[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-aws-aws-serverless":3,"mdc-wldile-key":38,"related-repo-aws-aws-serverless":565,"related-org-aws-aws-serverless":665},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":27,"repoUrl":28,"updatedAt":29,"license":30,"forks":31,"topics":32,"repo":33,"sourceUrl":36,"mdContent":37},"aws-serverless","build and manage AWS serverless applications","Builds, deploys, manages, debugs, configures, and optimizes serverless applications on AWS using Lambda, API Gateway, Step Functions, EventBridge, and SAM\u002FCDK. Covers cold starts, CORS debugging, event source mappings, troubleshooting, concurrency, SnapStart, Powertools, function URLs, EventBridge Scheduler, Lambda layers, and production readiness. Triggers on mentions of Lambda, API Gateway, Step Functions, SAM templates, CDK serverless stacks, DynamoDB stream triggers, SQS event sources, cold starts, timeouts, 502\u002F504 errors, throttling, concurrency, CORS, Powertools, or any event-driven architecture on AWS, even without the word \"serverless.\" Does not apply to EC2, ECS\u002FFargate containers, or Amplify hosting.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"aws","AWS (Amazon)","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Faws.png",[12,16,19,22,24],{"name":13,"slug":14,"type":15},"Deployment","deployment","tag",{"name":17,"slug":18,"type":15},"API Development","api-development",{"name":20,"slug":21,"type":15},"Serverless","serverless",{"name":23,"slug":8,"type":15},"AWS",{"name":25,"slug":26,"type":15},"Debugging","debugging",1822,"https:\u002F\u002Fgithub.com\u002Faws\u002Fagent-toolkit-for-aws","2026-07-22T05:35:58.401027",null,157,[],{"repoUrl":28,"stars":27,"forks":31,"topics":34,"description":35},[],"Official, AWS-supported MCP servers, skills, and plugins to help AI agents build on AWS","https:\u002F\u002Fgithub.com\u002Faws\u002Fagent-toolkit-for-aws\u002Ftree\u002FHEAD\u002Fskills\u002Fcore-skills\u002Faws-serverless","---\nname: aws-serverless\ndescription: Builds, deploys, manages, debugs, configures, and optimizes serverless applications on AWS using Lambda, API Gateway, Step Functions, EventBridge, and SAM\u002FCDK. Covers cold starts, CORS debugging, event source mappings, troubleshooting, concurrency, SnapStart, Powertools, function URLs, EventBridge Scheduler, Lambda layers, and production readiness. Triggers on mentions of Lambda, API Gateway, Step Functions, SAM templates, CDK serverless stacks, DynamoDB stream triggers, SQS event sources, cold starts, timeouts, 502\u002F504 errors, throttling, concurrency, CORS, Powertools, or any event-driven architecture on AWS, even without the word \"serverless.\" Does not apply to EC2, ECS\u002FFargate containers, or Amplify hosting.\nversion: 1\n---\n\n# AWS Serverless\n\nDomain expertise for building serverless applications on AWS: Lambda, API Gateway, Step Functions, EventBridge, event source mappings, concurrency, cold starts, deployment, and troubleshooting.\n\n**Works best with** the [AWS MCP server](https:\u002F\u002Fdocs.aws.amazon.com\u002Faws-mcp\u002F) — run CLI commands, query CloudWatch, validate configs directly. All guidance also works with standard AWS CLI access.\n\n## Specialized skills — check these first\n\nThese cover capabilities and procedures the general references below do **not**. Several are specialized features or step-by-step tested procedures you would otherwise miss. Route to the matching skill before falling back to the references.\n\n### Advanced Lambda compute (easy to overlook)\n\n| Use this skill | When the workload involves |\n|---|---|\n| **aws-lambda-microvms** | Strong tenant isolation, sandboxed\u002Funtrusted code execution (AI agent code sandboxes, REPLs, notebooks, CI runners), long-lived sessions, suspend\u002Fresume with preserved state, port-listening servers (gRPC, WebSocket, custom TCP), Firecracker microVMs, snapshot-resumable compute, up to 8-hour lifetimes |\n| **aws-lambda-durable-functions** | Durable execution, checkpoint-and-replay, long-running multi-step workflows written as plain code (TS\u002FPython\u002FJava), automatic state persistence, saga pattern in code, human-in-the-loop callbacks, executions up to 1 year, `context.step`\u002F`context.wait`\u002F`context.invoke`, `withDurableExecution`, `durable-execution-sdk` |\n| **aws-lambda-managed-instances** | Lambda Managed Instances (LMI), capacity providers, EC2-backed Lambda, steady high-volume traffic (50M+ req\u002Fmo) wanting Savings Plans \u002F Reserved Instance pricing, `PerExecutionEnvironmentMaxConcurrency`, `CapacityProviderConfig`, multi-concurrent execution environments |\n\n### Step-by-step task procedures (tested CLI SOPs)\n\n| Use this skill | For the task |\n|---|---|\n| **connecting-lambda-to-api-gateway** | Wire an existing Lambda to a new REST\u002FHTTP API: proxy integration, permissions, CORS, throttling, access logging, deployment |\n| **connecting-lambda-to-dynamodb** | Connect Lambda to DynamoDB: IAM execution role, read\u002Fwrite permissions, stream event source mapping |\n| **creating-api-gateway-stage** | Create an API Gateway stage with CloudWatch logging, X-Ray tracing, throttling, WAF association, and authorization |\n| **deploying-custom-domain-rest-api** | Deploy a Regional REST API with custom domain: ACM cert, Lambda backend, request authorizer, base path mapping, Route 53 DNS |\n| **debugging-lambda-timeouts** | Systematically diagnose a timing-out Lambda: config, CloudWatch logs\u002Fmetrics, VPC, cold starts, memory, downstream calls |\n| **processing-s3-uploads-with-step-functions** | Deploy an event-driven workflow: S3 upload → EventBridge → Step Functions → Lambda (small files) or Fargate (large files), with VPC\u002FECR\u002FECS\u002FIAM |\n\n## Routing (general references in this skill)\n\n| User need | Read |\n|-----------|------|\n| Building a new serverless app — pattern selection | [architecture.md](references\u002Farchitecture.md) |\n| Lambda config, cold starts, SnapStart, memory, VPC, layers, Function URLs | [lambda.md](references\u002Flambda.md) |\n| Concurrency (reserved, provisioned, ESM controls) | [concurrency.md](references\u002Fconcurrency.md) |\n| Event sources (SQS, DynamoDB Streams, SNS, Kinesis), filtering, batch failures | [event-sources.md](references\u002Fevent-sources.md) |\n| Step Functions, EventBridge rules\u002Fpipes\u002Fscheduler | [orchestration.md](references\u002Forchestration.md) |\n| API Gateway quotas, authorizers, WebSocket | [api-gateway.md](references\u002Fapi-gateway.md) |\n| SAM\u002FCDK resource types and fast iteration | [deployment.md](references\u002Fdeployment.md) |\n| Production readiness, observability, anti-patterns | [production.md](references\u002Fproduction.md) |\n| Debugging an error (exact string → cause → fix) | [troubleshooting.md](references\u002Ftroubleshooting.md) |\n| Powertools handler template | [powertools-handler.py](assets\u002Fpowertools-handler.py) |\n\n**Note:** Reference files contain specific runtime versions, quotas, and feature matrices that change. When precision matters (production, runtime choice, quotas), confirm against current AWS documentation. The references focus on values and gotchas that are easy to get wrong — not on basics.\n",{"data":39,"body":41},{"name":4,"description":6,"version":40},1,{"type":42,"children":43},"root",[44,52,58,80,87,99,106,234,240,357,363,555],{"type":45,"tag":46,"props":47,"children":48},"element","h1",{"id":4},[49],{"type":50,"value":51},"text","AWS Serverless",{"type":45,"tag":53,"props":54,"children":55},"p",{},[56],{"type":50,"value":57},"Domain expertise for building serverless applications on AWS: Lambda, API Gateway, Step Functions, EventBridge, event source mappings, concurrency, cold starts, deployment, and troubleshooting.",{"type":45,"tag":53,"props":59,"children":60},{},[61,67,69,78],{"type":45,"tag":62,"props":63,"children":64},"strong",{},[65],{"type":50,"value":66},"Works best with",{"type":50,"value":68}," the ",{"type":45,"tag":70,"props":71,"children":75},"a",{"href":72,"rel":73},"https:\u002F\u002Fdocs.aws.amazon.com\u002Faws-mcp\u002F",[74],"nofollow",[76],{"type":50,"value":77},"AWS MCP server",{"type":50,"value":79}," — run CLI commands, query CloudWatch, validate configs directly. All guidance also works with standard AWS CLI access.",{"type":45,"tag":81,"props":82,"children":84},"h2",{"id":83},"specialized-skills-check-these-first",[85],{"type":50,"value":86},"Specialized skills — check these first",{"type":45,"tag":53,"props":88,"children":89},{},[90,92,97],{"type":50,"value":91},"These cover capabilities and procedures the general references below do ",{"type":45,"tag":62,"props":93,"children":94},{},[95],{"type":50,"value":96},"not",{"type":50,"value":98},". Several are specialized features or step-by-step tested procedures you would otherwise miss. Route to the matching skill before falling back to the references.",{"type":45,"tag":100,"props":101,"children":103},"h3",{"id":102},"advanced-lambda-compute-easy-to-overlook",[104],{"type":50,"value":105},"Advanced Lambda compute (easy to overlook)",{"type":45,"tag":107,"props":108,"children":109},"table",{},[110,129],{"type":45,"tag":111,"props":112,"children":113},"thead",{},[114],{"type":45,"tag":115,"props":116,"children":117},"tr",{},[118,124],{"type":45,"tag":119,"props":120,"children":121},"th",{},[122],{"type":50,"value":123},"Use this skill",{"type":45,"tag":119,"props":125,"children":126},{},[127],{"type":50,"value":128},"When the workload involves",{"type":45,"tag":130,"props":131,"children":132},"tbody",{},[133,150,203],{"type":45,"tag":115,"props":134,"children":135},{},[136,145],{"type":45,"tag":137,"props":138,"children":139},"td",{},[140],{"type":45,"tag":62,"props":141,"children":142},{},[143],{"type":50,"value":144},"aws-lambda-microvms",{"type":45,"tag":137,"props":146,"children":147},{},[148],{"type":50,"value":149},"Strong tenant isolation, sandboxed\u002Funtrusted code execution (AI agent code sandboxes, REPLs, notebooks, CI runners), long-lived sessions, suspend\u002Fresume with preserved state, port-listening servers (gRPC, WebSocket, custom TCP), Firecracker microVMs, snapshot-resumable compute, up to 8-hour lifetimes",{"type":45,"tag":115,"props":151,"children":152},{},[153,161],{"type":45,"tag":137,"props":154,"children":155},{},[156],{"type":45,"tag":62,"props":157,"children":158},{},[159],{"type":50,"value":160},"aws-lambda-durable-functions",{"type":45,"tag":137,"props":162,"children":163},{},[164,166,173,175,181,182,188,190,196,197],{"type":50,"value":165},"Durable execution, checkpoint-and-replay, long-running multi-step workflows written as plain code (TS\u002FPython\u002FJava), automatic state persistence, saga pattern in code, human-in-the-loop callbacks, executions up to 1 year, ",{"type":45,"tag":167,"props":168,"children":170},"code",{"className":169},[],[171],{"type":50,"value":172},"context.step",{"type":50,"value":174},"\u002F",{"type":45,"tag":167,"props":176,"children":178},{"className":177},[],[179],{"type":50,"value":180},"context.wait",{"type":50,"value":174},{"type":45,"tag":167,"props":183,"children":185},{"className":184},[],[186],{"type":50,"value":187},"context.invoke",{"type":50,"value":189},", ",{"type":45,"tag":167,"props":191,"children":193},{"className":192},[],[194],{"type":50,"value":195},"withDurableExecution",{"type":50,"value":189},{"type":45,"tag":167,"props":198,"children":200},{"className":199},[],[201],{"type":50,"value":202},"durable-execution-sdk",{"type":45,"tag":115,"props":204,"children":205},{},[206,214],{"type":45,"tag":137,"props":207,"children":208},{},[209],{"type":45,"tag":62,"props":210,"children":211},{},[212],{"type":50,"value":213},"aws-lambda-managed-instances",{"type":45,"tag":137,"props":215,"children":216},{},[217,219,225,226,232],{"type":50,"value":218},"Lambda Managed Instances (LMI), capacity providers, EC2-backed Lambda, steady high-volume traffic (50M+ req\u002Fmo) wanting Savings Plans \u002F Reserved Instance pricing, ",{"type":45,"tag":167,"props":220,"children":222},{"className":221},[],[223],{"type":50,"value":224},"PerExecutionEnvironmentMaxConcurrency",{"type":50,"value":189},{"type":45,"tag":167,"props":227,"children":229},{"className":228},[],[230],{"type":50,"value":231},"CapacityProviderConfig",{"type":50,"value":233},", multi-concurrent execution environments",{"type":45,"tag":100,"props":235,"children":237},{"id":236},"step-by-step-task-procedures-tested-cli-sops",[238],{"type":50,"value":239},"Step-by-step task procedures (tested CLI SOPs)",{"type":45,"tag":107,"props":241,"children":242},{},[243,258],{"type":45,"tag":111,"props":244,"children":245},{},[246],{"type":45,"tag":115,"props":247,"children":248},{},[249,253],{"type":45,"tag":119,"props":250,"children":251},{},[252],{"type":50,"value":123},{"type":45,"tag":119,"props":254,"children":255},{},[256],{"type":50,"value":257},"For the task",{"type":45,"tag":130,"props":259,"children":260},{},[261,277,293,309,325,341],{"type":45,"tag":115,"props":262,"children":263},{},[264,272],{"type":45,"tag":137,"props":265,"children":266},{},[267],{"type":45,"tag":62,"props":268,"children":269},{},[270],{"type":50,"value":271},"connecting-lambda-to-api-gateway",{"type":45,"tag":137,"props":273,"children":274},{},[275],{"type":50,"value":276},"Wire an existing Lambda to a new REST\u002FHTTP API: proxy integration, permissions, CORS, throttling, access logging, deployment",{"type":45,"tag":115,"props":278,"children":279},{},[280,288],{"type":45,"tag":137,"props":281,"children":282},{},[283],{"type":45,"tag":62,"props":284,"children":285},{},[286],{"type":50,"value":287},"connecting-lambda-to-dynamodb",{"type":45,"tag":137,"props":289,"children":290},{},[291],{"type":50,"value":292},"Connect Lambda to DynamoDB: IAM execution role, read\u002Fwrite permissions, stream event source mapping",{"type":45,"tag":115,"props":294,"children":295},{},[296,304],{"type":45,"tag":137,"props":297,"children":298},{},[299],{"type":45,"tag":62,"props":300,"children":301},{},[302],{"type":50,"value":303},"creating-api-gateway-stage",{"type":45,"tag":137,"props":305,"children":306},{},[307],{"type":50,"value":308},"Create an API Gateway stage with CloudWatch logging, X-Ray tracing, throttling, WAF association, and authorization",{"type":45,"tag":115,"props":310,"children":311},{},[312,320],{"type":45,"tag":137,"props":313,"children":314},{},[315],{"type":45,"tag":62,"props":316,"children":317},{},[318],{"type":50,"value":319},"deploying-custom-domain-rest-api",{"type":45,"tag":137,"props":321,"children":322},{},[323],{"type":50,"value":324},"Deploy a Regional REST API with custom domain: ACM cert, Lambda backend, request authorizer, base path mapping, Route 53 DNS",{"type":45,"tag":115,"props":326,"children":327},{},[328,336],{"type":45,"tag":137,"props":329,"children":330},{},[331],{"type":45,"tag":62,"props":332,"children":333},{},[334],{"type":50,"value":335},"debugging-lambda-timeouts",{"type":45,"tag":137,"props":337,"children":338},{},[339],{"type":50,"value":340},"Systematically diagnose a timing-out Lambda: config, CloudWatch logs\u002Fmetrics, VPC, cold starts, memory, downstream calls",{"type":45,"tag":115,"props":342,"children":343},{},[344,352],{"type":45,"tag":137,"props":345,"children":346},{},[347],{"type":45,"tag":62,"props":348,"children":349},{},[350],{"type":50,"value":351},"processing-s3-uploads-with-step-functions",{"type":45,"tag":137,"props":353,"children":354},{},[355],{"type":50,"value":356},"Deploy an event-driven workflow: S3 upload → EventBridge → Step Functions → Lambda (small files) or Fargate (large files), with VPC\u002FECR\u002FECS\u002FIAM",{"type":45,"tag":81,"props":358,"children":360},{"id":359},"routing-general-references-in-this-skill",[361],{"type":50,"value":362},"Routing (general references in this skill)",{"type":45,"tag":107,"props":364,"children":365},{},[366,382],{"type":45,"tag":111,"props":367,"children":368},{},[369],{"type":45,"tag":115,"props":370,"children":371},{},[372,377],{"type":45,"tag":119,"props":373,"children":374},{},[375],{"type":50,"value":376},"User need",{"type":45,"tag":119,"props":378,"children":379},{},[380],{"type":50,"value":381},"Read",{"type":45,"tag":130,"props":383,"children":384},{},[385,402,419,436,453,470,487,504,521,538],{"type":45,"tag":115,"props":386,"children":387},{},[388,393],{"type":45,"tag":137,"props":389,"children":390},{},[391],{"type":50,"value":392},"Building a new serverless app — pattern selection",{"type":45,"tag":137,"props":394,"children":395},{},[396],{"type":45,"tag":70,"props":397,"children":399},{"href":398},"references\u002Farchitecture.md",[400],{"type":50,"value":401},"architecture.md",{"type":45,"tag":115,"props":403,"children":404},{},[405,410],{"type":45,"tag":137,"props":406,"children":407},{},[408],{"type":50,"value":409},"Lambda config, cold starts, SnapStart, memory, VPC, layers, Function URLs",{"type":45,"tag":137,"props":411,"children":412},{},[413],{"type":45,"tag":70,"props":414,"children":416},{"href":415},"references\u002Flambda.md",[417],{"type":50,"value":418},"lambda.md",{"type":45,"tag":115,"props":420,"children":421},{},[422,427],{"type":45,"tag":137,"props":423,"children":424},{},[425],{"type":50,"value":426},"Concurrency (reserved, provisioned, ESM controls)",{"type":45,"tag":137,"props":428,"children":429},{},[430],{"type":45,"tag":70,"props":431,"children":433},{"href":432},"references\u002Fconcurrency.md",[434],{"type":50,"value":435},"concurrency.md",{"type":45,"tag":115,"props":437,"children":438},{},[439,444],{"type":45,"tag":137,"props":440,"children":441},{},[442],{"type":50,"value":443},"Event sources (SQS, DynamoDB Streams, SNS, Kinesis), filtering, batch failures",{"type":45,"tag":137,"props":445,"children":446},{},[447],{"type":45,"tag":70,"props":448,"children":450},{"href":449},"references\u002Fevent-sources.md",[451],{"type":50,"value":452},"event-sources.md",{"type":45,"tag":115,"props":454,"children":455},{},[456,461],{"type":45,"tag":137,"props":457,"children":458},{},[459],{"type":50,"value":460},"Step Functions, EventBridge rules\u002Fpipes\u002Fscheduler",{"type":45,"tag":137,"props":462,"children":463},{},[464],{"type":45,"tag":70,"props":465,"children":467},{"href":466},"references\u002Forchestration.md",[468],{"type":50,"value":469},"orchestration.md",{"type":45,"tag":115,"props":471,"children":472},{},[473,478],{"type":45,"tag":137,"props":474,"children":475},{},[476],{"type":50,"value":477},"API Gateway quotas, authorizers, WebSocket",{"type":45,"tag":137,"props":479,"children":480},{},[481],{"type":45,"tag":70,"props":482,"children":484},{"href":483},"references\u002Fapi-gateway.md",[485],{"type":50,"value":486},"api-gateway.md",{"type":45,"tag":115,"props":488,"children":489},{},[490,495],{"type":45,"tag":137,"props":491,"children":492},{},[493],{"type":50,"value":494},"SAM\u002FCDK resource types and fast iteration",{"type":45,"tag":137,"props":496,"children":497},{},[498],{"type":45,"tag":70,"props":499,"children":501},{"href":500},"references\u002Fdeployment.md",[502],{"type":50,"value":503},"deployment.md",{"type":45,"tag":115,"props":505,"children":506},{},[507,512],{"type":45,"tag":137,"props":508,"children":509},{},[510],{"type":50,"value":511},"Production readiness, observability, anti-patterns",{"type":45,"tag":137,"props":513,"children":514},{},[515],{"type":45,"tag":70,"props":516,"children":518},{"href":517},"references\u002Fproduction.md",[519],{"type":50,"value":520},"production.md",{"type":45,"tag":115,"props":522,"children":523},{},[524,529],{"type":45,"tag":137,"props":525,"children":526},{},[527],{"type":50,"value":528},"Debugging an error (exact string → cause → fix)",{"type":45,"tag":137,"props":530,"children":531},{},[532],{"type":45,"tag":70,"props":533,"children":535},{"href":534},"references\u002Ftroubleshooting.md",[536],{"type":50,"value":537},"troubleshooting.md",{"type":45,"tag":115,"props":539,"children":540},{},[541,546],{"type":45,"tag":137,"props":542,"children":543},{},[544],{"type":50,"value":545},"Powertools handler template",{"type":45,"tag":137,"props":547,"children":548},{},[549],{"type":45,"tag":70,"props":550,"children":552},{"href":551},"assets\u002Fpowertools-handler.py",[553],{"type":50,"value":554},"powertools-handler.py",{"type":45,"tag":53,"props":556,"children":557},{},[558,563],{"type":45,"tag":62,"props":559,"children":560},{},[561],{"type":50,"value":562},"Note:",{"type":50,"value":564}," Reference files contain specific runtime versions, quotas, and feature matrices that change. When precision matters (production, runtime choice, quotas), confirm against current AWS documentation. The references focus on values and gotchas that are easy to get wrong — not on basics.",{"items":566,"total":664},[567,584,597,610,623,633,648],{"slug":568,"name":568,"fn":569,"description":570,"org":571,"tags":572,"stars":27,"repoUrl":28,"updatedAt":583},"agents-build","add capabilities to existing agent projects","Use when adding capabilities to an existing agent project — memory, app integration, VPC, multi-agent, migration, model changes, browser, code interpreter, or resource removal. Triggers on: \"add memory\", \"remember across sessions\", \"call agent from app\", \"invoke agent from code\", \"auth to call agent\", \"streaming responses\", \"VPC\", \"VPC connectivity\", \"VPC error\", \"can't reach from VPC\", \"multi-agent\", \"A2A\", \"A2A auth\", \"orchestrator not delegating\", \"specialist not called\", \"migrate Bedrock Agent\", \"after import\", \"migration issue\", \"framework for migration\", \"change model\", \"browser tool\", \"code interpreter\", \"delete agent\", \"tear down\", \"agentcore remove\", \"cross-account memory\", \"resource-based policy on memory\", \"pay for x402 content\", \"402 Payment Required\", \"microtransactions\", \"paid API or tool\". Not for connecting to external APIs via Gateway — use agents-connect. Not for scaffolding a new project — use agents-get-started. Not for CLI\u002Fdev server errors — use agents-debug. Strands vs LangGraph in a migration context routes here.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[573,576,579,580],{"name":574,"slug":575,"type":15},"Agents","agents",{"name":577,"slug":578,"type":15},"Automation","automation",{"name":23,"slug":8,"type":15},{"name":581,"slug":582,"type":15},"Engineering","engineering","2026-07-12T08:42:53.812877",{"slug":585,"name":585,"fn":586,"description":587,"org":588,"tags":589,"stars":27,"repoUrl":28,"updatedAt":596},"agents-connect","connect agents to external services","Use when connecting your agent to external APIs, tools, or services via Gateway, or restricting tool access with Cedar policies. Handles gateway setup, target types, outbound auth (OAuth, API key, IAM), credentials, and Cedar policy authoring. Triggers on: \"connect to API\", \"add gateway\", \"connect to MCP server\", \"Lambda tools\", \"OpenAPI\", \"gateway target\", \"Cedar policy\", \"restrict tools\", \"policy engine\", \"gateway auth error\", \"store API key\", \"outbound credential\", \"env var API key\", \"API key None after deploy\", \"credential not available after deploy\", \"should this be a gateway target\", \"give my agent tools\", \"add tools to agent\". Not for inbound auth (who can call your agent) — use agents-harden. Not for debugging agent behavior — use agents-debug. Not for VPC networking errors (agent can't reach APIs due to VPC) — use agents-build. Not for creating or hosting a new MCP server project — use agents-get-started.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[590,591,592,595],{"name":574,"slug":575,"type":15},{"name":17,"slug":18,"type":15},{"name":593,"slug":594,"type":15},"Authentication","authentication",{"name":23,"slug":8,"type":15},"2026-07-16T06:00:38.866147",{"slug":598,"name":598,"fn":599,"description":600,"org":601,"tags":602,"stars":27,"repoUrl":28,"updatedAt":609},"agents-debug","debug agent and environment issues","Use when your agent or environment is broken — wrong answers, errors, timeouts, tool failures, or CLI issues. Reads traces and logs to diagnose root causes. Also checks prerequisites when the CLI itself isn't working. Triggers on: \"agent not working\", \"wrong answer\", \"agent error\", \"tool call failing\", \"debug agent\", \"check logs\", \"read traces\", \"broken\", \"500 error\", \"424 error\", \"model access denied\", \"command not found\", \"stuck in DELETING\", \"maxVms exceeded\", \"cold start diagnosis\", \"cold start slow\", \"agentcore create error\", \"create failed\", \"exit code 7\", \"connection refused local dev\". Not for deploy failures — use agents-deploy. Not for performance tuning without errors — use agents-optimize. Not for VPC configuration — use agents-build. Not for observability setup or missing logs — use agents-optimize.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[603,604,605,606],{"name":574,"slug":575,"type":15},{"name":23,"slug":8,"type":15},{"name":25,"slug":26,"type":15},{"name":607,"slug":608,"type":15},"Observability","observability","2026-07-16T06:00:44.679093",{"slug":611,"name":611,"fn":612,"description":613,"org":614,"tags":615,"stars":27,"repoUrl":28,"updatedAt":622},"agents-deploy","deploy AI agents to AWS","Use when deploying your agent to AWS, or when a deploy has failed. Handles pre-flight validation, CDK\u002FIAM\u002Fquota error diagnosis, version management, rollback, and canary deployments. Triggers on: \"deploy my agent\", \"agentcore deploy\", \"deploy failed\", \"CDK error\", \"rollback\", \"canary deploy\", \"pin version\", \"redeploy\", \"deploy stuck\". Not for production hardening — use agents-harden. Not for adding capabilities before deploy — use agents-build or agents-connect. Not for VPC configuration errors — use agents-build.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[616,617,618,621],{"name":574,"slug":575,"type":15},{"name":23,"slug":8,"type":15},{"name":619,"slug":620,"type":15},"CI\u002FCD","ci-cd",{"name":13,"slug":14,"type":15},"2026-07-12T08:42:55.059577",{"slug":624,"name":624,"fn":625,"description":626,"org":627,"tags":628,"stars":27,"repoUrl":28,"updatedAt":632},"agents-get-started","scaffold and deploy new agent projects","Use when a developer wants to create a new agent project or get started with AgentCore. Handles framework selection, project scaffolding, first deploy, and first invocation. Triggers on: \"build an agent\", \"create an agent\", \"get started\", \"new project\", \"agentcore create\", \"which framework\", \"Strands vs LangGraph\", \"hello world agent\", \"first agent\", \"create MCP server\", \"host MCP server\", \"agentcore dev\", \"dev server\", \"what port\", \"local development\". Not for adding capabilities to existing projects — use agents-build or agents-connect. Strands vs LangGraph in a migration context routes to agents-build, not here. Connecting to an existing MCP server routes to agents-connect, not here.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[629,630,631],{"name":574,"slug":575,"type":15},{"name":23,"slug":8,"type":15},{"name":13,"slug":14,"type":15},"2026-07-12T08:42:51.963247",{"slug":634,"name":634,"fn":635,"description":636,"org":637,"tags":638,"stars":27,"repoUrl":28,"updatedAt":647},"agents-harden","harden agents for production","Use when preparing your agent for production — IAM scoping, inbound auth (JWT, SigV4), secrets management, cold start optimization, session lifecycle, rate limiting, input validation, and quota guidance. Triggers on: \"production checklist\", \"harden agent\", \"production ready\", \"secure agent\", \"inbound auth\", \"going live\", \"cold start optimization\", \"session lifecycle\", \"StopRuntimeSession\", \"quota\", \"throttling\", \"maxVms\", \"rate limit\", \"security audit of outbound API calls\", \"gateway target audit for production\", \"restrict who can call\", \"lock down endpoint\", \"only our app can call\". Not for Cedar tool-restriction policies — use agents-connect. Not for quality measurement — use agents-optimize. Not for outbound credential storage or API key wiring — use agents-connect. Not for A2A agent-to-agent auth — use agents-build. Cold start observation and diagnosis (not optimization) routes to agents-debug.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[639,640,641,644],{"name":574,"slug":575,"type":15},{"name":23,"slug":8,"type":15},{"name":642,"slug":643,"type":15},"Best Practices","best-practices",{"name":645,"slug":646,"type":15},"Security","security","2026-07-16T06:00:42.174705",{"slug":649,"name":649,"fn":650,"description":651,"org":652,"tags":653,"stars":27,"repoUrl":28,"updatedAt":663},"agents-optimize","optimize agent quality and performance","Use when measuring or improving agent quality and performance — set up evaluators, online monitoring, CI\u002FCD quality gates, observability, or cost optimization. Triggers on: \"evaluate my agent\", \"add evaluator\", \"measure quality\", \"quality gate\", \"run evals\", \"agent too slow\", \"why is it slow\", \"reduce latency\", \"set up observability\", \"CloudWatch dashboard\", \"how much does my agent cost\", \"cost optimization\", \"logs not showing up\", \"logs missing\", \"spans not found\", \"eval failing\", \"eval error\", \"dev traces\", \"local traces\", \"agentcore dev traces\", \"traces to CloudWatch\". Not for debugging errors or crashes — use agents-debug. Slow but correct routes here; broken routes to debug.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[654,655,656,659,660],{"name":574,"slug":575,"type":15},{"name":23,"slug":8,"type":15},{"name":657,"slug":658,"type":15},"Evals","evals",{"name":607,"slug":608,"type":15},{"name":661,"slug":662,"type":15},"Performance","performance","2026-07-12T08:42:56.488105",114,{"items":666,"total":781},[667,674,681,688,695,701,708,716,731,744,756,771],{"slug":568,"name":568,"fn":569,"description":570,"org":668,"tags":669,"stars":27,"repoUrl":28,"updatedAt":583},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[670,671,672,673],{"name":574,"slug":575,"type":15},{"name":577,"slug":578,"type":15},{"name":23,"slug":8,"type":15},{"name":581,"slug":582,"type":15},{"slug":585,"name":585,"fn":586,"description":587,"org":675,"tags":676,"stars":27,"repoUrl":28,"updatedAt":596},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[677,678,679,680],{"name":574,"slug":575,"type":15},{"name":17,"slug":18,"type":15},{"name":593,"slug":594,"type":15},{"name":23,"slug":8,"type":15},{"slug":598,"name":598,"fn":599,"description":600,"org":682,"tags":683,"stars":27,"repoUrl":28,"updatedAt":609},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[684,685,686,687],{"name":574,"slug":575,"type":15},{"name":23,"slug":8,"type":15},{"name":25,"slug":26,"type":15},{"name":607,"slug":608,"type":15},{"slug":611,"name":611,"fn":612,"description":613,"org":689,"tags":690,"stars":27,"repoUrl":28,"updatedAt":622},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[691,692,693,694],{"name":574,"slug":575,"type":15},{"name":23,"slug":8,"type":15},{"name":619,"slug":620,"type":15},{"name":13,"slug":14,"type":15},{"slug":624,"name":624,"fn":625,"description":626,"org":696,"tags":697,"stars":27,"repoUrl":28,"updatedAt":632},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[698,699,700],{"name":574,"slug":575,"type":15},{"name":23,"slug":8,"type":15},{"name":13,"slug":14,"type":15},{"slug":634,"name":634,"fn":635,"description":636,"org":702,"tags":703,"stars":27,"repoUrl":28,"updatedAt":647},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[704,705,706,707],{"name":574,"slug":575,"type":15},{"name":23,"slug":8,"type":15},{"name":642,"slug":643,"type":15},{"name":645,"slug":646,"type":15},{"slug":649,"name":649,"fn":650,"description":651,"org":709,"tags":710,"stars":27,"repoUrl":28,"updatedAt":663},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[711,712,713,714,715],{"name":574,"slug":575,"type":15},{"name":23,"slug":8,"type":15},{"name":657,"slug":658,"type":15},{"name":607,"slug":608,"type":15},{"name":661,"slug":662,"type":15},{"slug":717,"name":717,"fn":718,"description":719,"org":720,"tags":721,"stars":27,"repoUrl":28,"updatedAt":730},"amazon-aurora-mysql","manage Amazon Aurora MySQL clusters","Amazon Aurora MySQL — creates, modifies, and advises on Aurora MySQL clusters specifically (MySQL-compatible engine, Aurora serverless, parallel query). Trigger for Aurora MySQL cluster operations, ACU sizing, I\u002FO-Optimized storage, commitment pricing, or MySQL upgrade planning. Aurora MySQL uses full (VPC-based) configuration — express configuration is PostgreSQL-only. For Aurora PostgreSQL, use amazon-aurora-postgresql instead. Contains safety guardrails and response templates that override defaults.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[722,723,726,729],{"name":23,"slug":8,"type":15},{"name":724,"slug":725,"type":15},"Database","database",{"name":727,"slug":728,"type":15},"MySQL","mysql",{"name":20,"slug":21,"type":15},"2026-07-12T08:43:13.27939",{"slug":732,"name":732,"fn":733,"description":734,"org":735,"tags":736,"stars":27,"repoUrl":28,"updatedAt":743},"amazon-aurora-postgresql","configure Amazon Aurora PostgreSQL clusters","Amazon Aurora PostgreSQL — creates, modifies, and advises on Aurora PostgreSQL clusters specifically (PostgreSQL-compatible engine, Aurora serverless, express configuration, pgvector, Babelfish). Trigger for Aurora PostgreSQL cluster operations, express-configuration quick-start, ACU sizing, I\u002FO-Optimized storage, commitment pricing, or PostgreSQL upgrade planning. For Aurora MySQL, use amazon-aurora-mysql instead. Contains safety guardrails, express-first routing, and response templates that override defaults.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[737,738,739,742],{"name":23,"slug":8,"type":15},{"name":724,"slug":725,"type":15},{"name":740,"slug":741,"type":15},"PostgreSQL","postgresql",{"name":20,"slug":21,"type":15},"2026-07-16T06:00:34.789624",{"slug":745,"name":745,"fn":746,"description":747,"org":748,"tags":749,"stars":27,"repoUrl":28,"updatedAt":755},"amazon-bedrock","build generative AI apps with Amazon Bedrock","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, migrating\u002Fporting\u002Fconverting a Bedrock Agent (including inline agents) to an AgentCore Harness, 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. Also covers AgentCore Payments setup (x402, microtransactions, Payment Manager, Connector, Instrument, Coinbase CDP, Stripe Privy, 402 Payment Required, pay for content, paid endpoint, agent payments). NOT for custom model training, Rekognition, or Comprehend.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[750,751,752],{"name":574,"slug":575,"type":15},{"name":23,"slug":8,"type":15},{"name":753,"slug":754,"type":15},"LLM","llm","2026-07-25T05:30:35.20899",{"slug":757,"name":757,"fn":758,"description":759,"org":760,"tags":761,"stars":27,"repoUrl":28,"updatedAt":770},"amazon-documentdb","manage Amazon DocumentDB clusters","Manages Amazon DocumentDB end-to-end — serverless-on-8.0 cluster setup, TLS\u002FVPC\u002Fdriver config, flexible-schema and vector-search data modeling, MongoDB compatibility assessment, DMS-based migration, slow-query diagnosis, major version upgrades (4.0→5.0→8.0), Well-Architected reviews (41-check wa_review.py), cost estimation, and security hardening. Retrieve for every DocumentDB question and when the user asks to set up or migrate MongoDB to AWS — DocumentDB is AWS's MongoDB-compatible managed database. Triggers: JSON document store, document database, MongoDB on AWS, Nested fields, Lambda cannot connect, TLS handshake, VPC port 27017, IAM auth, Secrets Manager, encryption at rest, $graphLookup, flexible schema, COLLSCAN, compound index, DMS migration, CDC cutover, $vectorSearch, RAG, Global Clusters, DR replication, cost sizing, audit, health check, production-readiness.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[762,763,764,767],{"name":23,"slug":8,"type":15},{"name":724,"slug":725,"type":15},{"name":765,"slug":766,"type":15},"MongoDB","mongodb",{"name":768,"slug":769,"type":15},"NoSQL","nosql","2026-07-12T08:43:00.455878",{"slug":772,"name":772,"fn":773,"description":774,"org":775,"tags":776,"stars":27,"repoUrl":28,"updatedAt":780},"amazon-dynamodb","design and debug DynamoDB data layers","Designs, reviews, and debugs DynamoDB data layers from design axioms — enumerates access patterns, chooses partition\u002Fsort keys and GSIs, decides single-table vs. multi-table, configures Streams, Global Tables, TTL, and zero-ETL integrations to OpenSearch\u002FRedshift\u002FSageMaker Lakehouse, and produces a defensible data-layer design with a monthly cost estimate and optional live validation. Applies whenever a user is designing, reviewing, or refactoring anything backed by DynamoDB — schemas, access patterns, GSIs, single- vs. multi-table choices, Streams consumers, transactional outboxes, Global Tables, zero-ETL pipelines — even when they don't say \"axioms\" or \"design review.\" Also applies when debugging hot partitions, throttling, unbounded Scans, LWW conflicts, or surprise bills on DynamoDB workloads.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[777,778,779],{"name":23,"slug":8,"type":15},{"name":724,"slug":725,"type":15},{"name":768,"slug":769,"type":15},"2026-07-16T06:00:37.690386",115]