[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-aws-labs-model-evaluation":3,"mdc-xbdw6o-key":42,"related-repo-aws-labs-model-evaluation":606,"related-org-aws-labs-model-evaluation":713},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":12,"stars":26,"repoUrl":27,"updatedAt":28,"license":29,"forks":30,"topics":31,"repo":37,"sourceUrl":40,"mdContent":41},"model-evaluation","evaluate SageMaker machine learning models","Generates python code that evaluates SageMaker models. Supports two evaluation types: LLM-as-Judge and Custom Scorer. Use when the user says \"evaluate my model\", \"run a benchmark\", \"test model performance\", \"how did my model perform\", \"compare models\", or other similar requests.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},"aws-labs","AWS Labs","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Faws-labs.png","awslabs",[13,17,20,23],{"name":14,"slug":15,"type":16},"Machine Learning","machine-learning","tag",{"name":18,"slug":19,"type":16},"Evals","evals",{"name":21,"slug":22,"type":16},"Python","python",{"name":24,"slug":25,"type":16},"AWS","aws",831,"https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fagent-plugins","2026-07-12T08:39:16.771287",null,127,[32,33,34,25,35,36],"agent-plugins","agent-skills","agents","coding-agent-skills","coding-agents",{"repoUrl":27,"stars":26,"forks":30,"topics":38,"description":39},[32,33,34,25,35,36],"Agent Plugins for AWS equip AI coding agents with the skills to help you architect, deploy, and operate on AWS.","https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fagent-plugins\u002Ftree\u002FHEAD\u002Fplugins\u002Fsagemaker-ai\u002Fskills\u002Fmodel-evaluation","---\nname: model-evaluation\ndescription: 'Generates python code that evaluates SageMaker models. Supports two evaluation types: LLM-as-Judge and Custom Scorer. Use when the user says \"evaluate my model\", \"run a benchmark\", \"test model performance\", \"how did my model perform\", \"compare models\", or other similar requests.'\nmetadata:\n  version: \"3.0.0\"\n---\n\n# Model Evaluation\n\nGenerate code that evaluates a SageMaker model.\n\n## Prerequisites\n\n- The SDK environment has been verified (SDK version, region, execution role). If not done, activate the `sdk-getting-started` skill first.\n\n## Principles\n\n1. **One thing at a time.** Each response advances exactly one decision. Never combine multiple questions in a single turn.\n2. **Confirm before proceeding.** Wait for the user to agree before moving to the next step.\n3. **Don't read files until you need them.** Only read reference files when you've reached the step that requires them.\n4. **Don't ask what you already know.** If the answer is in conversation history, workflow_state.json, plan.md, or any file you've already read — use it. Confirm if unsure, but don't re-ask.\n5. **No narration.** Share outcomes and ask questions. Keep responses short.\n6. **No repetition.** If you said something before a tool call, don't repeat it after.\n\n## Scope\n\nThis skill supports the evaluation feature for SageMaker Serverless Model Customization. It can evaluate any base or fine-tuned model supported by SageMaker serverless model customization — both OSS models (Llama, Mistral, Qwen, etc.) and Nova models.\n\nTell the user when the skill is activated:\n\n> \"I can help evaluate any base or fine-tuned model supported by SageMaker serverless model customization.\"\n\nIf the user requests help evaluating a model that isn't supported by SageMaker serverless model customization, explain that it is not supported by this skill.\n\n## Evaluation Types\n\nThere are two evaluation types:\n\n- **LLM-as-Judge** — an LLM grades your model's responses. (OSS models only — not supported for Nova.)\n- **Custom Scorer** — programmatic evaluation via Lambda function (includes built-in math and code scorers). Works with both OSS and Nova models.\n\n## Workflow\n\n### Step 1: Determine evaluation type\n\n**Do you already know which evaluation type to use?**\n\nCheck conversation history, plan.md, workflow_state.json, or anything else you've already read.\n\n**If yes:** confirm with the user.\n\n> \"It sounds like you want to run [evaluation type]. Is that right?\"\n\n⏸ Wait for confirmation. If confirmed → go to Step 2.\n\n**If no:** ask.\n\n> \"What kind of evaluation would you like to run? I support:\n>\n> 1. **LLM-as-Judge** — an LLM grades your model's responses\n> 2. **Custom Scorer** — programmatic scoring (math, code, or your own logic)\n>\n> Pick one, or say 'help me decide' if you're not sure.\"\n\n⏸ Wait for user.\n\n- If user picks one → go to Step 2.\n- If user indicates uncertainty, by saying something like \"help me decide,\" \"whatever you think,\" \"I'm not sure\" → read `references\u002Fevaluation-type-guide.md` and follow its instructions. It will guide the user to a choice and then return here.\n  You MUST NEVER make a recommendation to the user on eval type without reading `references\u002Fevaluation-type-guide.md`.\n\n### Step 2: Validate and hand off to evaluation workflow\n\nBefore reading the reference file, validate that the chosen evaluation type is compatible with the user's situation. You may already know these answers from conversation context — don't ask if you don't need to.\n\n#### LLM-as-Judge validation\n\n1. **What model type are we evaluating?** LLM-as-Judge is not supported for Nova models. To determine model type (if you don't already know it):\n   - If you have the **training job name or ARN**, use the AWS MCP tool `list-tags` on the training job ARN and look for the `sagemaker-studio:jumpstart-model-id` tag. Contains \"nova\" → Nova. Anything else → OSS.\n   - If you have a **Model Package ARN**, use the AWS MCP tool `describe-model-package` and check the model description or source tags.\n   - If neither is available, ask the user.\n2. **Does the user have an evaluation dataset?** LLM-as-Judge requires one.\n\n#### Custom Scorer validation\n\n1. **Does the user have an evaluation dataset?** Custom Scorer requires one. (Works with both OSS and Nova models, though for Nova only custom lambdas are supported.)\n\n---\n\nIf validation fails, tell the user which requirement(s) aren't met and offer alternatives:\n\n> \"[Evaluation type] won't work because [reason].\"\n\nIf the failure reason was lack of an eval dataset, there's nothing we can do. Inform the user:\n\n> \"Unfortunately all of the supported eval types require an eval dataset. I can't help you with model evaluation.\"\n\nIf the failure reason is something else, offer to help them pick a different evaluation type.\n\n⏸ Wait for user.\n\nIf they say they do want help choosing a different eval type → read `references\u002Fevaluation-type-guide.md`.\n\nIf validation passes, read the corresponding reference file:\n\n| User chose    | Read                                     |\n| ------------- | ---------------------------------------- |\n| LLM-as-Judge  | `references\u002Fllmaaj-evaluation.md`        |\n| Custom Scorer | `references\u002Fcustom-scorer-evaluation.md` |\n\nFollow the reference file's instructions from the beginning.\n",{"data":43,"body":46},{"name":4,"description":6,"metadata":44},{"version":45},"3.0.0",{"type":47,"children":48},"root",[49,57,63,70,89,95,160,166,171,176,185,190,196,201,224,230,237,245,250,260,276,281,291,325,330,358,364,369,376,454,460,472,476,481,503,508,516,521,525,536,541,601],{"type":50,"tag":51,"props":52,"children":53},"element","h1",{"id":4},[54],{"type":55,"value":56},"text","Model Evaluation",{"type":50,"tag":58,"props":59,"children":60},"p",{},[61],{"type":55,"value":62},"Generate code that evaluates a SageMaker model.",{"type":50,"tag":64,"props":65,"children":67},"h2",{"id":66},"prerequisites",[68],{"type":55,"value":69},"Prerequisites",{"type":50,"tag":71,"props":72,"children":73},"ul",{},[74],{"type":50,"tag":75,"props":76,"children":77},"li",{},[78,80,87],{"type":55,"value":79},"The SDK environment has been verified (SDK version, region, execution role). If not done, activate the ",{"type":50,"tag":81,"props":82,"children":84},"code",{"className":83},[],[85],{"type":55,"value":86},"sdk-getting-started",{"type":55,"value":88}," skill first.",{"type":50,"tag":64,"props":90,"children":92},{"id":91},"principles",[93],{"type":55,"value":94},"Principles",{"type":50,"tag":96,"props":97,"children":98},"ol",{},[99,110,120,130,140,150],{"type":50,"tag":75,"props":100,"children":101},{},[102,108],{"type":50,"tag":103,"props":104,"children":105},"strong",{},[106],{"type":55,"value":107},"One thing at a time.",{"type":55,"value":109}," Each response advances exactly one decision. Never combine multiple questions in a single turn.",{"type":50,"tag":75,"props":111,"children":112},{},[113,118],{"type":50,"tag":103,"props":114,"children":115},{},[116],{"type":55,"value":117},"Confirm before proceeding.",{"type":55,"value":119}," Wait for the user to agree before moving to the next step.",{"type":50,"tag":75,"props":121,"children":122},{},[123,128],{"type":50,"tag":103,"props":124,"children":125},{},[126],{"type":55,"value":127},"Don't read files until you need them.",{"type":55,"value":129}," Only read reference files when you've reached the step that requires them.",{"type":50,"tag":75,"props":131,"children":132},{},[133,138],{"type":50,"tag":103,"props":134,"children":135},{},[136],{"type":55,"value":137},"Don't ask what you already know.",{"type":55,"value":139}," If the answer is in conversation history, workflow_state.json, plan.md, or any file you've already read — use it. Confirm if unsure, but don't re-ask.",{"type":50,"tag":75,"props":141,"children":142},{},[143,148],{"type":50,"tag":103,"props":144,"children":145},{},[146],{"type":55,"value":147},"No narration.",{"type":55,"value":149}," Share outcomes and ask questions. Keep responses short.",{"type":50,"tag":75,"props":151,"children":152},{},[153,158],{"type":50,"tag":103,"props":154,"children":155},{},[156],{"type":55,"value":157},"No repetition.",{"type":55,"value":159}," If you said something before a tool call, don't repeat it after.",{"type":50,"tag":64,"props":161,"children":163},{"id":162},"scope",[164],{"type":55,"value":165},"Scope",{"type":50,"tag":58,"props":167,"children":168},{},[169],{"type":55,"value":170},"This skill supports the evaluation feature for SageMaker Serverless Model Customization. It can evaluate any base or fine-tuned model supported by SageMaker serverless model customization — both OSS models (Llama, Mistral, Qwen, etc.) and Nova models.",{"type":50,"tag":58,"props":172,"children":173},{},[174],{"type":55,"value":175},"Tell the user when the skill is activated:",{"type":50,"tag":177,"props":178,"children":179},"blockquote",{},[180],{"type":50,"tag":58,"props":181,"children":182},{},[183],{"type":55,"value":184},"\"I can help evaluate any base or fine-tuned model supported by SageMaker serverless model customization.\"",{"type":50,"tag":58,"props":186,"children":187},{},[188],{"type":55,"value":189},"If the user requests help evaluating a model that isn't supported by SageMaker serverless model customization, explain that it is not supported by this skill.",{"type":50,"tag":64,"props":191,"children":193},{"id":192},"evaluation-types",[194],{"type":55,"value":195},"Evaluation Types",{"type":50,"tag":58,"props":197,"children":198},{},[199],{"type":55,"value":200},"There are two evaluation types:",{"type":50,"tag":71,"props":202,"children":203},{},[204,214],{"type":50,"tag":75,"props":205,"children":206},{},[207,212],{"type":50,"tag":103,"props":208,"children":209},{},[210],{"type":55,"value":211},"LLM-as-Judge",{"type":55,"value":213}," — an LLM grades your model's responses. (OSS models only — not supported for Nova.)",{"type":50,"tag":75,"props":215,"children":216},{},[217,222],{"type":50,"tag":103,"props":218,"children":219},{},[220],{"type":55,"value":221},"Custom Scorer",{"type":55,"value":223}," — programmatic evaluation via Lambda function (includes built-in math and code scorers). Works with both OSS and Nova models.",{"type":50,"tag":64,"props":225,"children":227},{"id":226},"workflow",[228],{"type":55,"value":229},"Workflow",{"type":50,"tag":231,"props":232,"children":234},"h3",{"id":233},"step-1-determine-evaluation-type",[235],{"type":55,"value":236},"Step 1: Determine evaluation type",{"type":50,"tag":58,"props":238,"children":239},{},[240],{"type":50,"tag":103,"props":241,"children":242},{},[243],{"type":55,"value":244},"Do you already know which evaluation type to use?",{"type":50,"tag":58,"props":246,"children":247},{},[248],{"type":55,"value":249},"Check conversation history, plan.md, workflow_state.json, or anything else you've already read.",{"type":50,"tag":58,"props":251,"children":252},{},[253,258],{"type":50,"tag":103,"props":254,"children":255},{},[256],{"type":55,"value":257},"If yes:",{"type":55,"value":259}," confirm with the user.",{"type":50,"tag":177,"props":261,"children":262},{},[263],{"type":50,"tag":58,"props":264,"children":265},{},[266,268,274],{"type":55,"value":267},"\"It sounds like you want to run ",{"type":50,"tag":269,"props":270,"children":271},"span",{},[272],{"type":55,"value":273},"evaluation type",{"type":55,"value":275},". Is that right?\"",{"type":50,"tag":58,"props":277,"children":278},{},[279],{"type":55,"value":280},"⏸ Wait for confirmation. If confirmed → go to Step 2.",{"type":50,"tag":58,"props":282,"children":283},{},[284,289],{"type":50,"tag":103,"props":285,"children":286},{},[287],{"type":55,"value":288},"If no:",{"type":55,"value":290}," ask.",{"type":50,"tag":177,"props":292,"children":293},{},[294,299,320],{"type":50,"tag":58,"props":295,"children":296},{},[297],{"type":55,"value":298},"\"What kind of evaluation would you like to run? I support:",{"type":50,"tag":96,"props":300,"children":301},{},[302,311],{"type":50,"tag":75,"props":303,"children":304},{},[305,309],{"type":50,"tag":103,"props":306,"children":307},{},[308],{"type":55,"value":211},{"type":55,"value":310}," — an LLM grades your model's responses",{"type":50,"tag":75,"props":312,"children":313},{},[314,318],{"type":50,"tag":103,"props":315,"children":316},{},[317],{"type":55,"value":221},{"type":55,"value":319}," — programmatic scoring (math, code, or your own logic)",{"type":50,"tag":58,"props":321,"children":322},{},[323],{"type":55,"value":324},"Pick one, or say 'help me decide' if you're not sure.\"",{"type":50,"tag":58,"props":326,"children":327},{},[328],{"type":55,"value":329},"⏸ Wait for user.",{"type":50,"tag":71,"props":331,"children":332},{},[333,338],{"type":50,"tag":75,"props":334,"children":335},{},[336],{"type":55,"value":337},"If user picks one → go to Step 2.",{"type":50,"tag":75,"props":339,"children":340},{},[341,343,349,351,356],{"type":55,"value":342},"If user indicates uncertainty, by saying something like \"help me decide,\" \"whatever you think,\" \"I'm not sure\" → read ",{"type":50,"tag":81,"props":344,"children":346},{"className":345},[],[347],{"type":55,"value":348},"references\u002Fevaluation-type-guide.md",{"type":55,"value":350}," and follow its instructions. It will guide the user to a choice and then return here.\nYou MUST NEVER make a recommendation to the user on eval type without reading ",{"type":50,"tag":81,"props":352,"children":354},{"className":353},[],[355],{"type":55,"value":348},{"type":55,"value":357},".",{"type":50,"tag":231,"props":359,"children":361},{"id":360},"step-2-validate-and-hand-off-to-evaluation-workflow",[362],{"type":55,"value":363},"Step 2: Validate and hand off to evaluation workflow",{"type":50,"tag":58,"props":365,"children":366},{},[367],{"type":55,"value":368},"Before reading the reference file, validate that the chosen evaluation type is compatible with the user's situation. You may already know these answers from conversation context — don't ask if you don't need to.",{"type":50,"tag":370,"props":371,"children":373},"h4",{"id":372},"llm-as-judge-validation",[374],{"type":55,"value":375},"LLM-as-Judge validation",{"type":50,"tag":96,"props":377,"children":378},{},[379,444],{"type":50,"tag":75,"props":380,"children":381},{},[382,387,389],{"type":50,"tag":103,"props":383,"children":384},{},[385],{"type":55,"value":386},"What model type are we evaluating?",{"type":55,"value":388}," LLM-as-Judge is not supported for Nova models. To determine model type (if you don't already know it):\n",{"type":50,"tag":71,"props":390,"children":391},{},[392,420,439],{"type":50,"tag":75,"props":393,"children":394},{},[395,397,402,404,410,412,418],{"type":55,"value":396},"If you have the ",{"type":50,"tag":103,"props":398,"children":399},{},[400],{"type":55,"value":401},"training job name or ARN",{"type":55,"value":403},", use the AWS MCP tool ",{"type":50,"tag":81,"props":405,"children":407},{"className":406},[],[408],{"type":55,"value":409},"list-tags",{"type":55,"value":411}," on the training job ARN and look for the ",{"type":50,"tag":81,"props":413,"children":415},{"className":414},[],[416],{"type":55,"value":417},"sagemaker-studio:jumpstart-model-id",{"type":55,"value":419}," tag. Contains \"nova\" → Nova. Anything else → OSS.",{"type":50,"tag":75,"props":421,"children":422},{},[423,425,430,431,437],{"type":55,"value":424},"If you have a ",{"type":50,"tag":103,"props":426,"children":427},{},[428],{"type":55,"value":429},"Model Package ARN",{"type":55,"value":403},{"type":50,"tag":81,"props":432,"children":434},{"className":433},[],[435],{"type":55,"value":436},"describe-model-package",{"type":55,"value":438}," and check the model description or source tags.",{"type":50,"tag":75,"props":440,"children":441},{},[442],{"type":55,"value":443},"If neither is available, ask the user.",{"type":50,"tag":75,"props":445,"children":446},{},[447,452],{"type":50,"tag":103,"props":448,"children":449},{},[450],{"type":55,"value":451},"Does the user have an evaluation dataset?",{"type":55,"value":453}," LLM-as-Judge requires one.",{"type":50,"tag":370,"props":455,"children":457},{"id":456},"custom-scorer-validation",[458],{"type":55,"value":459},"Custom Scorer validation",{"type":50,"tag":96,"props":461,"children":462},{},[463],{"type":50,"tag":75,"props":464,"children":465},{},[466,470],{"type":50,"tag":103,"props":467,"children":468},{},[469],{"type":55,"value":451},{"type":55,"value":471}," Custom Scorer requires one. (Works with both OSS and Nova models, though for Nova only custom lambdas are supported.)",{"type":50,"tag":473,"props":474,"children":475},"hr",{},[],{"type":50,"tag":58,"props":477,"children":478},{},[479],{"type":55,"value":480},"If validation fails, tell the user which requirement(s) aren't met and offer alternatives:",{"type":50,"tag":177,"props":482,"children":483},{},[484],{"type":50,"tag":58,"props":485,"children":486},{},[487,489,494,496,501],{"type":55,"value":488},"\"",{"type":50,"tag":269,"props":490,"children":491},{},[492],{"type":55,"value":493},"Evaluation type",{"type":55,"value":495}," won't work because ",{"type":50,"tag":269,"props":497,"children":498},{},[499],{"type":55,"value":500},"reason",{"type":55,"value":502},".\"",{"type":50,"tag":58,"props":504,"children":505},{},[506],{"type":55,"value":507},"If the failure reason was lack of an eval dataset, there's nothing we can do. Inform the user:",{"type":50,"tag":177,"props":509,"children":510},{},[511],{"type":50,"tag":58,"props":512,"children":513},{},[514],{"type":55,"value":515},"\"Unfortunately all of the supported eval types require an eval dataset. I can't help you with model evaluation.\"",{"type":50,"tag":58,"props":517,"children":518},{},[519],{"type":55,"value":520},"If the failure reason is something else, offer to help them pick a different evaluation type.",{"type":50,"tag":58,"props":522,"children":523},{},[524],{"type":55,"value":329},{"type":50,"tag":58,"props":526,"children":527},{},[528,530,535],{"type":55,"value":529},"If they say they do want help choosing a different eval type → read ",{"type":50,"tag":81,"props":531,"children":533},{"className":532},[],[534],{"type":55,"value":348},{"type":55,"value":357},{"type":50,"tag":58,"props":537,"children":538},{},[539],{"type":55,"value":540},"If validation passes, read the corresponding reference file:",{"type":50,"tag":542,"props":543,"children":544},"table",{},[545,564],{"type":50,"tag":546,"props":547,"children":548},"thead",{},[549],{"type":50,"tag":550,"props":551,"children":552},"tr",{},[553,559],{"type":50,"tag":554,"props":555,"children":556},"th",{},[557],{"type":55,"value":558},"User chose",{"type":50,"tag":554,"props":560,"children":561},{},[562],{"type":55,"value":563},"Read",{"type":50,"tag":565,"props":566,"children":567},"tbody",{},[568,585],{"type":50,"tag":550,"props":569,"children":570},{},[571,576],{"type":50,"tag":572,"props":573,"children":574},"td",{},[575],{"type":55,"value":211},{"type":50,"tag":572,"props":577,"children":578},{},[579],{"type":50,"tag":81,"props":580,"children":582},{"className":581},[],[583],{"type":55,"value":584},"references\u002Fllmaaj-evaluation.md",{"type":50,"tag":550,"props":586,"children":587},{},[588,592],{"type":50,"tag":572,"props":589,"children":590},{},[591],{"type":55,"value":221},{"type":50,"tag":572,"props":593,"children":594},{},[595],{"type":50,"tag":81,"props":596,"children":598},{"className":597},[],[599],{"type":55,"value":600},"references\u002Fcustom-scorer-evaluation.md",{"type":50,"tag":58,"props":602,"children":603},{},[604],{"type":55,"value":605},"Follow the reference file's instructions from the beginning.",{"items":607,"total":712},[608,625,645,657,674,687,697],{"slug":609,"name":609,"fn":610,"description":611,"org":612,"tags":613,"stars":26,"repoUrl":27,"updatedAt":624},"amazon-location-service","integrate Amazon Location Service maps","Integrates Amazon Location Service APIs for AWS applications. Use this skill when users want to add maps (interactive MapLibre or static images); geocode addresses to coordinates or reverse geocode coordinates to addresses; calculate routes, travel times, or service areas; find places and businesses through text search, nearby search, or autocomplete suggestions; retrieve detailed place information including hours, contacts, and addresses; monitor geographical boundaries with geofences; or track device locations. Covers authentication, SDK integration, and all Amazon Location Service capabilities.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[614,617,618,621],{"name":615,"slug":616,"type":16},"API Development","api-development",{"name":24,"slug":25,"type":16},{"name":619,"slug":620,"type":16},"Maps","maps",{"name":622,"slug":623,"type":16},"Navigation","navigation","2026-07-12T08:39:49.88311",{"slug":626,"name":626,"fn":627,"description":628,"org":629,"tags":630,"stars":26,"repoUrl":27,"updatedAt":644},"amplify-workflow","build and deploy apps with AWS Amplify","Build and deploy full-stack web and mobile apps with AWS Amplify Gen2 (TypeScript code-first). Covers auth (Cognito), data (AppSync\u002FDynamoDB including schema modeling, enum types, relationships, authorization rules), storage (S3), functions, APIs, and AI (Amplify AI Kit with Bedrock). Supports React, Next.js, Vue, Angular, React Native, Flutter, Swift, and Android. Always use this skill for Amplify Gen2 topics — even for questions you think you know — it contains validated, version-specific patterns that prevent common mistakes. TRIGGER when: user mentions Amplify Gen2; project has amplify\u002F directory or amplify_outputs; code imports @aws-amplify packages; user asks about defineBackend, defineAuth, defineData, defineStorage, or npx ampx. SKIP: Amplify Gen1 (amplify CLI v6), standalone SAM\u002FCDK without Amplify (use aws-serverless), direct Bedrock without Amplify AI Kit (use bedrock).",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[631,634,635,638,641],{"name":632,"slug":633,"type":16},"Auth","auth",{"name":24,"slug":25,"type":16},{"name":636,"slug":637,"type":16},"Database","database",{"name":639,"slug":640,"type":16},"Deployment","deployment",{"name":642,"slug":643,"type":16},"TypeScript","typescript","2026-07-12T08:39:43.500162",{"slug":646,"name":646,"fn":647,"description":648,"org":649,"tags":650,"stars":26,"repoUrl":27,"updatedAt":656},"api-gateway","build and manage Amazon API Gateway APIs","Build, manage, and operate APIs with Amazon API Gateway (REST, HTTP, and WebSocket). Triggers on phrases like: API Gateway, REST API, HTTP API, WebSocket API, custom domain, Lambda authorizer, usage plan, throttling, CORS, VPC link, private API. Also covers troubleshooting API Gateway errors (4xx, 5xx, timeout, CORS failures) and IaC templates containing API Gateway resources. For general REST API design unrelated to AWS, do not trigger.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[651,652,653],{"name":615,"slug":616,"type":16},{"name":24,"slug":25,"type":16},{"name":654,"slug":655,"type":16},"REST API","rest-api","2026-07-12T08:39:00.149339",{"slug":658,"name":658,"fn":659,"description":660,"org":661,"tags":662,"stars":26,"repoUrl":27,"updatedAt":673},"aws-architecture-diagram","generate AWS architecture diagrams","Generate validated AWS architecture diagrams as draw.io XML using official AWS4 icon libraries. Use this skill whenever the user wants to create, generate, or design AWS architecture diagrams, cloud infrastructure diagrams, or system design visuals. Also triggers for requests to visualize existing infrastructure from CloudFormation, CDK, or Terraform code. Supports two modes: analyze an existing codebase to auto-generate diagrams, or brainstorm interactively from scratch. Exports .drawio files with optional PNG\u002FSVG\u002FPDF export via draw.io desktop CLI.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[663,666,667,670],{"name":664,"slug":665,"type":16},"Architecture","architecture",{"name":24,"slug":25,"type":16},{"name":668,"slug":669,"type":16},"Design","design",{"name":671,"slug":672,"type":16},"Diagrams","diagrams","2026-07-12T08:37:11.012278",{"slug":675,"name":675,"fn":676,"description":677,"org":678,"tags":679,"stars":26,"repoUrl":27,"updatedAt":686},"aws-lambda","build and deploy AWS Lambda functions","Design, build, deploy, test, and debug serverless applications with AWS Lambda. Triggers on phrases like: Lambda function, event source, serverless application, API Gateway, EventBridge, Step Functions, serverless API, event-driven architecture, Lambda trigger. For deploying non-serverless apps to AWS, use deploy-on-aws plugin instead.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[680,681,682,683],{"name":615,"slug":616,"type":16},{"name":24,"slug":25,"type":16},{"name":639,"slug":640,"type":16},{"name":684,"slug":685,"type":16},"Serverless","serverless","2026-07-12T08:38:58.598492",{"slug":688,"name":688,"fn":689,"description":690,"org":691,"tags":692,"stars":26,"repoUrl":27,"updatedAt":696},"aws-lambda-durable-functions","build resilient AWS Lambda durable functions","Build resilient, long-running, multi-step applications with AWS Lambda durable functions with automatic state persistence, retry logic, and orchestration for long-running executions. Covers the critical replay model, step operations, wait\u002Fcallback patterns, error handling with saga pattern, testing with LocalDurableTestRunner. Triggers on phrases like: lambda durable functions, workflow orchestration, state machines, retry\u002Fcheckpoint patterns, long-running stateful Lambda functions, saga pattern, human-in-the-loop callbacks, and reliable serverless applications.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[693,694,695],{"name":664,"slug":665,"type":16},{"name":24,"slug":25,"type":16},{"name":684,"slug":685,"type":16},"2026-07-12T08:39:05.546173",{"slug":698,"name":698,"fn":699,"description":700,"org":701,"tags":702,"stars":26,"repoUrl":27,"updatedAt":711},"aws-lambda-managed-instances","configure AWS Lambda Managed Instances","Evaluate, configure, and migrate workloads to AWS Lambda Managed Instances (LMI). Triggers on: Lambda Managed Instances, LMI, capacity provider, multi-concurrency Lambda, dedicated instance Lambda, EC2-backed Lambda, cold start elimination, Graviton Lambda, instance type for Lambda, scheduled scaling for LMI, Lambda cost optimization with Reserved Instances or Savings Plans. Also trigger when users describe high-volume predictable workloads seeking cost savings, want to scale LMI capacity on a schedule, or compare Lambda vs EC2 for steady-state traffic. For standard Lambda without LMI, use the aws-lambda skill instead.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[703,704,705,708],{"name":24,"slug":25,"type":16},{"name":639,"slug":640,"type":16},{"name":706,"slug":707,"type":16},"Infrastructure","infrastructure",{"name":709,"slug":710,"type":16},"Performance","performance","2026-07-12T08:39:07.007071",33,{"items":714,"total":888},[715,734,751,761,774,787,797,807,828,843,858,873],{"slug":716,"name":716,"fn":717,"description":718,"org":719,"tags":720,"stars":731,"repoUrl":732,"updatedAt":733},"agentcore-investigation","investigate Bedrock AgentCore runtime sessions","Investigate Bedrock AgentCore runtime sessions via CloudWatch Logs Insights — resolve session\u002Ftrace IDs, query OTEL spans, filter noise, build timelines. Use when debugging AgentCore agent sessions, tracing tool calls, or analyzing latency.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[721,722,725,728],{"name":24,"slug":25,"type":16},{"name":723,"slug":724,"type":16},"Debugging","debugging",{"name":726,"slug":727,"type":16},"Logs","logs",{"name":729,"slug":730,"type":16},"Observability","observability",9427,"https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fmcp","2026-07-12T08:37:22.601527",{"slug":735,"name":736,"fn":737,"description":738,"org":739,"tags":740,"stars":731,"repoUrl":732,"updatedAt":750},"amazon-aurora-dsql","amazon aurora dsql","build applications with Aurora DSQL","Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, load data, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL and PostgreSQL-to-DSQL schema conversion, FK replacement code generation, OCC retry patterns, ORM migration (Django\u002FHibernate\u002FRails), DDL operations, query plan explainability, SQL compatibility validation, and bulk data loading. Triggers on phrases like: DSQL, Aurora DSQL, create DSQL table, DSQL schema, migrate to DSQL, distributed SQL database, serverless PostgreSQL-compatible database, DSQL query plan, DSQL EXPLAIN ANALYZE, why is my DSQL query slow, DSQL foreign key, DSQL OCC retry, DSQL multi-region, load into DSQL, load CSV into DSQL, bulk load DSQL, aurora-dsql-loader.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[741,744,745,746,747],{"name":742,"slug":743,"type":16},"Aurora","aurora",{"name":24,"slug":25,"type":16},{"name":636,"slug":637,"type":16},{"name":684,"slug":685,"type":16},{"name":748,"slug":749,"type":16},"SQL","sql","2026-07-12T08:36:45.053393",{"slug":752,"name":753,"fn":737,"description":738,"org":754,"tags":755,"stars":731,"repoUrl":732,"updatedAt":760},"aurora-dsql","aurora dsql",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[756,757,758,759],{"name":24,"slug":25,"type":16},{"name":636,"slug":637,"type":16},{"name":684,"slug":685,"type":16},{"name":748,"slug":749,"type":16},"2026-07-12T08:36:42.694299",{"slug":762,"name":763,"fn":737,"description":738,"org":764,"tags":765,"stars":731,"repoUrl":732,"updatedAt":773},"aws-dsql","aws dsql",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[766,767,768,771,772],{"name":24,"slug":25,"type":16},{"name":636,"slug":637,"type":16},{"name":769,"slug":770,"type":16},"Migration","migration",{"name":684,"slug":685,"type":16},{"name":748,"slug":749,"type":16},"2026-07-12T08:36:38.584057",{"slug":775,"name":776,"fn":737,"description":738,"org":777,"tags":778,"stars":731,"repoUrl":732,"updatedAt":786},"distributed-postgres","distributed postgres",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[779,780,781,784,785],{"name":24,"slug":25,"type":16},{"name":636,"slug":637,"type":16},{"name":782,"slug":783,"type":16},"PostgreSQL","postgresql",{"name":684,"slug":685,"type":16},{"name":748,"slug":749,"type":16},"2026-07-12T08:36:46.530743",{"slug":788,"name":789,"fn":737,"description":738,"org":790,"tags":791,"stars":731,"repoUrl":732,"updatedAt":796},"distributed-sql","distributed sql",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[792,793,794,795],{"name":24,"slug":25,"type":16},{"name":636,"slug":637,"type":16},{"name":684,"slug":685,"type":16},{"name":748,"slug":749,"type":16},"2026-07-12T08:36:48.104182",{"slug":798,"name":798,"fn":737,"description":738,"org":799,"tags":800,"stars":731,"repoUrl":732,"updatedAt":806},"dsql",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[801,802,803,804,805],{"name":24,"slug":25,"type":16},{"name":636,"slug":637,"type":16},{"name":769,"slug":770,"type":16},{"name":684,"slug":685,"type":16},{"name":748,"slug":749,"type":16},"2026-07-12T08:36:36.374512",{"slug":808,"name":808,"fn":809,"description":810,"org":811,"tags":812,"stars":825,"repoUrl":826,"updatedAt":827},"cost-efficiency-analyzer","analyze cost efficiency and expenses","Analyzes cost structure, cost efficiency, and expense management from P&L data. Use when the user asks about costs, expenses, COGS, operating expenses, cost ratios, cost control, spending efficiency, margin compression from cost side, or wants to understand where money is going. Also use for \"are we spending too much\", \"cost breakdown\", \"expense analysis\", or \"how efficient are our operations\". NOT for revenue or top-line analysis.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[813,816,819,822],{"name":814,"slug":815,"type":16},"Accounting","accounting",{"name":817,"slug":818,"type":16},"Analytics","analytics",{"name":820,"slug":821,"type":16},"Cost Optimization","cost-optimization",{"name":823,"slug":824,"type":16},"Finance","finance",3176,"https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fagentcore-samples","2026-07-12T08:40:03.29555",{"slug":829,"name":829,"fn":830,"description":831,"org":832,"tags":833,"stars":825,"repoUrl":826,"updatedAt":842},"executive-financial-briefing","generate executive financial briefings","Generates a concise executive-level financial briefing or summary suitable for a CEO, CFO, or board presentation. Use when the user asks for a summary, briefing, executive summary, board update, financial overview, financial health check, or \"how is the business doing\". Covers the full P&L picture in one page. Also use for \"give me the highlights\", \"what do I need to know\", or \"quick financial update\".",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[834,835,836,839],{"name":24,"slug":25,"type":16},{"name":823,"slug":824,"type":16},{"name":837,"slug":838,"type":16},"Management","management",{"name":840,"slug":841,"type":16},"Reporting","reporting","2026-07-12T08:40:02.066471",{"slug":844,"name":844,"fn":845,"description":846,"org":847,"tags":848,"stars":825,"repoUrl":826,"updatedAt":857},"multi-quarter-trend-analysis","analyze multi-quarter financial trends","Analyzes financial trends across multiple quarters by comparing P&L metrics over time. Use when the user wants to see trends, patterns, trajectories, or directional movement across 3 or more quarters. Also use for \"how are we trending\", \"show me the trend\", \"track performance over time\", \"quarter over quarter comparison across all quarters\", or any multi-period longitudinal analysis.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[849,850,851,854],{"name":817,"slug":818,"type":16},{"name":823,"slug":824,"type":16},{"name":852,"slug":853,"type":16},"Financial Statements","financial-statements",{"name":855,"slug":856,"type":16},"Variance Analysis","variance-analysis","2026-07-12T08:40:00.79141",{"slug":859,"name":859,"fn":860,"description":861,"org":862,"tags":863,"stars":825,"repoUrl":826,"updatedAt":872},"pdf","process and manipulate PDF documents","Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text\u002Ftables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting\u002Fdecrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[864,867,870],{"name":865,"slug":866,"type":16},"Automation","automation",{"name":868,"slug":869,"type":16},"Documents","documents",{"name":871,"slug":859,"type":16},"PDF","2026-07-12T08:41:44.135656",{"slug":874,"name":874,"fn":875,"description":876,"org":877,"tags":878,"stars":825,"repoUrl":826,"updatedAt":887},"quarterly-kpi-calculator","calculate quarterly financial KPIs","Calculates quarterly financial KPIs from P&L data. P&L figures can be provided directly by the user or fetched from the financial data MCP server. Use when the user wants KPI calculations such as Gross Margin %, EBITDA Margin %, Operating Expense Ratio, or Revenue Growth % QoQ. Also use for quarterly performance review, P&L analysis, or interpreting financial ratios against benchmarks.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[879,880,883,884],{"name":814,"slug":815,"type":16},{"name":881,"slug":882,"type":16},"Data Analysis","data-analysis",{"name":823,"slug":824,"type":16},{"name":885,"slug":886,"type":16},"KPI","kpi","2026-07-12T08:39:59.54971",150]