sample-ai-agent-skills

Use this skill to investigate and troubleshoot IAM Access Analyzer problems by analyzing analyzer creation, findings, external access, unused access, policy validation, policy generation, archive rules, and following structured runbooks. Activate when: analyzer creation failures, finding issues, external access detection problems, unused access analysis errors, policy validation failures, policy generation issues, archive rule problems, or the user says something is wrong with Access Analyzer.

Use this skill to investigate and troubleshoot AWS Certificate Manager (ACM) problems by analyzing certificate status, validation state, renewal configuration, and following structured runbooks. Activate when: DNS validation failures, email validation issues, certificate pending validation, auto-renewal failures, imported certificate expiry, CloudFront certificate errors (us-east-1 requirement), ALB/NLB certificate issues, API Gateway custom domain certificate problems, private CA issues, certificate import failures, chain of trust errors, key algorithm problems, certificate transparency logging concerns, in-use certificate deletion errors, orphaned certificates, or the user says something is wrong with ACM without naming specific symptoms.

Use this skill to investigate and troubleshoot Amazon Managed Grafana (AMG) problems by analyzing workspace configurations, data source connectivity, dashboard errors, authentication/SSO settings, alerting rules, plugin issues, API access, VPC connectivity, and IAM permissions using structured runbooks. Activate when: workspace creation or upgrade failures, SSO/SAML authentication issues, user/role mapping problems, CloudWatch or Prometheus data source errors, OpenSearch connectivity failures, cross-account data source access, dashboard rendering errors, query failures, dashboard import/export issues, alert rule failures, notification channel problems, plugin availability or configuration issues, VPC connectivity problems, private data source access, API key issues, Terraform/CloudFormation provisioning errors, or the user says something is wrong with Managed Grafana without naming specific symptoms.

Use this skill to investigate and troubleshoot Amazon Managed Service for Prometheus (AMP) problems by analyzing workspace configurations, remote write failures, query performance, alerting/ruler issues, ingestion problems, Prometheus-compatible API issues, IAM/SigV4 authentication, and collector configuration. Activate when: workspace creation failures, remote write errors, SigV4 authentication failures, ingestion rate limiting, high cardinality issues, query timeouts, PromQL errors, rule evaluation failures, SNS alert integration issues, ADOT collector problems, Prometheus server remote write configuration, EKS add-on issues, Grafana data source setup, VPC endpoint access, or the user says something is wrong with AMP without naming specific symptoms.

Use this skill to investigate and troubleshoot AWS Amplify Hosting problems by analyzing build failures, deployment issues, custom domains, backend environments, SSR configuration, access control, and CDN performance using structured runbooks. Activate when: build failures, build settings wrong, environment variables missing, deployment failures, branch configuration issues, PR preview problems, custom domain not working, SSL certificate errors, backend environment issues, API integration failures, SSR rendering errors, compute configuration problems, access control misconfigured, basic auth not working, CDN caching issues, rewrite rules not matching, or the user says something is wrong with Amplify without naming specific symptoms.

Use this skill to investigate and troubleshoot Amazon API Gateway problems including REST API, HTTP API, and WebSocket API types by analyzing configurations, integrations, authorizers, deployments, and following structured runbooks. Activate when: Lambda proxy errors, integration timeouts, 4xx/5xx errors, CORS failures, authorization issues (Lambda authorizer, Cognito, IAM), throttling, deployment failures, custom domain problems, WebSocket connection issues, mapping template errors, request validation failures, binary media type issues, stage variable problems, canary deployment issues, or the user says something is wrong with API Gateway without naming specific symptoms.

Use this skill to investigate and troubleshoot AWS AppConfig problems. Activate when: configuration deployment fails, feature flags not toggling, deployment strategy issues, configuration validation errors, environment or application creation failures, hosted configuration version problems, extension failures, or rollback issues.

Use this skill to investigate and troubleshoot AWS Application Discovery Service problems by analyzing agent deployment, agentless discovery, data collection, export, dependency mapping, and Athena integration using structured runbooks. Activate when: agent deployment failures, agentless collector issues, data collection problems, export failures, dependency mapping errors, Athena query issues, or the user says something is wrong with Application Discovery Service without naming specific symptoms.

Use this skill to investigate and troubleshoot Amazon AppFlow problems by analyzing flow creation, connector profiles, flow execution, data mapping, scheduling, destinations, custom connectors, private connections, encryption, and following structured runbooks. Activate when: flow creation failures, connector profile errors, flow execution failures, data mapping issues, scheduling problems, destination errors, custom connector issues, private connection failures, encryption problems, or the user says something is wrong with AppFlow.

Use this skill to investigate and troubleshoot AWS Application Composer problems by analyzing project sync, template imports, resource configuration, connections, SAM/CloudFormation template generation, local development, IDE extensions, deployments, resource policies, and custom resource cards. Activate when: project sync failures, template import errors, resource configuration problems, connection issues, template generation failures, local development errors, IDE extension problems, deployment failures, or the user says something is wrong with Application Composer.

Use this skill to investigate and troubleshoot AWS App Mesh problems by analyzing mesh configurations, virtual nodes, virtual services, virtual routers, Envoy proxy injection, proxy health, proxy configuration, route configuration, traffic shifting, mTLS, certificate management, access logging, tracing, EKS integration, and controller issues using structured runbooks. Activate when: mesh creation or configuration failures, virtual node/service/router issues, Envoy proxy injection failures, proxy health check failures, proxy configuration errors, route configuration problems, traffic shifting not working, mTLS setup issues, certificate management errors, access logging problems, tracing configuration issues, EKS integration failures, App Mesh controller issues, or the user says something is wrong with App Mesh without naming specific symptoms.

Use this skill to investigate and troubleshoot AWS App Runner problems by analyzing service configurations, deployment status, auto-scaling settings, health checks, networking, and following structured runbooks. Activate when: deployment failures, build failures, image pull errors, health check failures, application crashes, port configuration issues, auto-scaling problems, cold start latency, custom domain/SSL issues, VPC connector problems, outbound connectivity failures, ECR source issues, GitHub source issues, instance role permission errors, secrets/environment variable problems, logging issues, X-Ray tracing configuration, or the user says something is wrong with App Runner without naming specific symptoms.

Use this skill to investigate and troubleshoot Amazon AppStream 2.0 problems by analyzing fleet creation, scaling issues, instance failures, image builder configuration, image creation, streaming session failures, latency, disconnects, user pool management, SAML federation, VPC configuration, internet access, application launch failures, app settings persistence, home folders, app settings storage, and following structured runbooks. Activate when: fleet creation failures, scaling not working, instance failures, image builder issues, image creation errors, streaming session failures, high latency, frequent disconnects, user pool problems, SAML federation errors, VPC configuration issues, internet access problems, application launch failures, app settings not persisting, home folder issues, storage problems, or the user says something is wrong with AppStream without naming specific symptoms.

Use this skill to investigate and troubleshoot AWS AppSync problems (GraphQL APIs, merged APIs, real-time subscriptions) by analyzing API configurations, resolvers, data sources, authorization, and following structured runbooks. Activate when: schema errors, resolver failures, VTL mapping issues, JavaScript resolver errors, subscription disconnects, auth failures, caching problems, query latency, N+1 resolver issues, or the user says something is wrong with their AppSync API without naming specific symptoms.

Use this skill to investigate and troubleshoot Amazon Athena problems by analyzing query failures, timeout issues, syntax errors, performance degradation, data format problems, partitioning, SerDe errors, workgroup configuration, federated queries, cost optimization, Glue Catalog integration, Lake Formation permissions, IAM access, encryption, and Athena for Apache Spark issues. Activate when: query failures, query timeouts, syntax errors, slow queries, data format mismatches, partition projection issues, SerDe deserialization errors, workgroup misconfiguration, query result location errors, federated query failures, data source connector issues, high data scan costs, query result reuse problems, Glue Data Catalog sync issues, Lake Formation permission denials, IAM permission errors, encryption failures, Spark session issues, notebook errors, or the user says something is wrong with Athena without naming specific symptoms.

Use this skill to investigate and troubleshoot AWS Audit Manager problems by analyzing assessment creation, frameworks, controls, evidence collection, delegation, reports, custom frameworks, and following structured runbooks. Activate when: assessment creation failures, framework issues, control evaluation errors, evidence collection problems, delegation failures, report generation errors, custom framework issues, or the user says something is wrong with Audit Manager.

Use this skill to investigate and troubleshoot Amazon Aurora (MySQL and PostgreSQL) problems by analyzing cluster configurations, performance metrics, connectivity, parameter groups, and following structured runbooks. Activate when: cluster creation failures, storage issues, cluster endpoint confusion, cluster parameter groups, high CPU or wait events, memory pressure, Aurora I/O model issues, query performance, connection failures, endpoint confusion, RDS Proxy issues, connection limits, writer failover, reader failover, DNS propagation, reader lag, Aurora MySQL binlog replication, Aurora PostgreSQL logical replication, Serverless v2 scaling issues, cold start, capacity allocation, Global Database replication lag, planned failover, unplanned failover, backup failures, backtrack (MySQL only), clone issues, encryption, IAM database authentication, DMS to Aurora, MySQL/PostgreSQL migration, or the user says something is wrong with Aurora without naming specific symptoms.

Use this skill to investigate and troubleshoot EC2 Auto Scaling problems by analyzing scaling activities, launch failures, health checks, scaling policies, lifecycle hooks, ELB integration, and mixed instances configuration using structured runbooks. Activate when: group not scaling out, not scaling in, scaling too aggressively, cooldown issues, launch failures, launch template errors, AMI issues, health check failures, instance refresh problems, warm pool issues, target tracking not working, step scaling misconfigured, predictive scaling inaccurate, lifecycle hook timeouts, termination policy unexpected, ELB health check mismatches, EventBridge events missing, mixed instances allocation failures, spot capacity issues, or the user says something is wrong with Auto Scaling without naming specific symptoms.

Use this skill to investigate and troubleshoot AWS Backup Gateway problems by analyzing gateway deployment, connectivity, hypervisor connections, vCenter authentication, VM discovery, VM backups, restores, bandwidth throttling, network configuration, and gateway maintenance. Activate when: gateway deployment failures, connectivity issues, hypervisor errors, VM backup failures, restore problems, performance issues, or the user says something is wrong with Backup Gateway.

Use this skill to investigate and troubleshoot AWS Backup problems by analyzing backup jobs, restore operations, backup plans, vault configurations, cross-account setups, and following structured runbooks. Activate when: backup job failures, restore failures, backup plan misconfiguration, vault access issues, vault lock problems, cross-region copy failures, cross-account backup issues, KMS encryption errors, IAM permission problems, service-specific backup issues (EC2, RDS, DynamoDB), compliance reporting gaps, audit manager findings, lifecycle rule confusion, resource selection failures, on-demand backup errors, point-in-time restore issues, or the user says something is wrong with AWS Backup without naming specific symptoms.

Use this skill to investigate and troubleshoot AWS Batch problems by analyzing job failures, compute environments, job queues, job definitions, networking, array jobs, multi-node parallel jobs, performance, and security using structured runbooks. Activate when: job failures, jobs stuck in RUNNABLE, job timeout, compute environment failures, EC2 vs Fargate issues, spot interruptions, job queue scheduling problems, job definition errors, container configuration issues, VPC networking problems, ECR access failures, array job failures, multi-node parallel issues, throughput bottlenecks, resource optimization, IAM role errors, secrets access problems, or the user says something is wrong with AWS Batch without naming specific symptoms.

Use this skill to investigate and troubleshoot Amazon Bedrock problems by analyzing model access, invocation errors, throttling, knowledge base creation, sync failures, retrieval issues, agent creation, action group errors, orchestration problems, custom model training, provisioned throughput, content filtering, topic denial, latency, token limits, IAM permissions, VPC configuration, Lambda integration, streaming responses, and following structured runbooks. Activate when: model access denied, invocation errors, throttling/rate limits, knowledge base creation failures, data sync issues, poor retrieval quality, agent creation errors, action group failures, orchestration loops, fine-tuning failures, provisioned throughput issues, guardrail blocking legitimate content, latency problems, token limit exceeded, IAM permission errors, VPC endpoint issues, Lambda timeout with Bedrock, streaming response errors, or the user says something is wrong with Bedrock without naming specific symptoms.

Use this skill to investigate and troubleshoot Bottlerocket OS problems by analyzing AMI launches, OS updates, ECS/EKS agent issues, admin/control container access, networking, storage, settings API, bootstrap, security hardening, and following structured runbooks. Activate when: AMI launch failures, update failures, ECS agent issues, kubelet problems, admin container access, control container issues, networking misconfigurations, storage errors, settings API failures, bootstrap problems, security hardening questions, or the user says something is wrong with Bottlerocket.

Use this skill to investigate and troubleshoot Amazon Braket quantum computing problems by analyzing quantum task failures, simulator errors, hardware device issues, circuit validation, hybrid jobs, notebook instances, SDK errors, cost management, device availability, and result retrieval using structured runbooks. Activate when: quantum task failures, task timeouts, simulator errors, hardware device problems, circuit validation failures, hybrid job issues, notebook instance problems, SDK errors, cost concerns, device availability questions, result retrieval failures, or the user says something is wrong with Braket.

Use this skill to investigate and troubleshoot AWS Budgets Actions problems by analyzing budget creation, alert configuration, action execution, IAM policy actions, SCP actions, EC2/RDS instance actions, approval workflows, threshold configuration, notifications, and organization budgets, following structured runbooks. Activate when: budget creation failures, alert configuration issues, action execution failures, IAM policy action errors, SCP action failures, EC2 instance action errors, RDS instance action errors, approval workflow issues, threshold configuration, notification failures, organization budgets, or the user says something is wrong with Budgets Actions.

Use this skill to investigate and troubleshoot AWS Systems Manager Change Manager problems by analyzing change templates, change requests, approval workflows, runbook execution, scheduling, and following structured runbooks. Activate when: change template errors, change request failures, approval workflow issues, runbook execution problems, scheduling conflicts, or the user says something is wrong with Change Manager.

Use this skill to investigate and troubleshoot advanced AWS Chatbot problems by analyzing custom action failures, action approvals, Microsoft Teams integration, guardrail configuration, notification filtering, run command from chat, Lambda invocation from chat, cross-account notifications, event pattern matching, and audit logging. Activate when: custom action failures, approval issues, Teams integration problems, guardrail configuration errors, notification filtering issues, run command from chat failures, Lambda invocation errors, cross-account notification problems, event pattern matching issues, audit logging gaps, or the user says something is wrong with advanced AWS Chatbot features.

Use this skill to investigate and troubleshoot AWS Chatbot problems by analyzing Slack workspace configurations, Microsoft Teams channel setups, SNS notification delivery, EventBridge integration, CLI commands in chat, command permissions, channel IAM roles, guardrail policies, CloudWatch alarm notifications, and Security Hub finding delivery using structured runbooks. Activate when: Slack workspace configuration issues, Teams channel setup failures, SNS notification not delivered to chat, EventBridge events not appearing, CLI commands failing in chat, permission errors for chat commands, channel role misconfiguration, guardrail policy blocking actions, CloudWatch alarm notifications missing, Security Hub integration not working, or the user says something is wrong with AWS Chatbot without naming specific symptoms.

Use this skill to investigate and troubleshoot Amazon Chime SDK problems by analyzing meeting creation, audio/video issues, messaging, SIP media applications, PSTN integration, identity management, and SDK integration using structured runbooks. Activate when: meeting creation failures, audio/video quality issues, messaging problems, SIP media application errors, PSTN audio failures, identity/auth issues, SDK integration errors, or the user says something is wrong with Chime SDK without naming specific symptoms.

Use this skill to investigate and troubleshoot AWS CI/CD pipeline problems by analyzing CodePipeline executions, CodeBuild projects, CodeDeploy deployments, artifact management, and following structured runbooks. Activate when: pipeline execution failures, source stage errors, approval timeouts, cross-account pipeline issues, build failures, build timeouts, out-of-memory builds, Docker build issues, deployment failures, rollback problems, health check failures, lifecycle hook errors, artifact upload or download failures, encryption issues, S3 permissions, GitHub/CodeCommit source problems, ECR image issues, Lambda deploy failures, pipeline or deployment notifications not working, slow builds, slow deployments, or the user says something is wrong with their CI/CD pipeline without naming specific symptoms.

Use this skill to investigate and troubleshoot AWS Clean Rooms ML problems by analyzing training model failures, configured model errors, audience generation issues, lookalike models, collaboration ML config, privacy budgets, seed audiences, output configuration, S3 data access, IAM permissions, differential privacy, and following structured runbooks. Activate when: training model failures, configured model errors, audience generation issues, lookalike model problems, collaboration ML configuration errors, privacy budget exhaustion, seed audience errors, output configuration failures, S3 data access issues, IAM permission errors, differential privacy problems, or the user says something is wrong with Clean Rooms ML.

Use this skill to investigate and troubleshoot AWS Clean Rooms problems by analyzing collaborations, configured tables, analysis rules, and following structured runbooks. Activate when: Collaboration creation failures, membership issues, configured table errors, analysis rule problems, query failures, output configuration issues, differential privacy errors, cryptographic computing problems, ML modeling failures, lookalike segment issues, IAM permission errors, data access problems, or the user says something is wrong with Clean Rooms without naming specific symptoms.

Use this skill to investigate and troubleshoot AWS CloudFormation and CDK problems by analyzing stack events, template errors, drift state, resource failures, and following structured runbooks. Activate when: CREATE_FAILED, UPDATE_FAILED, DELETE_FAILED, UPDATE_ROLLBACK_FAILED, template syntax errors, circular dependencies, parameter issues, resource creation failures, dependency failures, resource timeouts, resource already exists, drift detection, drift remediation, resource import, nested stack failures, output reference errors, custom resource Lambda failures, custom resource timeouts, cleanup on delete failures, StackSet operation failures, StackSet instance failures, StackSet deployment timeouts, change set failures, replacement detection, CDK synth errors, CDK deploy failures, CDK bootstrap issues, or the user says something is wrong with CloudFormation or CDK without naming specific symptoms.

Use this skill to investigate and troubleshoot Amazon CloudFront problems by analyzing distribution configurations, cache behaviors, origin settings, SSL/TLS certificates, edge functions, and following structured runbooks. Activate when: cache miss issues, stale content, invalidation failures, origin connection errors, S3 origin access problems, custom origin errors, SSL/TLS certificate issues, high latency, compression problems, signed URL/cookie failures, geo-restriction issues, Lambda@Edge errors, CloudFront Functions failures, 4xx/5xx errors, redirect loops, behavior matching issues, access log problems, or the user says something is wrong with CloudFront without naming specific symptoms.

Use this skill to investigate and troubleshoot AWS CloudHSM problems by analyzing cluster creation, HSM provisioning, client connectivity, key management, user management, backup/restore, high availability, CloudHSM SDK, PKCS#11, JCE provider, and OpenSSL integration following structured runbooks. Activate when: cluster creation failures, HSM initialization issues, client connection errors, key operation failures, crypto user management problems, backup failures, HA failover issues, SDK errors, PKCS#11 library problems, JCE provider exceptions, OpenSSL engine errors, or the user says something is wrong with CloudHSM without naming specific symptoms.

Use this skill to investigate and troubleshoot AWS Cloud Map problems by analyzing namespace configurations, service registrations, instance management, DNS resolution, TTL settings, ECS service discovery, EKS integration, IAM permissions, and VPC associations using structured runbooks. Activate when: DNS or HTTP namespace issues, service registration failures, health check problems, instance registration or deregistration issues, DNS resolution failures, TTL configuration problems, ECS service discovery not working, EKS integration issues, IAM permission errors, VPC association problems, or the user says something is wrong with Cloud Map without naming specific symptoms.

Use this skill to investigate and troubleshoot AWS CloudShell problems by analyzing session launches, environment persistence, network connectivity, storage, permissions, timeouts, performance, and following structured runbooks. Activate when: session launch failures, environment persistence issues, network connectivity problems, VPC environment errors, storage issues, file transfer failures, permissions errors, credential issues, timeout/disconnection problems, performance issues, custom environment problems, or the user says something is wrong with CloudShell.

Use this skill to investigate and troubleshoot AWS CloudTrail problems by analyzing trail creation failures, log delivery issues, S3 bucket configuration, missing events, data events, management events, organization trails, delegated admin, CloudTrail Lake queries, event data stores, Insights events, anomaly detection, CloudWatch Logs integration, EventBridge rules, log file validation, encryption, data event costs, and Lake pricing. Activate when: trail not delivering logs, events missing from CloudTrail, data events not captured, organization trail issues, CloudTrail Lake query failures, Insights not detecting anomalies, CloudWatch Logs not receiving events, log validation failures, encryption errors, unexpected CloudTrail costs, or the user says something is wrong with CloudTrail without naming specific symptoms.

Use this skill to investigate and troubleshoot Amazon CloudWatch Application Signals problems by analyzing service discovery, instrumentation, SLO configuration, service dependency mapping, metric collection, trace correlation, EKS/EC2 integration, alarm configuration, and following structured runbooks. Activate when: service discovery failures, instrumentation errors, SLO creation or evaluation issues, dependency mapping problems, metric collection failures, trace or log correlation errors, EKS/EC2 integration issues, alarm configuration problems, or the user says something is wrong with Application Signals.

Use this skill to investigate and troubleshoot Amazon CloudWatch problems by analyzing log groups, metrics, alarms, Synthetics canaries, Contributor Insights rules, and cross-account observability configurations following structured runbooks. Activate when: missing logs, log group retention issues, subscription filter failures, missing or delayed metrics, custom metric publishing errors, metric math problems, INSUFFICIENT_DATA alarms, alarms not triggering, composite alarm misconfiguration, alarm action failures, Synthetics canary failures, canary VPC issues, canary script errors, Log Insights query errors or timeouts, Contributor Insights rule or cost issues, cross-account observability access problems, CloudWatch Agent issues, or the user says something is wrong with CloudWatch without naming specific symptoms.