[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-aws-managing-amazon-kinesis-data-streams":3,"mdc--x9uh1a-key":32,"related-repo-aws-managing-amazon-kinesis-data-streams":428,"related-org-aws-managing-amazon-kinesis-data-streams":534},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":21,"repoUrl":22,"updatedAt":23,"license":24,"forks":25,"topics":26,"repo":27,"sourceUrl":30,"mdContent":31},"managing-amazon-kinesis-data-streams","manage Amazon Kinesis data streams","Operates Amazon Kinesis Data Streams (KDS). Covers streaming tables and Amazon S3 delivery - serverless, fully managed delivery from a KDS stream to Apache Iceberg tables on S3 Tables or to general-purpose S3 buckets. Includes channel setup, IAM, schemas, output key templates, CloudWatch metrics and alarms, DLQ handling, quotas, and troubleshooting. For all other KDS topics and questions, search AWS documentation and blogs instead. Triggers: Kinesis Data Streams, KDS, streaming tables, stream to S3, stream to Iceberg, stream to S3 Tables, KDS delivery, KDS channel, CreateChannel, data channel, data freshness, dead-letter queue, KDS lakehouse, serverless Kinesis delivery, Firehose alternative for KDS, zero-ops Kinesis to S3. DO NOT USE for Kinesis Data Firehose, Kinesis Video Streams, or Managed Service for Apache Flink — use dedicated skills or search documentation instead.",{"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],{"name":13,"slug":14,"type":15},"Data Engineering","data-engineering","tag",{"name":17,"slug":18,"type":15},"Serverless","serverless",{"name":20,"slug":8,"type":15},"AWS",2481,"https:\u002F\u002Fgithub.com\u002Faws\u002Fagent-toolkit-for-aws","2026-09-02T07:48:05.812755",null,277,[],{"repoUrl":22,"stars":21,"forks":25,"topics":28,"description":29},[],"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\u002Fspecialized-skills\u002Fanalytics-skills\u002Fmanaging-amazon-kinesis-data-streams","---\nname: managing-amazon-kinesis-data-streams\ndescription: >-\n  Operates Amazon Kinesis Data Streams (KDS). Covers streaming tables and Amazon S3\n  delivery - serverless, fully managed delivery from a KDS stream to Apache Iceberg\n  tables on S3 Tables or to general-purpose S3 buckets. Includes channel setup, IAM,\n  schemas, output key templates, CloudWatch metrics and alarms, DLQ handling, quotas,\n  and troubleshooting. For all other KDS topics and questions, search AWS documentation\n  and blogs instead. Triggers: Kinesis Data Streams, KDS, streaming tables, stream\n  to S3, stream to Iceberg, stream to S3 Tables, KDS delivery, KDS channel, CreateChannel,\n  data channel, data freshness, dead-letter queue, KDS lakehouse, serverless Kinesis\n  delivery, Firehose alternative for KDS, zero-ops Kinesis to S3. DO NOT USE for Kinesis\n  Data Firehose, Kinesis Video Streams, or Managed Service for Apache Flink — use\n  dedicated skills or search documentation instead.\nversion: 1\n---\n\n# Amazon Kinesis Data Streams\n\n## Overview\n\nDomain expertise for Amazon Kinesis Data Streams. This skill covers **streaming tables and Amazon S3 delivery**, which provide serverless, fully managed delivery from a KDS stream directly to Apache Iceberg tables on S3 Tables or to general-purpose S3 buckets — no consumers, no Firehose, no Flink required for append-only delivery.\n\nDelivery is configured as a **channel** on a stream via `CreateChannel`. Channels consume no shard capacity and no enhanced fan-out slots, so they do not compete with existing consumers.\n\nThe AWS MCP server is recommended for executing AWS operations. When the MCP server is not available, use the AWS CLI or shell commands instead.\n\n## Which Workflow Do You Need?\n\n| Customer Intent | Reference |\n|---|---|\n| Deliver stream data to Apache Iceberg tables on S3 Tables — setup, IAM, Glue schema, type mapping, partitioning, channel lifecycle | [references\u002Fstreaming-tables.md](references\u002Fstreaming-tables.md) |\n| Deliver stream data to a general-purpose S3 bucket as objects — setup, IAM, compression, storage class, output key templates, channel lifecycle | [references\u002Fgeneral-purpose-delivery-to-s3.md](references\u002Fgeneral-purpose-delivery-to-s3.md) |\n| Build a lakehouse \u002F data lake from Kinesis; make streaming data queryable in Athena | [references\u002Fstreaming-tables.md](references\u002Fstreaming-tables.md) |\n| Zero-ops, serverless alternative to Firehose or Kinesis consumers for KDS → S3 delivery | [references\u002Fgeneral-purpose-delivery-to-s3.md](references\u002Fgeneral-purpose-delivery-to-s3.md) |\n| CloudWatch metrics and alarms, delivery logging, CloudTrail, encryption, channel states, quotas, naming rules, what can be updated | [references\u002Fmonitoring-security-and-limits.md](references\u002Fmonitoring-security-and-limits.md) |\n| Channel is ACTIVE but no data arrives; records landing in the DLQ; rising data freshness | Start with [references\u002Fmonitoring-security-and-limits.md](references\u002Fmonitoring-security-and-limits.md), then the destination-specific troubleshooting table |\n| Deliver to both S3 and S3 Tables from one stream | Supported — create one channel per destination |\n\n## Prerequisites\n\nBoth destinations require an **ON_DEMAND stream** — provisioned-mode streams are not supported. Each channel also needs an IAM service execution role trusted by `kinesis.amazonaws.com`, and a destination in the **same Region** as the stream.\n\n## Hard Limits to Check First\n\nThese rule out the feature entirely, so confirm them before designing a solution:\n\n- **Append-only** — no CDC, upserts, or deletes\n- **No schema evolution** — a schema change means deleting and recreating the channel\n- **No backfill** — only records produced after the channel is `ACTIVE` are delivered\n- **No transformations** — records are delivered as-is\n- **New table per channel** — cannot deliver into an existing Iceberg table\n- **Data freshness is 300–900 seconds** — not sub-minute\n- **Same Region only** — cross-account is supported, cross-Region is not\n\nIf any of these block the customer, recommend **Managed Service for Apache Flink** instead.\n\n## Additional Resources\n\n- [KDS Developer Guide](https:\u002F\u002Fdocs.aws.amazon.com\u002Fstreams\u002Flatest\u002Fdev\u002Fintroduction.html)\n- [KDS API Reference](https:\u002F\u002Fdocs.aws.amazon.com\u002Fkinesis\u002Flatest\u002FAPIReference\u002F)\n- [S3 Tables Developer Guide](https:\u002F\u002Fdocs.aws.amazon.com\u002FAmazonS3\u002Flatest\u002Fuserguide\u002Fs3-tables.html)\n- [Glue Schema Registry](https:\u002F\u002Fdocs.aws.amazon.com\u002Fglue\u002Flatest\u002Fdg\u002Fschema-registry.html)\n",{"data":33,"body":35},{"name":4,"description":6,"version":34},1,{"type":36,"children":37},"root",[38,47,54,68,89,94,100,239,245,272,278,283,366,378,384],{"type":39,"tag":40,"props":41,"children":43},"element","h1",{"id":42},"amazon-kinesis-data-streams",[44],{"type":45,"value":46},"text","Amazon Kinesis Data Streams",{"type":39,"tag":48,"props":49,"children":51},"h2",{"id":50},"overview",[52],{"type":45,"value":53},"Overview",{"type":39,"tag":55,"props":56,"children":57},"p",{},[58,60,66],{"type":45,"value":59},"Domain expertise for Amazon Kinesis Data Streams. This skill covers ",{"type":39,"tag":61,"props":62,"children":63},"strong",{},[64],{"type":45,"value":65},"streaming tables and Amazon S3 delivery",{"type":45,"value":67},", which provide serverless, fully managed delivery from a KDS stream directly to Apache Iceberg tables on S3 Tables or to general-purpose S3 buckets — no consumers, no Firehose, no Flink required for append-only delivery.",{"type":39,"tag":55,"props":69,"children":70},{},[71,73,78,80,87],{"type":45,"value":72},"Delivery is configured as a ",{"type":39,"tag":61,"props":74,"children":75},{},[76],{"type":45,"value":77},"channel",{"type":45,"value":79}," on a stream via ",{"type":39,"tag":81,"props":82,"children":84},"code",{"className":83},[],[85],{"type":45,"value":86},"CreateChannel",{"type":45,"value":88},". Channels consume no shard capacity and no enhanced fan-out slots, so they do not compete with existing consumers.",{"type":39,"tag":55,"props":90,"children":91},{},[92],{"type":45,"value":93},"The AWS MCP server is recommended for executing AWS operations. When the MCP server is not available, use the AWS CLI or shell commands instead.",{"type":39,"tag":48,"props":95,"children":97},{"id":96},"which-workflow-do-you-need",[98],{"type":45,"value":99},"Which Workflow Do You Need?",{"type":39,"tag":101,"props":102,"children":103},"table",{},[104,123],{"type":39,"tag":105,"props":106,"children":107},"thead",{},[108],{"type":39,"tag":109,"props":110,"children":111},"tr",{},[112,118],{"type":39,"tag":113,"props":114,"children":115},"th",{},[116],{"type":45,"value":117},"Customer Intent",{"type":39,"tag":113,"props":119,"children":120},{},[121],{"type":45,"value":122},"Reference",{"type":39,"tag":124,"props":125,"children":126},"tbody",{},[127,145,161,176,191,207,226],{"type":39,"tag":109,"props":128,"children":129},{},[130,136],{"type":39,"tag":131,"props":132,"children":133},"td",{},[134],{"type":45,"value":135},"Deliver stream data to Apache Iceberg tables on S3 Tables — setup, IAM, Glue schema, type mapping, partitioning, channel lifecycle",{"type":39,"tag":131,"props":137,"children":138},{},[139],{"type":39,"tag":140,"props":141,"children":143},"a",{"href":142},"references\u002Fstreaming-tables.md",[144],{"type":45,"value":142},{"type":39,"tag":109,"props":146,"children":147},{},[148,153],{"type":39,"tag":131,"props":149,"children":150},{},[151],{"type":45,"value":152},"Deliver stream data to a general-purpose S3 bucket as objects — setup, IAM, compression, storage class, output key templates, channel lifecycle",{"type":39,"tag":131,"props":154,"children":155},{},[156],{"type":39,"tag":140,"props":157,"children":159},{"href":158},"references\u002Fgeneral-purpose-delivery-to-s3.md",[160],{"type":45,"value":158},{"type":39,"tag":109,"props":162,"children":163},{},[164,169],{"type":39,"tag":131,"props":165,"children":166},{},[167],{"type":45,"value":168},"Build a lakehouse \u002F data lake from Kinesis; make streaming data queryable in Athena",{"type":39,"tag":131,"props":170,"children":171},{},[172],{"type":39,"tag":140,"props":173,"children":174},{"href":142},[175],{"type":45,"value":142},{"type":39,"tag":109,"props":177,"children":178},{},[179,184],{"type":39,"tag":131,"props":180,"children":181},{},[182],{"type":45,"value":183},"Zero-ops, serverless alternative to Firehose or Kinesis consumers for KDS → S3 delivery",{"type":39,"tag":131,"props":185,"children":186},{},[187],{"type":39,"tag":140,"props":188,"children":189},{"href":158},[190],{"type":45,"value":158},{"type":39,"tag":109,"props":192,"children":193},{},[194,199],{"type":39,"tag":131,"props":195,"children":196},{},[197],{"type":45,"value":198},"CloudWatch metrics and alarms, delivery logging, CloudTrail, encryption, channel states, quotas, naming rules, what can be updated",{"type":39,"tag":131,"props":200,"children":201},{},[202],{"type":39,"tag":140,"props":203,"children":205},{"href":204},"references\u002Fmonitoring-security-and-limits.md",[206],{"type":45,"value":204},{"type":39,"tag":109,"props":208,"children":209},{},[210,215],{"type":39,"tag":131,"props":211,"children":212},{},[213],{"type":45,"value":214},"Channel is ACTIVE but no data arrives; records landing in the DLQ; rising data freshness",{"type":39,"tag":131,"props":216,"children":217},{},[218,220,224],{"type":45,"value":219},"Start with ",{"type":39,"tag":140,"props":221,"children":222},{"href":204},[223],{"type":45,"value":204},{"type":45,"value":225},", then the destination-specific troubleshooting table",{"type":39,"tag":109,"props":227,"children":228},{},[229,234],{"type":39,"tag":131,"props":230,"children":231},{},[232],{"type":45,"value":233},"Deliver to both S3 and S3 Tables from one stream",{"type":39,"tag":131,"props":235,"children":236},{},[237],{"type":45,"value":238},"Supported — create one channel per destination",{"type":39,"tag":48,"props":240,"children":242},{"id":241},"prerequisites",[243],{"type":45,"value":244},"Prerequisites",{"type":39,"tag":55,"props":246,"children":247},{},[248,250,255,257,263,265,270],{"type":45,"value":249},"Both destinations require an ",{"type":39,"tag":61,"props":251,"children":252},{},[253],{"type":45,"value":254},"ON_DEMAND stream",{"type":45,"value":256}," — provisioned-mode streams are not supported. Each channel also needs an IAM service execution role trusted by ",{"type":39,"tag":81,"props":258,"children":260},{"className":259},[],[261],{"type":45,"value":262},"kinesis.amazonaws.com",{"type":45,"value":264},", and a destination in the ",{"type":39,"tag":61,"props":266,"children":267},{},[268],{"type":45,"value":269},"same Region",{"type":45,"value":271}," as the stream.",{"type":39,"tag":48,"props":273,"children":275},{"id":274},"hard-limits-to-check-first",[276],{"type":45,"value":277},"Hard Limits to Check First",{"type":39,"tag":55,"props":279,"children":280},{},[281],{"type":45,"value":282},"These rule out the feature entirely, so confirm them before designing a solution:",{"type":39,"tag":284,"props":285,"children":286},"ul",{},[287,298,308,326,336,346,356],{"type":39,"tag":288,"props":289,"children":290},"li",{},[291,296],{"type":39,"tag":61,"props":292,"children":293},{},[294],{"type":45,"value":295},"Append-only",{"type":45,"value":297}," — no CDC, upserts, or deletes",{"type":39,"tag":288,"props":299,"children":300},{},[301,306],{"type":39,"tag":61,"props":302,"children":303},{},[304],{"type":45,"value":305},"No schema evolution",{"type":45,"value":307}," — a schema change means deleting and recreating the channel",{"type":39,"tag":288,"props":309,"children":310},{},[311,316,318,324],{"type":39,"tag":61,"props":312,"children":313},{},[314],{"type":45,"value":315},"No backfill",{"type":45,"value":317}," — only records produced after the channel is ",{"type":39,"tag":81,"props":319,"children":321},{"className":320},[],[322],{"type":45,"value":323},"ACTIVE",{"type":45,"value":325}," are delivered",{"type":39,"tag":288,"props":327,"children":328},{},[329,334],{"type":39,"tag":61,"props":330,"children":331},{},[332],{"type":45,"value":333},"No transformations",{"type":45,"value":335}," — records are delivered as-is",{"type":39,"tag":288,"props":337,"children":338},{},[339,344],{"type":39,"tag":61,"props":340,"children":341},{},[342],{"type":45,"value":343},"New table per channel",{"type":45,"value":345}," — cannot deliver into an existing Iceberg table",{"type":39,"tag":288,"props":347,"children":348},{},[349,354],{"type":39,"tag":61,"props":350,"children":351},{},[352],{"type":45,"value":353},"Data freshness is 300–900 seconds",{"type":45,"value":355}," — not sub-minute",{"type":39,"tag":288,"props":357,"children":358},{},[359,364],{"type":39,"tag":61,"props":360,"children":361},{},[362],{"type":45,"value":363},"Same Region only",{"type":45,"value":365}," — cross-account is supported, cross-Region is not",{"type":39,"tag":55,"props":367,"children":368},{},[369,371,376],{"type":45,"value":370},"If any of these block the customer, recommend ",{"type":39,"tag":61,"props":372,"children":373},{},[374],{"type":45,"value":375},"Managed Service for Apache Flink",{"type":45,"value":377}," instead.",{"type":39,"tag":48,"props":379,"children":381},{"id":380},"additional-resources",[382],{"type":45,"value":383},"Additional Resources",{"type":39,"tag":284,"props":385,"children":386},{},[387,398,408,418],{"type":39,"tag":288,"props":388,"children":389},{},[390],{"type":39,"tag":140,"props":391,"children":395},{"href":392,"rel":393},"https:\u002F\u002Fdocs.aws.amazon.com\u002Fstreams\u002Flatest\u002Fdev\u002Fintroduction.html",[394],"nofollow",[396],{"type":45,"value":397},"KDS Developer Guide",{"type":39,"tag":288,"props":399,"children":400},{},[401],{"type":39,"tag":140,"props":402,"children":405},{"href":403,"rel":404},"https:\u002F\u002Fdocs.aws.amazon.com\u002Fkinesis\u002Flatest\u002FAPIReference\u002F",[394],[406],{"type":45,"value":407},"KDS API Reference",{"type":39,"tag":288,"props":409,"children":410},{},[411],{"type":39,"tag":140,"props":412,"children":415},{"href":413,"rel":414},"https:\u002F\u002Fdocs.aws.amazon.com\u002FAmazonS3\u002Flatest\u002Fuserguide\u002Fs3-tables.html",[394],[416],{"type":45,"value":417},"S3 Tables Developer Guide",{"type":39,"tag":288,"props":419,"children":420},{},[421],{"type":39,"tag":140,"props":422,"children":425},{"href":423,"rel":424},"https:\u002F\u002Fdocs.aws.amazon.com\u002Fglue\u002Flatest\u002Fdg\u002Fschema-registry.html",[394],[426],{"type":45,"value":427},"Glue Schema Registry",{"items":429,"total":533},[430,447,462,477,492,502,517],{"slug":431,"name":431,"fn":432,"description":433,"org":434,"tags":435,"stars":21,"repoUrl":22,"updatedAt":446},"agents-build","add capabilities to existing agent projects","Use to extend an existing agent project with memory, app integration, VPC, multi-agent, migration, model, browser, code interpreter, payments, or resource removal. Triggers: \"add memory\", \"remember across sessions\", \"call agent from app\", \"invoke agent from code\", \"agent auth\", \"streaming\", \"VPC\", \"VPC connectivity\", \"can't reach from VPC\", \"multi-agent\", \"A2A\", \"A2A auth\", \"orchestrator not delegating\", \"specialist not called\", \"migrate Bedrock Agent\", \"migration issue\", \"change model\", \"browser tool\", \"code interpreter\", \"delete agent\", \"tear down\", \"agentcore remove\", \"cross-account memory\", \"add payments capability to my agent\", \"wire payments plugin\", \"integrate x402 payments with the agent I'm building\", \"add MPP payments\", \"Machine Payments Protocol\". External APIs via Gateway: use agents-connect. New project: use agents-get-started. CLI\u002Fdev-server errors: use agents-debug. Runtime x402\u002FMPP payments: use agents-pay. Migration-specific Strands vs LangGraph routes here.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[436,439,442,443],{"name":437,"slug":438,"type":15},"Agents","agents",{"name":440,"slug":441,"type":15},"Automation","automation",{"name":20,"slug":8,"type":15},{"name":444,"slug":445,"type":15},"Engineering","engineering","2026-08-20T03:27:06.137661",{"slug":448,"name":448,"fn":449,"description":450,"org":451,"tags":452,"stars":21,"repoUrl":22,"updatedAt":461},"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},[453,454,457,460],{"name":437,"slug":438,"type":15},{"name":455,"slug":456,"type":15},"API Development","api-development",{"name":458,"slug":459,"type":15},"Authentication","authentication",{"name":20,"slug":8,"type":15},"2026-07-16T06:00:38.866147",{"slug":463,"name":463,"fn":464,"description":465,"org":466,"tags":467,"stars":21,"repoUrl":22,"updatedAt":476},"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},[468,469,470,473],{"name":437,"slug":438,"type":15},{"name":20,"slug":8,"type":15},{"name":471,"slug":472,"type":15},"Debugging","debugging",{"name":474,"slug":475,"type":15},"Observability","observability","2026-07-16T06:00:44.679093",{"slug":478,"name":478,"fn":479,"description":480,"org":481,"tags":482,"stars":21,"repoUrl":22,"updatedAt":491},"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},[483,484,485,488],{"name":437,"slug":438,"type":15},{"name":20,"slug":8,"type":15},{"name":486,"slug":487,"type":15},"CI\u002FCD","ci-cd",{"name":489,"slug":490,"type":15},"Deployment","deployment","2026-07-12T08:42:55.059577",{"slug":493,"name":493,"fn":494,"description":495,"org":496,"tags":497,"stars":21,"repoUrl":22,"updatedAt":501},"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},[498,499,500],{"name":437,"slug":438,"type":15},{"name":20,"slug":8,"type":15},{"name":489,"slug":490,"type":15},"2026-07-12T08:42:51.963247",{"slug":503,"name":503,"fn":504,"description":505,"org":506,"tags":507,"stars":21,"repoUrl":22,"updatedAt":516},"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},[508,509,510,513],{"name":437,"slug":438,"type":15},{"name":20,"slug":8,"type":15},{"name":511,"slug":512,"type":15},"Best Practices","best-practices",{"name":514,"slug":515,"type":15},"Security","security","2026-07-16T06:00:42.174705",{"slug":518,"name":518,"fn":519,"description":520,"org":521,"tags":522,"stars":21,"repoUrl":22,"updatedAt":532},"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},[523,524,525,528,529],{"name":437,"slug":438,"type":15},{"name":20,"slug":8,"type":15},{"name":526,"slug":527,"type":15},"Evals","evals",{"name":474,"slug":475,"type":15},{"name":530,"slug":531,"type":15},"Performance","performance","2026-07-12T08:42:56.488105",124,{"items":535,"total":653},[536,543,550,557,564,570,577,585,599,614,627,639],{"slug":431,"name":431,"fn":432,"description":433,"org":537,"tags":538,"stars":21,"repoUrl":22,"updatedAt":446},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[539,540,541,542],{"name":437,"slug":438,"type":15},{"name":440,"slug":441,"type":15},{"name":20,"slug":8,"type":15},{"name":444,"slug":445,"type":15},{"slug":448,"name":448,"fn":449,"description":450,"org":544,"tags":545,"stars":21,"repoUrl":22,"updatedAt":461},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[546,547,548,549],{"name":437,"slug":438,"type":15},{"name":455,"slug":456,"type":15},{"name":458,"slug":459,"type":15},{"name":20,"slug":8,"type":15},{"slug":463,"name":463,"fn":464,"description":465,"org":551,"tags":552,"stars":21,"repoUrl":22,"updatedAt":476},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[553,554,555,556],{"name":437,"slug":438,"type":15},{"name":20,"slug":8,"type":15},{"name":471,"slug":472,"type":15},{"name":474,"slug":475,"type":15},{"slug":478,"name":478,"fn":479,"description":480,"org":558,"tags":559,"stars":21,"repoUrl":22,"updatedAt":491},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[560,561,562,563],{"name":437,"slug":438,"type":15},{"name":20,"slug":8,"type":15},{"name":486,"slug":487,"type":15},{"name":489,"slug":490,"type":15},{"slug":493,"name":493,"fn":494,"description":495,"org":565,"tags":566,"stars":21,"repoUrl":22,"updatedAt":501},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[567,568,569],{"name":437,"slug":438,"type":15},{"name":20,"slug":8,"type":15},{"name":489,"slug":490,"type":15},{"slug":503,"name":503,"fn":504,"description":505,"org":571,"tags":572,"stars":21,"repoUrl":22,"updatedAt":516},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[573,574,575,576],{"name":437,"slug":438,"type":15},{"name":20,"slug":8,"type":15},{"name":511,"slug":512,"type":15},{"name":514,"slug":515,"type":15},{"slug":518,"name":518,"fn":519,"description":520,"org":578,"tags":579,"stars":21,"repoUrl":22,"updatedAt":532},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[580,581,582,583,584],{"name":437,"slug":438,"type":15},{"name":20,"slug":8,"type":15},{"name":526,"slug":527,"type":15},{"name":474,"slug":475,"type":15},{"name":530,"slug":531,"type":15},{"slug":586,"name":586,"fn":587,"description":588,"org":589,"tags":590,"stars":21,"repoUrl":22,"updatedAt":598},"agents-pay","handle x402 payments for agent tasks","Use when THIS agent needs to pay for x402-protected content at runtime: hitting a paywall mid-task, settling it via AgentCore Payments, and applying operator-defined spend limits. Covers payment setup, policy, session budgets, and troubleshooting. Triggers on: \"my agent hit a 402 while calling an API\", \"a tool call returned 402 Payment Required\", \"my agent needs to pay for x402-protected content\", \"let the agent pay for content, capped at $5 per session\", \"set a spend limit for the agent\", \"ProcessPayment failed\", or \"why did my agent refuse to pay\". Not for BUILDING payment capability for end users, including wallets and framework middleware; use agents-build and references\u002Fpayments.md. For non-paid APIs via Gateway use agents-connect. For inbound auth use agents-harden. For project scaffolding use agents-get-started.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[591,592,593,596],{"name":437,"slug":438,"type":15},{"name":440,"slug":441,"type":15},{"name":594,"slug":595,"type":15},"Payments","payments",{"name":597,"slug":597,"type":15},"x402","2026-08-10T04:16:31.844309",{"slug":600,"name":600,"fn":601,"description":602,"org":603,"tags":604,"stars":21,"repoUrl":22,"updatedAt":613},"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},[605,606,609,612],{"name":20,"slug":8,"type":15},{"name":607,"slug":608,"type":15},"Database","database",{"name":610,"slug":611,"type":15},"MySQL","mysql",{"name":17,"slug":18,"type":15},"2026-07-12T08:43:13.27939",{"slug":615,"name":615,"fn":616,"description":617,"org":618,"tags":619,"stars":21,"repoUrl":22,"updatedAt":626},"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},[620,621,622,625],{"name":20,"slug":8,"type":15},{"name":607,"slug":608,"type":15},{"name":623,"slug":624,"type":15},"PostgreSQL","postgresql",{"name":17,"slug":18,"type":15},"2026-07-16T06:00:34.789624",{"slug":628,"name":628,"fn":629,"description":630,"org":631,"tags":632,"stars":21,"repoUrl":22,"updatedAt":638},"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 (including the Harness managed agent loop). 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, quota health checks and throttling diagnosis, cost attribution, migrating between Claude model generations, chunking strategies, API selection (Converse vs InvokeModel), and model selection. Also covers AgentCore Payments setup (x402, microtransactions, Payment Manager, Coinbase CDP, Stripe Privy, 402 Payment Required, paid endpoint). NOT for custom model training, Rekognition, or Comprehend.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[633,634,635],{"name":437,"slug":438,"type":15},{"name":20,"slug":8,"type":15},{"name":636,"slug":637,"type":15},"LLM","llm","2026-08-07T04:38:13.03499",{"slug":640,"name":640,"fn":641,"description":642,"org":643,"tags":644,"stars":21,"repoUrl":22,"updatedAt":652},"amazon-braket","run quantum computing workflows on AWS","Runs quantum computing workflows on AWS through Amazon Braket — discovering devices (QPUs and simulators) and their availability, building gate-model circuits and analog Hamiltonian programs, submitting quantum tasks, program sets and hybrid jobs, looking up prices, and capping spend with spending limits. Applies to any request about quantum computing, quantum hardware, quantum simulation, AHS, OpenQASM, or running a quantum algorithm on AWS.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[645,646,649],{"name":20,"slug":8,"type":15},{"name":647,"slug":648,"type":15},"Quantum Computing","quantum-computing",{"name":650,"slug":651,"type":15},"Simulation","simulation","2026-08-27T13:04:17.249442",145]