[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-aws-labs-dataset-evaluation":3,"mdc-jc16rk-key":45,"related-repo-aws-labs-dataset-evaluation":454,"related-org-aws-labs-dataset-evaluation":561},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":12,"stars":29,"repoUrl":30,"updatedAt":31,"license":32,"forks":33,"topics":34,"repo":40,"sourceUrl":43,"mdContent":44},"dataset-evaluation","validate datasets for SageMaker fine-tuning","Validates dataset formatting and quality for SageMaker model fine-tuning (SFT, DPO, or RLVR). Use when the user says \"is my dataset okay\", \"evaluate my data\", \"check my training data\", \"I have my own data\", or before starting any fine-tuning job. Detects file format, checks schema compliance against the selected model and technique, and reports whether the data is ready for training or evaluation.",{"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",[13,17,20,23,26],{"name":14,"slug":15,"type":16},"Datasets","datasets","tag",{"name":18,"slug":19,"type":16},"LLM","llm",{"name":21,"slug":22,"type":16},"Data Quality","data-quality",{"name":24,"slug":25,"type":16},"QA","qa",{"name":27,"slug":28,"type":16},"AWS","aws",831,"https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fagent-plugins","2026-07-12T08:39:18.030117",null,127,[35,36,37,28,38,39],"agent-plugins","agent-skills","agents","coding-agent-skills","coding-agents",{"repoUrl":30,"stars":29,"forks":33,"topics":41,"description":42},[35,36,37,28,38,39],"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\u002Fdataset-evaluation","---\nname: dataset-evaluation\ndescription: Validates dataset formatting and quality for SageMaker model fine-tuning (SFT, DPO, or RLVR). Use when the user says \"is my dataset okay\", \"evaluate my data\", \"check my training data\", \"I have my own data\", or before starting any fine-tuning job. Detects file format, checks schema compliance against the selected model and technique, and reports whether the data is ready for training or evaluation.\nmetadata:\n  version: \"1.0.0\"\n---\n\n# Workflow Instruction\n\nFollow the workflow shown below. Locate the dataset, check the file type, and resolve any issues with missing files or wrong file types. Determine the fine-tuning model and fine-tuning strategy. Run the appropriate validation based on the model family. Summarize the results: is the dataset ready for fine-tuning?\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---\n\n## Workflow\n\n1. **Locate Dataset**:\n   - The full path may be a local file path, or an S3 URI\n   - Resolve the full path to the dataset file, make sure read permissions are available, and help the user if the file is not found\n\n2. **Determine strategy and model**:\n   - File formatting depends on the currently selected fine-tuning strategy and fine-tuning base model.\n   - If the strategy and model are already known from the conversation context (e.g., selected via the model-selection and finetuning-technique skills), use them.\n   - If not available in context, activate the model-selection and\u002For finetuning-technique skills to determine them before proceeding.\n   - **Exception:** If the user is validating an evaluation dataset (not a training dataset), neither model nor technique is required — the format detector can validate eval format (query\u002Fresponse structure) independently. Do not block on model-selection or finetuning-technique for eval dataset validation.\n\n3. **Check File Formatting**: Run the tool format_detector.py to make sure the file conforms to formatting requirements.\n   - Send the full path directly to the format_detector script as an argument\n   - Do not send the model and strategy as arguments\n   - Do not download data from S3\n   - Do not make local copies of data\n\n4. **Summarize Results**: Tell the user if their data is ready\n   - Examine the output of format_detector and compare to the known strategy and model\n   - **Important: training datasets and evaluation datasets have different format requirements.**\n     - **Training datasets** must match the fine-tuning strategy format per `references\u002Fstrategy_data_requirements.md`\n     - **Evaluation datasets** (for model evaluation) must match one of the [SageMaker evaluation dataset formats](https:\u002F\u002Fdocs.aws.amazon.com\u002Fsagemaker\u002Flatest\u002Fdg\u002Fmodel-customize-evaluation-dataset-formats.html).\n     - **Custom Scorer evaluation datasets** have scorer-specific requirements. If the dataset is intended for Custom Scorer evaluation (Prime Math, Prime Code, or Custom Lambda), read `references\u002Fcustom-scorer-evaluation-dataset-formats.md` and validate against the scorer-specific schema. The scorer type should be known from conversation context (determined in the model-evaluation skill).\n   - Report back to the user if their current dataset is valid for its intended purpose\n   - Warn the user if their dataset is valid, but for a different strategy or model\n   - Warn the user if their dataset is not valid for any strategy\u002Fmodel pair\n   - If the user plans to finetune a model with the evaluated dataset, it needs to be uploaded to an S3 bucket in the same region as the planned training job (usually the default region). Warn the user if this is NOT the case.\n   - If the dataset is NOT in the necessary format, recommend transforming it using the dataset-transformation skill, wait for user confirmation, and update the plan based on their response\n\n## Messages to the User\n\n- Introduction: \"This skill checks the structure of your dataset for model fine-tuning.\"\n- File types: This skill applies to files that are formatted according to the [Amazon SageMaker AI Developer Guide](https:\u002F\u002Fdocs.aws.amazon.com\u002Fsagemaker\u002Flatest\u002Fdg\u002Fautopilot-llms-finetuning-data-format.html#autopilot-llms-finetuning-dataset-format)\n\n# Resources\n\n- scripts\u002Fformat_detector.py is self-contained format validation script that can be run independently\n- model-selection and finetuning-technique skills should have already determined the base model and fine-tuning strategy\n- references\u002Fstrategy_data_requirements.md contains data format requirements per strategy\n\n## Script Details\n\n- scripts\u002Fformat_detector.py is self-contained format validation script that can be run independently:\n\n```bash\n# With the file path argument identified in workflow step 1\npython scripts\u002Fformat_detector.py local_path\u002Fto\u002Fdataset\n```\n\n## References\n\n- `scripts\u002Fformat_detector.py` — Self-contained format validation script\n- `references\u002Fstrategy_data_requirements.md` — Data format requirements per strategy\n",{"data":46,"body":49},{"name":4,"description":6,"metadata":47},{"version":48},"1.0.0",{"type":50,"children":51},"root",[52,61,67,74,93,97,103,310,316,336,342,360,366,374,418,424,448],{"type":53,"tag":54,"props":55,"children":57},"element","h1",{"id":56},"workflow-instruction",[58],{"type":59,"value":60},"text","Workflow Instruction",{"type":53,"tag":62,"props":63,"children":64},"p",{},[65],{"type":59,"value":66},"Follow the workflow shown below. Locate the dataset, check the file type, and resolve any issues with missing files or wrong file types. Determine the fine-tuning model and fine-tuning strategy. Run the appropriate validation based on the model family. Summarize the results: is the dataset ready for fine-tuning?",{"type":53,"tag":68,"props":69,"children":71},"h2",{"id":70},"prerequisites",[72],{"type":59,"value":73},"Prerequisites",{"type":53,"tag":75,"props":76,"children":77},"ul",{},[78],{"type":53,"tag":79,"props":80,"children":81},"li",{},[82,84,91],{"type":59,"value":83},"The SDK environment has been verified (SDK version, region, execution role). If not done, activate the ",{"type":53,"tag":85,"props":86,"children":88},"code",{"className":87},[],[89],{"type":59,"value":90},"sdk-getting-started",{"type":59,"value":92}," skill first.",{"type":53,"tag":94,"props":95,"children":96},"hr",{},[],{"type":53,"tag":68,"props":98,"children":100},{"id":99},"workflow",[101],{"type":59,"value":102},"Workflow",{"type":53,"tag":104,"props":105,"children":106},"ol",{},[107,131,168,201],{"type":53,"tag":79,"props":108,"children":109},{},[110,116,118],{"type":53,"tag":111,"props":112,"children":113},"strong",{},[114],{"type":59,"value":115},"Locate Dataset",{"type":59,"value":117},":",{"type":53,"tag":75,"props":119,"children":120},{},[121,126],{"type":53,"tag":79,"props":122,"children":123},{},[124],{"type":59,"value":125},"The full path may be a local file path, or an S3 URI",{"type":53,"tag":79,"props":127,"children":128},{},[129],{"type":59,"value":130},"Resolve the full path to the dataset file, make sure read permissions are available, and help the user if the file is not found",{"type":53,"tag":79,"props":132,"children":133},{},[134,139,140],{"type":53,"tag":111,"props":135,"children":136},{},[137],{"type":59,"value":138},"Determine strategy and model",{"type":59,"value":117},{"type":53,"tag":75,"props":141,"children":142},{},[143,148,153,158],{"type":53,"tag":79,"props":144,"children":145},{},[146],{"type":59,"value":147},"File formatting depends on the currently selected fine-tuning strategy and fine-tuning base model.",{"type":53,"tag":79,"props":149,"children":150},{},[151],{"type":59,"value":152},"If the strategy and model are already known from the conversation context (e.g., selected via the model-selection and finetuning-technique skills), use them.",{"type":53,"tag":79,"props":154,"children":155},{},[156],{"type":59,"value":157},"If not available in context, activate the model-selection and\u002For finetuning-technique skills to determine them before proceeding.",{"type":53,"tag":79,"props":159,"children":160},{},[161,166],{"type":53,"tag":111,"props":162,"children":163},{},[164],{"type":59,"value":165},"Exception:",{"type":59,"value":167}," If the user is validating an evaluation dataset (not a training dataset), neither model nor technique is required — the format detector can validate eval format (query\u002Fresponse structure) independently. Do not block on model-selection or finetuning-technique for eval dataset validation.",{"type":53,"tag":79,"props":169,"children":170},{},[171,176,178],{"type":53,"tag":111,"props":172,"children":173},{},[174],{"type":59,"value":175},"Check File Formatting",{"type":59,"value":177},": Run the tool format_detector.py to make sure the file conforms to formatting requirements.",{"type":53,"tag":75,"props":179,"children":180},{},[181,186,191,196],{"type":53,"tag":79,"props":182,"children":183},{},[184],{"type":59,"value":185},"Send the full path directly to the format_detector script as an argument",{"type":53,"tag":79,"props":187,"children":188},{},[189],{"type":59,"value":190},"Do not send the model and strategy as arguments",{"type":53,"tag":79,"props":192,"children":193},{},[194],{"type":59,"value":195},"Do not download data from S3",{"type":53,"tag":79,"props":197,"children":198},{},[199],{"type":59,"value":200},"Do not make local copies of data",{"type":53,"tag":79,"props":202,"children":203},{},[204,209,211],{"type":53,"tag":111,"props":205,"children":206},{},[207],{"type":59,"value":208},"Summarize Results",{"type":59,"value":210},": Tell the user if their data is ready",{"type":53,"tag":75,"props":212,"children":213},{},[214,219,285,290,295,300,305],{"type":53,"tag":79,"props":215,"children":216},{},[217],{"type":59,"value":218},"Examine the output of format_detector and compare to the known strategy and model",{"type":53,"tag":79,"props":220,"children":221},{},[222,227],{"type":53,"tag":111,"props":223,"children":224},{},[225],{"type":59,"value":226},"Important: training datasets and evaluation datasets have different format requirements.",{"type":53,"tag":75,"props":228,"children":229},{},[230,246,267],{"type":53,"tag":79,"props":231,"children":232},{},[233,238,240],{"type":53,"tag":111,"props":234,"children":235},{},[236],{"type":59,"value":237},"Training datasets",{"type":59,"value":239}," must match the fine-tuning strategy format per ",{"type":53,"tag":85,"props":241,"children":243},{"className":242},[],[244],{"type":59,"value":245},"references\u002Fstrategy_data_requirements.md",{"type":53,"tag":79,"props":247,"children":248},{},[249,254,256,265],{"type":53,"tag":111,"props":250,"children":251},{},[252],{"type":59,"value":253},"Evaluation datasets",{"type":59,"value":255}," (for model evaluation) must match one of the ",{"type":53,"tag":257,"props":258,"children":262},"a",{"href":259,"rel":260},"https:\u002F\u002Fdocs.aws.amazon.com\u002Fsagemaker\u002Flatest\u002Fdg\u002Fmodel-customize-evaluation-dataset-formats.html",[261],"nofollow",[263],{"type":59,"value":264},"SageMaker evaluation dataset formats",{"type":59,"value":266},".",{"type":53,"tag":79,"props":268,"children":269},{},[270,275,277,283],{"type":53,"tag":111,"props":271,"children":272},{},[273],{"type":59,"value":274},"Custom Scorer evaluation datasets",{"type":59,"value":276}," have scorer-specific requirements. If the dataset is intended for Custom Scorer evaluation (Prime Math, Prime Code, or Custom Lambda), read ",{"type":53,"tag":85,"props":278,"children":280},{"className":279},[],[281],{"type":59,"value":282},"references\u002Fcustom-scorer-evaluation-dataset-formats.md",{"type":59,"value":284}," and validate against the scorer-specific schema. The scorer type should be known from conversation context (determined in the model-evaluation skill).",{"type":53,"tag":79,"props":286,"children":287},{},[288],{"type":59,"value":289},"Report back to the user if their current dataset is valid for its intended purpose",{"type":53,"tag":79,"props":291,"children":292},{},[293],{"type":59,"value":294},"Warn the user if their dataset is valid, but for a different strategy or model",{"type":53,"tag":79,"props":296,"children":297},{},[298],{"type":59,"value":299},"Warn the user if their dataset is not valid for any strategy\u002Fmodel pair",{"type":53,"tag":79,"props":301,"children":302},{},[303],{"type":59,"value":304},"If the user plans to finetune a model with the evaluated dataset, it needs to be uploaded to an S3 bucket in the same region as the planned training job (usually the default region). Warn the user if this is NOT the case.",{"type":53,"tag":79,"props":306,"children":307},{},[308],{"type":59,"value":309},"If the dataset is NOT in the necessary format, recommend transforming it using the dataset-transformation skill, wait for user confirmation, and update the plan based on their response",{"type":53,"tag":68,"props":311,"children":313},{"id":312},"messages-to-the-user",[314],{"type":59,"value":315},"Messages to the User",{"type":53,"tag":75,"props":317,"children":318},{},[319,324],{"type":53,"tag":79,"props":320,"children":321},{},[322],{"type":59,"value":323},"Introduction: \"This skill checks the structure of your dataset for model fine-tuning.\"",{"type":53,"tag":79,"props":325,"children":326},{},[327,329],{"type":59,"value":328},"File types: This skill applies to files that are formatted according to the ",{"type":53,"tag":257,"props":330,"children":333},{"href":331,"rel":332},"https:\u002F\u002Fdocs.aws.amazon.com\u002Fsagemaker\u002Flatest\u002Fdg\u002Fautopilot-llms-finetuning-data-format.html#autopilot-llms-finetuning-dataset-format",[261],[334],{"type":59,"value":335},"Amazon SageMaker AI Developer Guide",{"type":53,"tag":54,"props":337,"children":339},{"id":338},"resources",[340],{"type":59,"value":341},"Resources",{"type":53,"tag":75,"props":343,"children":344},{},[345,350,355],{"type":53,"tag":79,"props":346,"children":347},{},[348],{"type":59,"value":349},"scripts\u002Fformat_detector.py is self-contained format validation script that can be run independently",{"type":53,"tag":79,"props":351,"children":352},{},[353],{"type":59,"value":354},"model-selection and finetuning-technique skills should have already determined the base model and fine-tuning strategy",{"type":53,"tag":79,"props":356,"children":357},{},[358],{"type":59,"value":359},"references\u002Fstrategy_data_requirements.md contains data format requirements per strategy",{"type":53,"tag":68,"props":361,"children":363},{"id":362},"script-details",[364],{"type":59,"value":365},"Script Details",{"type":53,"tag":75,"props":367,"children":368},{},[369],{"type":53,"tag":79,"props":370,"children":371},{},[372],{"type":59,"value":373},"scripts\u002Fformat_detector.py is self-contained format validation script that can be run independently:",{"type":53,"tag":375,"props":376,"children":381},"pre",{"className":377,"code":378,"language":379,"meta":380,"style":380},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","# With the file path argument identified in workflow step 1\npython scripts\u002Fformat_detector.py local_path\u002Fto\u002Fdataset\n","bash","",[382],{"type":53,"tag":85,"props":383,"children":384},{"__ignoreMap":380},[385,397],{"type":53,"tag":386,"props":387,"children":390},"span",{"class":388,"line":389},"line",1,[391],{"type":53,"tag":386,"props":392,"children":394},{"style":393},"--shiki-light:#90A4AE;--shiki-light-font-style:italic;--shiki-default:#546E7A;--shiki-default-font-style:italic;--shiki-dark:#676E95;--shiki-dark-font-style:italic",[395],{"type":59,"value":396},"# With the file path argument identified in workflow step 1\n",{"type":53,"tag":386,"props":398,"children":400},{"class":388,"line":399},2,[401,407,413],{"type":53,"tag":386,"props":402,"children":404},{"style":403},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[405],{"type":59,"value":406},"python",{"type":53,"tag":386,"props":408,"children":410},{"style":409},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[411],{"type":59,"value":412}," scripts\u002Fformat_detector.py",{"type":53,"tag":386,"props":414,"children":415},{"style":409},[416],{"type":59,"value":417}," local_path\u002Fto\u002Fdataset\n",{"type":53,"tag":68,"props":419,"children":421},{"id":420},"references",[422],{"type":59,"value":423},"References",{"type":53,"tag":75,"props":425,"children":426},{},[427,438],{"type":53,"tag":79,"props":428,"children":429},{},[430,436],{"type":53,"tag":85,"props":431,"children":433},{"className":432},[],[434],{"type":59,"value":435},"scripts\u002Fformat_detector.py",{"type":59,"value":437}," — Self-contained format validation script",{"type":53,"tag":79,"props":439,"children":440},{},[441,446],{"type":53,"tag":85,"props":442,"children":444},{"className":443},[],[445],{"type":59,"value":245},{"type":59,"value":447}," — Data format requirements per strategy",{"type":53,"tag":449,"props":450,"children":451},"style",{},[452],{"type":59,"value":453},"html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"items":455,"total":560},[456,473,493,505,522,535,545],{"slug":457,"name":457,"fn":458,"description":459,"org":460,"tags":461,"stars":29,"repoUrl":30,"updatedAt":472},"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},[462,465,466,469],{"name":463,"slug":464,"type":16},"API Development","api-development",{"name":27,"slug":28,"type":16},{"name":467,"slug":468,"type":16},"Maps","maps",{"name":470,"slug":471,"type":16},"Navigation","navigation","2026-07-12T08:39:49.88311",{"slug":474,"name":474,"fn":475,"description":476,"org":477,"tags":478,"stars":29,"repoUrl":30,"updatedAt":492},"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},[479,482,483,486,489],{"name":480,"slug":481,"type":16},"Auth","auth",{"name":27,"slug":28,"type":16},{"name":484,"slug":485,"type":16},"Database","database",{"name":487,"slug":488,"type":16},"Deployment","deployment",{"name":490,"slug":491,"type":16},"TypeScript","typescript","2026-07-12T08:39:43.500162",{"slug":494,"name":494,"fn":495,"description":496,"org":497,"tags":498,"stars":29,"repoUrl":30,"updatedAt":504},"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},[499,500,501],{"name":463,"slug":464,"type":16},{"name":27,"slug":28,"type":16},{"name":502,"slug":503,"type":16},"REST API","rest-api","2026-07-12T08:39:00.149339",{"slug":506,"name":506,"fn":507,"description":508,"org":509,"tags":510,"stars":29,"repoUrl":30,"updatedAt":521},"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},[511,514,515,518],{"name":512,"slug":513,"type":16},"Architecture","architecture",{"name":27,"slug":28,"type":16},{"name":516,"slug":517,"type":16},"Design","design",{"name":519,"slug":520,"type":16},"Diagrams","diagrams","2026-07-12T08:37:11.012278",{"slug":523,"name":523,"fn":524,"description":525,"org":526,"tags":527,"stars":29,"repoUrl":30,"updatedAt":534},"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},[528,529,530,531],{"name":463,"slug":464,"type":16},{"name":27,"slug":28,"type":16},{"name":487,"slug":488,"type":16},{"name":532,"slug":533,"type":16},"Serverless","serverless","2026-07-12T08:38:58.598492",{"slug":536,"name":536,"fn":537,"description":538,"org":539,"tags":540,"stars":29,"repoUrl":30,"updatedAt":544},"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},[541,542,543],{"name":512,"slug":513,"type":16},{"name":27,"slug":28,"type":16},{"name":532,"slug":533,"type":16},"2026-07-12T08:39:05.546173",{"slug":546,"name":546,"fn":547,"description":548,"org":549,"tags":550,"stars":29,"repoUrl":30,"updatedAt":559},"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},[551,552,553,556],{"name":27,"slug":28,"type":16},{"name":487,"slug":488,"type":16},{"name":554,"slug":555,"type":16},"Infrastructure","infrastructure",{"name":557,"slug":558,"type":16},"Performance","performance","2026-07-12T08:39:07.007071",33,{"items":562,"total":736},[563,582,599,609,622,635,645,655,676,691,706,721],{"slug":564,"name":564,"fn":565,"description":566,"org":567,"tags":568,"stars":579,"repoUrl":580,"updatedAt":581},"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},[569,570,573,576],{"name":27,"slug":28,"type":16},{"name":571,"slug":572,"type":16},"Debugging","debugging",{"name":574,"slug":575,"type":16},"Logs","logs",{"name":577,"slug":578,"type":16},"Observability","observability",9427,"https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fmcp","2026-07-12T08:37:22.601527",{"slug":583,"name":584,"fn":585,"description":586,"org":587,"tags":588,"stars":579,"repoUrl":580,"updatedAt":598},"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},[589,592,593,594,595],{"name":590,"slug":591,"type":16},"Aurora","aurora",{"name":27,"slug":28,"type":16},{"name":484,"slug":485,"type":16},{"name":532,"slug":533,"type":16},{"name":596,"slug":597,"type":16},"SQL","sql","2026-07-12T08:36:45.053393",{"slug":600,"name":601,"fn":585,"description":586,"org":602,"tags":603,"stars":579,"repoUrl":580,"updatedAt":608},"aurora-dsql","aurora dsql",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[604,605,606,607],{"name":27,"slug":28,"type":16},{"name":484,"slug":485,"type":16},{"name":532,"slug":533,"type":16},{"name":596,"slug":597,"type":16},"2026-07-12T08:36:42.694299",{"slug":610,"name":611,"fn":585,"description":586,"org":612,"tags":613,"stars":579,"repoUrl":580,"updatedAt":621},"aws-dsql","aws dsql",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[614,615,616,619,620],{"name":27,"slug":28,"type":16},{"name":484,"slug":485,"type":16},{"name":617,"slug":618,"type":16},"Migration","migration",{"name":532,"slug":533,"type":16},{"name":596,"slug":597,"type":16},"2026-07-12T08:36:38.584057",{"slug":623,"name":624,"fn":585,"description":586,"org":625,"tags":626,"stars":579,"repoUrl":580,"updatedAt":634},"distributed-postgres","distributed postgres",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[627,628,629,632,633],{"name":27,"slug":28,"type":16},{"name":484,"slug":485,"type":16},{"name":630,"slug":631,"type":16},"PostgreSQL","postgresql",{"name":532,"slug":533,"type":16},{"name":596,"slug":597,"type":16},"2026-07-12T08:36:46.530743",{"slug":636,"name":637,"fn":585,"description":586,"org":638,"tags":639,"stars":579,"repoUrl":580,"updatedAt":644},"distributed-sql","distributed sql",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[640,641,642,643],{"name":27,"slug":28,"type":16},{"name":484,"slug":485,"type":16},{"name":532,"slug":533,"type":16},{"name":596,"slug":597,"type":16},"2026-07-12T08:36:48.104182",{"slug":646,"name":646,"fn":585,"description":586,"org":647,"tags":648,"stars":579,"repoUrl":580,"updatedAt":654},"dsql",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[649,650,651,652,653],{"name":27,"slug":28,"type":16},{"name":484,"slug":485,"type":16},{"name":617,"slug":618,"type":16},{"name":532,"slug":533,"type":16},{"name":596,"slug":597,"type":16},"2026-07-12T08:36:36.374512",{"slug":656,"name":656,"fn":657,"description":658,"org":659,"tags":660,"stars":673,"repoUrl":674,"updatedAt":675},"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},[661,664,667,670],{"name":662,"slug":663,"type":16},"Accounting","accounting",{"name":665,"slug":666,"type":16},"Analytics","analytics",{"name":668,"slug":669,"type":16},"Cost Optimization","cost-optimization",{"name":671,"slug":672,"type":16},"Finance","finance",3176,"https:\u002F\u002Fgithub.com\u002Fawslabs\u002Fagentcore-samples","2026-07-12T08:40:03.29555",{"slug":677,"name":677,"fn":678,"description":679,"org":680,"tags":681,"stars":673,"repoUrl":674,"updatedAt":690},"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},[682,683,684,687],{"name":27,"slug":28,"type":16},{"name":671,"slug":672,"type":16},{"name":685,"slug":686,"type":16},"Management","management",{"name":688,"slug":689,"type":16},"Reporting","reporting","2026-07-12T08:40:02.066471",{"slug":692,"name":692,"fn":693,"description":694,"org":695,"tags":696,"stars":673,"repoUrl":674,"updatedAt":705},"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},[697,698,699,702],{"name":665,"slug":666,"type":16},{"name":671,"slug":672,"type":16},{"name":700,"slug":701,"type":16},"Financial Statements","financial-statements",{"name":703,"slug":704,"type":16},"Variance Analysis","variance-analysis","2026-07-12T08:40:00.79141",{"slug":707,"name":707,"fn":708,"description":709,"org":710,"tags":711,"stars":673,"repoUrl":674,"updatedAt":720},"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},[712,715,718],{"name":713,"slug":714,"type":16},"Automation","automation",{"name":716,"slug":717,"type":16},"Documents","documents",{"name":719,"slug":707,"type":16},"PDF","2026-07-12T08:41:44.135656",{"slug":722,"name":722,"fn":723,"description":724,"org":725,"tags":726,"stars":673,"repoUrl":674,"updatedAt":735},"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},[727,728,731,732],{"name":662,"slug":663,"type":16},{"name":729,"slug":730,"type":16},"Data Analysis","data-analysis",{"name":671,"slug":672,"type":16},{"name":733,"slug":734,"type":16},"KPI","kpi","2026-07-12T08:39:59.54971",150]