[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-aws-aws-ai-ml":3,"mdc--ugi3z7-key":35,"related-org-aws-aws-ai-ml":421,"related-repo-aws-aws-ai-ml":596},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":24,"repoUrl":25,"updatedAt":26,"license":27,"forks":28,"topics":29,"repo":30,"sourceUrl":33,"mdContent":34},"aws-ai-ml","deploy and customize AI models on SageMaker","Selects, deploys, and customizes AI models on Amazon SageMaker. Fine-tuning (SFT, DPO, RLVR, RLAIF), model selection, dataset preparation, evaluation, deployment to SageMaker endpoints or Bedrock, and endpoint diagnostics. Covers the full lifecycle from planning through production. Use when fine-tuning models on SageMaker, selecting base models from SageMaker Hub, finding a model to deploy without fine-tuning, transforming datasets for training, checking data readiness, evaluating model quality, deploying to endpoints, setting up IAM roles and S3 buckets for training jobs, or managing a SageMaker Managed MLflow app. Also use to check endpoint health, diagnose failures, debug latency or errors, or view container logs and CloudWatch metrics. Covers Serverless Model Customization, Nova and OSS deployment paths, and PySDK v3 usage. NOT for Ground Truth labeling, Feature Store, or general-purpose AWS infrastructure.\n",{"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],{"name":13,"slug":14,"type":15},"Machine Learning","machine-learning","tag",{"name":17,"slug":18,"type":15},"AI","ai",{"name":20,"slug":21,"type":15},"Deployment","deployment",{"name":23,"slug":8,"type":15},"AWS",1822,"https:\u002F\u002Fgithub.com\u002Faws\u002Fagent-toolkit-for-aws","2026-08-07T05:03:42.885888",null,157,[],{"repoUrl":25,"stars":24,"forks":28,"topics":31,"description":32},[],"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-ai-ml","---\nname: aws-ai-ml\ndescription: >\n  Selects, deploys, and customizes AI models on Amazon SageMaker. Fine-tuning\n  (SFT, DPO, RLVR, RLAIF), model selection, dataset preparation, evaluation,\n  deployment to SageMaker endpoints or Bedrock, and endpoint diagnostics. Covers\n  the full lifecycle from planning through production. Use when fine-tuning\n  models on SageMaker, selecting base models from SageMaker Hub, finding a model\n  to deploy without fine-tuning, transforming datasets for training, checking\n  data readiness, evaluating model quality, deploying to endpoints, setting up\n  IAM roles and S3 buckets for training jobs, or managing a SageMaker Managed\n  MLflow app. Also use to check endpoint health, diagnose failures, debug\n  latency or errors, or view container logs and CloudWatch metrics. Covers\n  Serverless Model Customization, Nova and OSS deployment paths, and PySDK v3\n  usage. NOT for Ground Truth labeling, Feature Store, or general-purpose AWS\n  infrastructure.\nversion: 1\n---\n\n# AWS AI\u002FML Model Customization\n\nDomain expertise for fine-tuning and deploying models on Amazon SageMaker. Covers the full model customization lifecycle from planning through production deployment.\n\n## Routing\n\nMatch the user's intent to the appropriate reference folder and load only that content.\n\n| User intent | Reference | When to use |\n|-------------|-----------|-------------|\n| Plan a model customization project, discover scope of work, resume or modify a plan | [references\u002Fplanning\u002F](references\u002Fplanning\u002F) | User's request relates to model customization or deployment (fine-tuning, training, building, customizing, reviewing data, deploying or standing up a model — including selecting or deploying an off-the-shelf or base model with no training — or getting advice on approach). Always co-activate with other intents to discover full scope. Load this reference FIRST when the request matches multiple rows in this table — read its plan templates before routing to a single-action reference. |\n| Define the business problem, success criteria, or use case spec | [references\u002Fuse-case-specification\u002F](references\u002Fuse-case-specification\u002F) | User says \"define my use case\", \"capture requirements\", \"what should I decide up front\", or as default first step in any plan. Skip only if user explicitly declines. |\n| Select or change a base model | [references\u002Fmodel-selection\u002F](references\u002Fmodel-selection\u002F) | User asks which model to use, mentions a model name or family, or wants to evaluate what's available. **Always activate model-selection even for known model names** because the exact Hub model ID must be resolved. **Recommended:** route to use-case-specification first to capture requirements — this produces better filtering results. Routing to use-case-specification first is not required if user provides a specific model name\u002FID or declines. If intent is ambiguous (fine-tune vs deploy as-is), model-selection MUST confirm which path before proceeding. Base model filtering for deployment MUST go through select-for-deployment.md and its scripts for any final recommendation. |\n| Choose a fine-tuning technique (SFT, DPO, RLVR, RLAIF) | [references\u002Ffinetuning-technique\u002F](references\u002Ffinetuning-technique\u002F) | User has decided to fine-tune and needs to choose a technique, or technique needs validation against the selected model's recipes. Requires a base model to be selected first. |\n| Validate dataset quality and format | [references\u002Fdataset-evaluation\u002F](references\u002Fdataset-evaluation\u002F) | User says \"is my dataset okay\", \"check my training data\", \"I have my own data\", or before starting any fine-tuning job. |\n| Transform or convert a dataset between formats | [references\u002Fdataset-transformation\u002F](references\u002Fdataset-transformation\u002F) | User says \"transform\", \"convert\", \"reformat\", or dataset schema needs to change. Always use this rather than writing inline transformation code. |\n| Generate fine-tuning code and start training | [references\u002Ffinetuning\u002F](references\u002Ffinetuning\u002F) | User says \"start training\", \"fine-tune my model\", \"I'm ready to train\", or plan reaches the finetuning step. Supports SFT, DPO, RLVR, RLAIF trainers. |\n| Evaluate or benchmark a trained model | [references\u002Fmodel-evaluation\u002F](references\u002Fmodel-evaluation\u002F) | User says \"evaluate my model\", \"run a benchmark\", \"test model performance\", \"compare models\". Supports LLM-as-Judge and Custom Scorer. |\n| Deploy a model to endpoint or Bedrock | [references\u002Fmodel-deployment\u002F](references\u002Fmodel-deployment\u002F) | User says \"deploy my model\", \"create an endpoint\", \"make it available\". Handles Nova vs OSS deployment pathways. |\n| Set up IAM roles, S3 buckets, SDK configuration | [references\u002Fsdk-getting-started\u002F](references\u002Fsdk-getting-started\u002F) | User says \"set up\", \"getting started\", \"check my environment\", \"configure SDK\", or as first step in any plan involving SageMaker training\u002Fevaluation\u002Fdeployment. |\n| Manage project directory and artifacts | [references\u002Fdirectory-management\u002F](references\u002Fdirectory-management\u002F) | Starting a new project, resuming existing one, or when PLAN.md needs to be associated with a project directory. |\n| Set up, update, or delete a SageMaker Managed MLflow app | [references\u002Fmanage-mlflow\u002F](references\u002Fmanage-mlflow\u002F) | User says \"set up MLflow\", \"create MLflow app\", \"update my MLflow app\", \"delete my MLflow app\", \"I need an MLflow server\", asks \"what is SageMaker MLflow\", or a workflow needs an MLflow backend and none is connected. |\n| Diagnose a failing or unhealthy SageMaker endpoint | [references\u002Fendpoint-diagnostics\u002F](references\u002Fendpoint-diagnostics\u002F) | User reports endpoint errors, latency, inference failures, or a deployment that failed. \"What's the status of my endpoint?\", \"Is my endpoint erroring?\", \"My endpoint failed — why?\", \"How many instances are running behind my endpoint?\", \"Is the latency my model or SageMaker?\", \"Show me the container logs for my endpoint.\" NOT for training-job issues, endpoint deletion, scaling changes, or new deployments. |\n\n## Rules\n\n- **Progressive disclosure.** Load only the reference folder relevant to the current user intent. Do not load all references at once.\n- **Best-effort help.** If the user's request falls outside this skill's references, do not dead-end the conversation. Help them using general AWS knowledge and documentation, and inform the user that the guidance is not covered by this skill's validated workflows.\n",{"data":36,"body":38},{"name":4,"description":6,"version":37},1,{"type":39,"children":40},"root",[41,50,56,63,68,390,396],{"type":42,"tag":43,"props":44,"children":46},"element","h1",{"id":45},"aws-aiml-model-customization",[47],{"type":48,"value":49},"text","AWS AI\u002FML Model Customization",{"type":42,"tag":51,"props":52,"children":53},"p",{},[54],{"type":48,"value":55},"Domain expertise for fine-tuning and deploying models on Amazon SageMaker. Covers the full model customization lifecycle from planning through production deployment.",{"type":42,"tag":57,"props":58,"children":60},"h2",{"id":59},"routing",[61],{"type":48,"value":62},"Routing",{"type":42,"tag":51,"props":64,"children":65},{},[66],{"type":48,"value":67},"Match the user's intent to the appropriate reference folder and load only that content.",{"type":42,"tag":69,"props":70,"children":71},"table",{},[72,96],{"type":42,"tag":73,"props":74,"children":75},"thead",{},[76],{"type":42,"tag":77,"props":78,"children":79},"tr",{},[80,86,91],{"type":42,"tag":81,"props":82,"children":83},"th",{},[84],{"type":48,"value":85},"User intent",{"type":42,"tag":81,"props":87,"children":88},{},[89],{"type":48,"value":90},"Reference",{"type":42,"tag":81,"props":92,"children":93},{},[94],{"type":48,"value":95},"When to use",{"type":42,"tag":97,"props":98,"children":99},"tbody",{},[100,123,144,180,201,222,243,264,285,306,327,348,369],{"type":42,"tag":77,"props":101,"children":102},{},[103,109,118],{"type":42,"tag":104,"props":105,"children":106},"td",{},[107],{"type":48,"value":108},"Plan a model customization project, discover scope of work, resume or modify a plan",{"type":42,"tag":104,"props":110,"children":111},{},[112],{"type":42,"tag":113,"props":114,"children":116},"a",{"href":115},"references\u002Fplanning\u002F",[117],{"type":48,"value":115},{"type":42,"tag":104,"props":119,"children":120},{},[121],{"type":48,"value":122},"User's request relates to model customization or deployment (fine-tuning, training, building, customizing, reviewing data, deploying or standing up a model — including selecting or deploying an off-the-shelf or base model with no training — or getting advice on approach). Always co-activate with other intents to discover full scope. Load this reference FIRST when the request matches multiple rows in this table — read its plan templates before routing to a single-action reference.",{"type":42,"tag":77,"props":124,"children":125},{},[126,131,139],{"type":42,"tag":104,"props":127,"children":128},{},[129],{"type":48,"value":130},"Define the business problem, success criteria, or use case spec",{"type":42,"tag":104,"props":132,"children":133},{},[134],{"type":42,"tag":113,"props":135,"children":137},{"href":136},"references\u002Fuse-case-specification\u002F",[138],{"type":48,"value":136},{"type":42,"tag":104,"props":140,"children":141},{},[142],{"type":48,"value":143},"User says \"define my use case\", \"capture requirements\", \"what should I decide up front\", or as default first step in any plan. Skip only if user explicitly declines.",{"type":42,"tag":77,"props":145,"children":146},{},[147,152,160],{"type":42,"tag":104,"props":148,"children":149},{},[150],{"type":48,"value":151},"Select or change a base model",{"type":42,"tag":104,"props":153,"children":154},{},[155],{"type":42,"tag":113,"props":156,"children":158},{"href":157},"references\u002Fmodel-selection\u002F",[159],{"type":48,"value":157},{"type":42,"tag":104,"props":161,"children":162},{},[163,165,171,173,178],{"type":48,"value":164},"User asks which model to use, mentions a model name or family, or wants to evaluate what's available. ",{"type":42,"tag":166,"props":167,"children":168},"strong",{},[169],{"type":48,"value":170},"Always activate model-selection even for known model names",{"type":48,"value":172}," because the exact Hub model ID must be resolved. ",{"type":42,"tag":166,"props":174,"children":175},{},[176],{"type":48,"value":177},"Recommended:",{"type":48,"value":179}," route to use-case-specification first to capture requirements — this produces better filtering results. Routing to use-case-specification first is not required if user provides a specific model name\u002FID or declines. If intent is ambiguous (fine-tune vs deploy as-is), model-selection MUST confirm which path before proceeding. Base model filtering for deployment MUST go through select-for-deployment.md and its scripts for any final recommendation.",{"type":42,"tag":77,"props":181,"children":182},{},[183,188,196],{"type":42,"tag":104,"props":184,"children":185},{},[186],{"type":48,"value":187},"Choose a fine-tuning technique (SFT, DPO, RLVR, RLAIF)",{"type":42,"tag":104,"props":189,"children":190},{},[191],{"type":42,"tag":113,"props":192,"children":194},{"href":193},"references\u002Ffinetuning-technique\u002F",[195],{"type":48,"value":193},{"type":42,"tag":104,"props":197,"children":198},{},[199],{"type":48,"value":200},"User has decided to fine-tune and needs to choose a technique, or technique needs validation against the selected model's recipes. Requires a base model to be selected first.",{"type":42,"tag":77,"props":202,"children":203},{},[204,209,217],{"type":42,"tag":104,"props":205,"children":206},{},[207],{"type":48,"value":208},"Validate dataset quality and format",{"type":42,"tag":104,"props":210,"children":211},{},[212],{"type":42,"tag":113,"props":213,"children":215},{"href":214},"references\u002Fdataset-evaluation\u002F",[216],{"type":48,"value":214},{"type":42,"tag":104,"props":218,"children":219},{},[220],{"type":48,"value":221},"User says \"is my dataset okay\", \"check my training data\", \"I have my own data\", or before starting any fine-tuning job.",{"type":42,"tag":77,"props":223,"children":224},{},[225,230,238],{"type":42,"tag":104,"props":226,"children":227},{},[228],{"type":48,"value":229},"Transform or convert a dataset between formats",{"type":42,"tag":104,"props":231,"children":232},{},[233],{"type":42,"tag":113,"props":234,"children":236},{"href":235},"references\u002Fdataset-transformation\u002F",[237],{"type":48,"value":235},{"type":42,"tag":104,"props":239,"children":240},{},[241],{"type":48,"value":242},"User says \"transform\", \"convert\", \"reformat\", or dataset schema needs to change. Always use this rather than writing inline transformation code.",{"type":42,"tag":77,"props":244,"children":245},{},[246,251,259],{"type":42,"tag":104,"props":247,"children":248},{},[249],{"type":48,"value":250},"Generate fine-tuning code and start training",{"type":42,"tag":104,"props":252,"children":253},{},[254],{"type":42,"tag":113,"props":255,"children":257},{"href":256},"references\u002Ffinetuning\u002F",[258],{"type":48,"value":256},{"type":42,"tag":104,"props":260,"children":261},{},[262],{"type":48,"value":263},"User says \"start training\", \"fine-tune my model\", \"I'm ready to train\", or plan reaches the finetuning step. Supports SFT, DPO, RLVR, RLAIF trainers.",{"type":42,"tag":77,"props":265,"children":266},{},[267,272,280],{"type":42,"tag":104,"props":268,"children":269},{},[270],{"type":48,"value":271},"Evaluate or benchmark a trained model",{"type":42,"tag":104,"props":273,"children":274},{},[275],{"type":42,"tag":113,"props":276,"children":278},{"href":277},"references\u002Fmodel-evaluation\u002F",[279],{"type":48,"value":277},{"type":42,"tag":104,"props":281,"children":282},{},[283],{"type":48,"value":284},"User says \"evaluate my model\", \"run a benchmark\", \"test model performance\", \"compare models\". Supports LLM-as-Judge and Custom Scorer.",{"type":42,"tag":77,"props":286,"children":287},{},[288,293,301],{"type":42,"tag":104,"props":289,"children":290},{},[291],{"type":48,"value":292},"Deploy a model to endpoint or Bedrock",{"type":42,"tag":104,"props":294,"children":295},{},[296],{"type":42,"tag":113,"props":297,"children":299},{"href":298},"references\u002Fmodel-deployment\u002F",[300],{"type":48,"value":298},{"type":42,"tag":104,"props":302,"children":303},{},[304],{"type":48,"value":305},"User says \"deploy my model\", \"create an endpoint\", \"make it available\". Handles Nova vs OSS deployment pathways.",{"type":42,"tag":77,"props":307,"children":308},{},[309,314,322],{"type":42,"tag":104,"props":310,"children":311},{},[312],{"type":48,"value":313},"Set up IAM roles, S3 buckets, SDK configuration",{"type":42,"tag":104,"props":315,"children":316},{},[317],{"type":42,"tag":113,"props":318,"children":320},{"href":319},"references\u002Fsdk-getting-started\u002F",[321],{"type":48,"value":319},{"type":42,"tag":104,"props":323,"children":324},{},[325],{"type":48,"value":326},"User says \"set up\", \"getting started\", \"check my environment\", \"configure SDK\", or as first step in any plan involving SageMaker training\u002Fevaluation\u002Fdeployment.",{"type":42,"tag":77,"props":328,"children":329},{},[330,335,343],{"type":42,"tag":104,"props":331,"children":332},{},[333],{"type":48,"value":334},"Manage project directory and artifacts",{"type":42,"tag":104,"props":336,"children":337},{},[338],{"type":42,"tag":113,"props":339,"children":341},{"href":340},"references\u002Fdirectory-management\u002F",[342],{"type":48,"value":340},{"type":42,"tag":104,"props":344,"children":345},{},[346],{"type":48,"value":347},"Starting a new project, resuming existing one, or when PLAN.md needs to be associated with a project directory.",{"type":42,"tag":77,"props":349,"children":350},{},[351,356,364],{"type":42,"tag":104,"props":352,"children":353},{},[354],{"type":48,"value":355},"Set up, update, or delete a SageMaker Managed MLflow app",{"type":42,"tag":104,"props":357,"children":358},{},[359],{"type":42,"tag":113,"props":360,"children":362},{"href":361},"references\u002Fmanage-mlflow\u002F",[363],{"type":48,"value":361},{"type":42,"tag":104,"props":365,"children":366},{},[367],{"type":48,"value":368},"User says \"set up MLflow\", \"create MLflow app\", \"update my MLflow app\", \"delete my MLflow app\", \"I need an MLflow server\", asks \"what is SageMaker MLflow\", or a workflow needs an MLflow backend and none is connected.",{"type":42,"tag":77,"props":370,"children":371},{},[372,377,385],{"type":42,"tag":104,"props":373,"children":374},{},[375],{"type":48,"value":376},"Diagnose a failing or unhealthy SageMaker endpoint",{"type":42,"tag":104,"props":378,"children":379},{},[380],{"type":42,"tag":113,"props":381,"children":383},{"href":382},"references\u002Fendpoint-diagnostics\u002F",[384],{"type":48,"value":382},{"type":42,"tag":104,"props":386,"children":387},{},[388],{"type":48,"value":389},"User reports endpoint errors, latency, inference failures, or a deployment that failed. \"What's the status of my endpoint?\", \"Is my endpoint erroring?\", \"My endpoint failed — why?\", \"How many instances are running behind my endpoint?\", \"Is the latency my model or SageMaker?\", \"Show me the container logs for my endpoint.\" NOT for training-job issues, endpoint deletion, scaling changes, or new deployments.",{"type":42,"tag":57,"props":391,"children":393},{"id":392},"rules",[394],{"type":48,"value":395},"Rules",{"type":42,"tag":397,"props":398,"children":399},"ul",{},[400,411],{"type":42,"tag":401,"props":402,"children":403},"li",{},[404,409],{"type":42,"tag":166,"props":405,"children":406},{},[407],{"type":48,"value":408},"Progressive disclosure.",{"type":48,"value":410}," Load only the reference folder relevant to the current user intent. Do not load all references at once.",{"type":42,"tag":401,"props":412,"children":413},{},[414,419],{"type":42,"tag":166,"props":415,"children":416},{},[417],{"type":48,"value":418},"Best-effort help.",{"type":48,"value":420}," If the user's request falls outside this skill's references, do not dead-end the conversation. Help them using general AWS knowledge and documentation, and inform the user that the guidance is not covered by this skill's validated workflows.",{"items":422,"total":595},[423,440,455,470,483,493,508,524,538,555,568,580],{"slug":424,"name":424,"fn":425,"description":426,"org":427,"tags":428,"stars":24,"repoUrl":25,"updatedAt":439},"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\", \"payments middleware for my agent\", \"integrate x402 payments with the agent I'm building\", \"enable my agent project with x402 payments\". External APIs via Gateway: use agents-connect. New project: use agents-get-started. CLI\u002Fdev-server errors: use agents-debug. Runtime x402 payments: use agents-pay. Migration-specific Strands vs LangGraph routes here.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[429,432,435,436],{"name":430,"slug":431,"type":15},"Agents","agents",{"name":433,"slug":434,"type":15},"Automation","automation",{"name":23,"slug":8,"type":15},{"name":437,"slug":438,"type":15},"Engineering","engineering","2026-08-07T04:38:08.981896",{"slug":441,"name":441,"fn":442,"description":443,"org":444,"tags":445,"stars":24,"repoUrl":25,"updatedAt":454},"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},[446,447,450,453],{"name":430,"slug":431,"type":15},{"name":448,"slug":449,"type":15},"API Development","api-development",{"name":451,"slug":452,"type":15},"Authentication","authentication",{"name":23,"slug":8,"type":15},"2026-07-16T06:00:38.866147",{"slug":456,"name":456,"fn":457,"description":458,"org":459,"tags":460,"stars":24,"repoUrl":25,"updatedAt":469},"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},[461,462,463,466],{"name":430,"slug":431,"type":15},{"name":23,"slug":8,"type":15},{"name":464,"slug":465,"type":15},"Debugging","debugging",{"name":467,"slug":468,"type":15},"Observability","observability","2026-07-16T06:00:44.679093",{"slug":471,"name":471,"fn":472,"description":473,"org":474,"tags":475,"stars":24,"repoUrl":25,"updatedAt":482},"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},[476,477,478,481],{"name":430,"slug":431,"type":15},{"name":23,"slug":8,"type":15},{"name":479,"slug":480,"type":15},"CI\u002FCD","ci-cd",{"name":20,"slug":21,"type":15},"2026-07-12T08:42:55.059577",{"slug":484,"name":484,"fn":485,"description":486,"org":487,"tags":488,"stars":24,"repoUrl":25,"updatedAt":492},"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},[489,490,491],{"name":430,"slug":431,"type":15},{"name":23,"slug":8,"type":15},{"name":20,"slug":21,"type":15},"2026-07-12T08:42:51.963247",{"slug":494,"name":494,"fn":495,"description":496,"org":497,"tags":498,"stars":24,"repoUrl":25,"updatedAt":507},"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},[499,500,501,504],{"name":430,"slug":431,"type":15},{"name":23,"slug":8,"type":15},{"name":502,"slug":503,"type":15},"Best Practices","best-practices",{"name":505,"slug":506,"type":15},"Security","security","2026-07-16T06:00:42.174705",{"slug":509,"name":509,"fn":510,"description":511,"org":512,"tags":513,"stars":24,"repoUrl":25,"updatedAt":523},"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},[514,515,516,519,520],{"name":430,"slug":431,"type":15},{"name":23,"slug":8,"type":15},{"name":517,"slug":518,"type":15},"Evals","evals",{"name":467,"slug":468,"type":15},{"name":521,"slug":522,"type":15},"Performance","performance","2026-07-12T08:42:56.488105",{"slug":525,"name":525,"fn":526,"description":527,"org":528,"tags":529,"stars":24,"repoUrl":25,"updatedAt":537},"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},[530,531,532,535],{"name":430,"slug":431,"type":15},{"name":433,"slug":434,"type":15},{"name":533,"slug":534,"type":15},"Payments","payments",{"name":536,"slug":536,"type":15},"x402","2026-08-07T05:03:33.377867",{"slug":539,"name":539,"fn":540,"description":541,"org":542,"tags":543,"stars":24,"repoUrl":25,"updatedAt":554},"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},[544,545,548,551],{"name":23,"slug":8,"type":15},{"name":546,"slug":547,"type":15},"Database","database",{"name":549,"slug":550,"type":15},"MySQL","mysql",{"name":552,"slug":553,"type":15},"Serverless","serverless","2026-07-12T08:43:13.27939",{"slug":556,"name":556,"fn":557,"description":558,"org":559,"tags":560,"stars":24,"repoUrl":25,"updatedAt":567},"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},[561,562,563,566],{"name":23,"slug":8,"type":15},{"name":546,"slug":547,"type":15},{"name":564,"slug":565,"type":15},"PostgreSQL","postgresql",{"name":552,"slug":553,"type":15},"2026-07-16T06:00:34.789624",{"slug":569,"name":569,"fn":570,"description":571,"org":572,"tags":573,"stars":24,"repoUrl":25,"updatedAt":579},"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},[574,575,576],{"name":430,"slug":431,"type":15},{"name":23,"slug":8,"type":15},{"name":577,"slug":578,"type":15},"LLM","llm","2026-08-07T04:38:13.03499",{"slug":581,"name":581,"fn":582,"description":583,"org":584,"tags":585,"stars":24,"repoUrl":25,"updatedAt":594},"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},[586,587,588,591],{"name":23,"slug":8,"type":15},{"name":546,"slug":547,"type":15},{"name":589,"slug":590,"type":15},"MongoDB","mongodb",{"name":592,"slug":593,"type":15},"NoSQL","nosql","2026-07-12T08:43:00.455878",118,{"items":597,"total":647},[598,605,612,619,626,632,639],{"slug":424,"name":424,"fn":425,"description":426,"org":599,"tags":600,"stars":24,"repoUrl":25,"updatedAt":439},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[601,602,603,604],{"name":430,"slug":431,"type":15},{"name":433,"slug":434,"type":15},{"name":23,"slug":8,"type":15},{"name":437,"slug":438,"type":15},{"slug":441,"name":441,"fn":442,"description":443,"org":606,"tags":607,"stars":24,"repoUrl":25,"updatedAt":454},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[608,609,610,611],{"name":430,"slug":431,"type":15},{"name":448,"slug":449,"type":15},{"name":451,"slug":452,"type":15},{"name":23,"slug":8,"type":15},{"slug":456,"name":456,"fn":457,"description":458,"org":613,"tags":614,"stars":24,"repoUrl":25,"updatedAt":469},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[615,616,617,618],{"name":430,"slug":431,"type":15},{"name":23,"slug":8,"type":15},{"name":464,"slug":465,"type":15},{"name":467,"slug":468,"type":15},{"slug":471,"name":471,"fn":472,"description":473,"org":620,"tags":621,"stars":24,"repoUrl":25,"updatedAt":482},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[622,623,624,625],{"name":430,"slug":431,"type":15},{"name":23,"slug":8,"type":15},{"name":479,"slug":480,"type":15},{"name":20,"slug":21,"type":15},{"slug":484,"name":484,"fn":485,"description":486,"org":627,"tags":628,"stars":24,"repoUrl":25,"updatedAt":492},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[629,630,631],{"name":430,"slug":431,"type":15},{"name":23,"slug":8,"type":15},{"name":20,"slug":21,"type":15},{"slug":494,"name":494,"fn":495,"description":496,"org":633,"tags":634,"stars":24,"repoUrl":25,"updatedAt":507},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[635,636,637,638],{"name":430,"slug":431,"type":15},{"name":23,"slug":8,"type":15},{"name":502,"slug":503,"type":15},{"name":505,"slug":506,"type":15},{"slug":509,"name":509,"fn":510,"description":511,"org":640,"tags":641,"stars":24,"repoUrl":25,"updatedAt":523},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[642,643,644,645,646],{"name":430,"slug":431,"type":15},{"name":23,"slug":8,"type":15},{"name":517,"slug":518,"type":15},{"name":467,"slug":468,"type":15},{"name":521,"slug":522,"type":15},117]