aws

Builds generative AI applications on Amazon Bedrock. Covers model invocation (Converse API, InvokeModel), RAG with Knowledge Bases, Bedrock Agents, Guardrails, and AgentCore. Use when invoking models, setting up Knowledge Bases, creating agents, applying guardrails, deploying to AgentCore, troubleshooting Bedrock errors (ThrottlingException, AccessDeniedException), or choosing models (Claude, Llama, Nova, Titan). ALSO USE for prompt caching setup and debugging, quota health checks and throttling diagnosis, cost attribution and tracking, migrating between Claude model generations (4.5 to 4.6 to 4.7), chunking strategies, API selection (Converse vs InvokeModel), guardrail capabilities, and model selection. NOT for custom model training, Rekognition, or Comprehend.

Analyze AWS costs, find savings, manage budgets, evaluate Savings Plans and Reserved Instances, right-size EC2/Lambda/RDS/EBS with Compute Optimizer, look up service pricing, query CUR with Athena, detect cost anomalies, scope costs to billing views, and monitor Free Tier usage. Triggers on: AWS bill, cost analysis, reduce spend, savings plan, reserved instance, right-size, budget alert, cost optimization, pricing, free tier, cost anomaly, CUR, cost audit, billing view, billing view ARN.

Authors, deploys, and troubleshoots AWS infrastructure using CDK with TypeScript or Python. Covers best practices, stack architecture, and construct patterns. Always use when writing CDK constructs, bootstrapping environments, running cdk deploy/synth/diff, fixing CDK or CloudFormation errors, planning stack structure, importing existing resources, resolving drift, or refactoring stacks without resource replacement.

Author, validate, and troubleshoot AWS CloudFormation templates. Covers template authoring with secure defaults, pre-deployment validation (cfn-lint, cfn-guard, change sets), and root-cause diagnosis of failed stacks using CloudFormation events and CloudTrail correlation.

Deploys and operates containerized workloads on ECS, Fargate, and ECR. Covers task definitions, Fargate services, ECR repository setup and lifecycle policies, ECS Exec debugging, service scaling, deployment strategies, load balancer integration, and logging configuration. Use when deploying, debugging, or optimizing containers on AWS. ALSO USE for container deployment options (ECS vs ECS Express Mode), networking modes, health check troubleshooting, OOM errors, secrets injection, blue/green deployments, ECR image management, and App Runner sunset guidance and migration. NOT for Kubernetes, EKS, or CI/CD pipelines.

Verified corrections for IAM behaviors that AI agents frequently get wrong — policy evaluation edge cases, trust policy gotchas, STS session limits, Organizations quirks, and SAML/MFA specifics. Use alongside documentation when working with IAM roles, policies, STS, or Organizations. Do NOT use for non-IAM authorization like Cognito user-pool policies or app-level RBAC.

Guides use of AWS messaging and streaming services. Covers Amazon SQS, Amazon SNS, Amazon EventBridge, Amazon MQ, Amazon Kinesis Data Streams, Amazon Data Firehose, Amazon Managed Service for Apache Flink, and Amazon Managed Streaming for Apache Kafka (MSK). Use when implementing messaging and streaming patterns.

Builds, configures, debugs, and optimizes AWS observability using CloudWatch (Logs Insights, Metrics, Alarms, Dashboards, EMF), X-Ray, CloudTrail, and ADOT. Covers Log Insights query syntax (fields, filter, stats, parse, pattern, join, subqueries), alarm configuration (metric, composite, anomaly detection, missing data treatment), dashboard design, custom metrics (PutMetricData, EMF, metric filters), X-Ray tracing (ADOT, sampling rules, annotations vs metadata), ADOT collector config, and CloudTrail auditing. Use when the user mentions CloudWatch, Log Insights, alarms, INSUFFICIENT_DATA, dashboards, custom metrics, EMF, X-Ray, traces, sampling, CloudTrail, who deleted, ADOT, OpenTelemetry, observability, monitoring, synthetics, canaries, or troubleshooting alarm behavior. Do NOT use for application logging setup, container log drivers, or security threat detection.

Testing standards, patterns, and utilities for Graph Explorer including Vitest, DbState, renderHookWithState, test data factories, SPARQL test helpers, and backward compatibility testing for persisted data.

Git workflow conventions for Graph Explorer. Use when making commits, creating branches, or discussing version control practices.

Handle management of any GitHub related tasks, including creating or modifying issues, publishing a branch as a pull requests (or PRs), or creating or modifying sub-issues or child issues.

Database connector and explorer patterns for Gremlin, openCypher, and SPARQL, including the query template tag and escapeString usage.

Graph Explorer product overview including supported graph types, query languages, databases, key features, and high-level architecture.

React component patterns, hooks, naming conventions, and the query-language translation system for Graph Explorer.

Schema storage and discovery in Graph Explorer, including SchemaStorageModel persistence, edge connections, incremental schema growth, and related Jotai atoms.

Tailwind CSS v4 styling rules, responsive design patterns, and data attribute conventions for Graph Explorer.

Exact patterns generated code must follow to match the AWS SDK for .NET public API surface

How to deserialize a Smithy model.json into typed C# records and navigate the shape graph

Rules for converting Smithy shape types to .NET types, including nullability and collection defaults

Use when creating, validating, or reasoning about DevConfig files for AWS SDK for .NET changes, including deciding whether Core or Services entries are required, choosing patch vs minor bumps, and writing changelog messages.

Use when working on the AWS SDK for .NET source code itself, including Core runtime changes, service client implementations, generator or model changes, repo-specific build and validation flows, and V3/V4 branch-targeting decisions.

Add a new AWS event source attribute (e.g., Kinesis, Kafka, MQ) to the Lambda .NET Annotations framework, including the attribute class, source generator integration, CloudFormation writer, unit tests, writer tests, source generator tests, and integration tests

Validates Java application compatibility with AWS Graviton (ARM64) architecture by analyzing native libraries, dependencies (including transitive), and architecture-specific code. Performs static analysis, applies ARM64-required dependency updates, configures Graviton JVM flags, and validates builds on ARM64. Use when migrating Java workloads from x86 to Graviton, validating ARM64 readiness, or running AWS Transform Custom java-x86-to-graviton transformations.

Proactively manage AWS service quota increases for the customer's account. Monitor quota utilization via Service Quotas, request increases, track pending requests, and verify applied changes. This skill enables the agent to act as a persistent butler — continuously monitoring limits, pre-emptively requesting increases before quotas become blocking, and shepherding requests through to completion.