Selects and validates SFT, DPO, RLVR, or RLAIF fine-tuning techniques against SageMaker model recipes.
awslabsmodel-deployment
Generates code to deploy LoRA fine-tuned SageMaker models to SageMaker endpoints or Bedrock.
awslabsdirectory-management
Creates project directory structures and organizes artifacts for SageMaker AI workflows.
awslabsdataset-evaluation
Validates JSONL dataset formatting and schema compliance for SageMaker model fine-tuning and evaluation.
awslabsplanning
Generates structured step-by-step plans for SageMaker model customization workflows.
awslabshyperpod-ssm
Execute commands and transfer files on SageMaker HyperPod cluster nodes via AWS Systems Manager.
awslabshyperpod-performance-debugger
Diagnose uneven NCCL bandwidth and filesystem bottlenecks on SageMaker HyperPod clusters.
awslabsfinetuning
Generates code to fine-tune base models using SageMaker serverless training jobs.
awslabshyperpod-node-debugger
Diagnose per-node hardware, network, and software issues on SageMaker HyperPod clusters.
awslabsdataset-transformation
Generates Python code that converts ML datasets between training and evaluation formats.
awslabsuse-case-specification
Creates a use case specification document defining business problems, stakeholders, and success criteria for model customization.
awslabssdk-getting-started
Validates SageMaker SDK version, AWS region, and execution role before ML operations.
awslabshyperpod-slurm-debugger
Diagnose Slurm scheduler and node-daemon issues on SageMaker HyperPod clusters.
awslabshyperpod-nccl
Diagnose NCCL and training-pod failures on SageMaker HyperPod GPU clusters.
awslabshyperpod-cluster-debugger
Diagnose and remediate SageMaker HyperPod cluster failures across EKS and Slurm orchestrators.
awslabsmodel-selection
Selects a base model for finetuning by querying SageMaker Hub and comparing benchmark rankings.
awslabsdocument-service
Analyzes codebases to generate technical documentation and architecture diagrams with file-line citations.
Frequently Asked Questions About Amazon Web Services - Labs
FAQPage SchemaWhat specific tasks can I perform using these architecture patterns?▼
You can design production-ready AWS environments, execute clinical data validation, perform genomic variant calling, and map healthcare claims to regulatory standards like CDISC or CMS-HCC.
Who is the target persona for these technical resources?▼
These resources are designed for cloud architects, bioinformatics engineers, healthcare data scientists, and site reliability engineers managing complex, regulated workloads on AWS.
What are the primary dependencies for deploying these architectures?▼
Deployments typically require AWS account access, familiarity with Infrastructure as Code frameworks like CDK or Terraform, and specific domain knowledge of healthcare data standards like HL7v2 or FHIR.