[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-aws-querying-data-lake":3,"mdc--9jrajj-key":35,"related-repo-aws-querying-data-lake":1023,"related-org-aws-querying-data-lake":1129},{"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},"querying-data-lake","execute SQL queries on AWS data lakes","Execute and manage Athena SQL queries across default and federated catalogs (Glue, S3 Tables, Redshift). Triggers on phrases like: query data, run SQL, athena query, analyze table, SQL query, workgroup status, profile table, query Redshift catalog, query S3 Tables. Do NOT use for finding specific data assets (use finding-data-lake-assets), full catalog audits (use exploring-data-catalog), importing data (use ingesting-into-data-lake).",{"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},"Data Engineering","data-engineering","tag",{"name":17,"slug":18,"type":15},"Data Analysis","data-analysis",{"name":20,"slug":21,"type":15},"SQL","sql",{"name":23,"slug":8,"type":15},"AWS",1822,"https:\u002F\u002Fgithub.com\u002Faws\u002Fagent-toolkit-for-aws","2026-07-12T08:43:21.369639",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\u002Fplugins\u002Faws-data-analytics\u002Fskills\u002Fquerying-data-lake","---\nname: querying-data-lake\ndescription: >-\n  Execute and manage Athena SQL queries across default and federated catalogs (Glue,\n  S3 Tables, Redshift). Triggers on phrases like: query data, run SQL, athena query,\n  analyze table, SQL query, workgroup status, profile table, query Redshift catalog,\n  query S3 Tables. Do NOT use for finding specific data assets (use finding-data-lake-assets),\n  full catalog audits (use exploring-data-catalog), importing data (use ingesting-into-data-lake).\nversion: 1\nargument-hint: '[SQL-query|query-name|workgroup-name|catalog-name|''profile TABLE_NAME'']'\n---\n\n# Query Data Lake\n\nExecute SQL queries on Amazon Athena across default and federated catalogs (Glue, S3 Tables, Redshift) with workgroup selection, statement classification, and error recovery.\n\n## Overview\n\nExecutes and manages Athena SQL queries across default and federated catalogs. Selects a workgroup, resolves target assets (delegating fuzzy references to `finding-data-lake-assets`), classifies statements for safety, and reports cost and data scanned. Use the AWS MCP server for sandboxed execution and audit logging; the same AWS CLI commands work directly when the MCP server is not available.\n\n**Constraints for parameter acquisition:**\n\n- You MUST accept a single optional argument: SQL text, a named-query name, a workgroup name, a catalog name, or `profile TABLE_NAME`\n- You MUST accept the argument as direct text or a pointer to a file containing SQL\n- You MUST ask the user for the target AWS region if not already set\n- You MUST confirm the output S3 location before executing any non-trivial query\n- You MUST respect the user's decision to abort at any step\n\n## Common Tasks\n\n### 1. Verify Dependencies\n\nCheck for required tools and AWS access before running queries.\n\n**Constraints:**\n\n- You MUST verify AWS MCP server tools are available (`aws___call_aws`) and run queries through them when present; fall back to AWS CLI only if the MCP server is unavailable\n- You MUST NOT fall back to shell or Bash for query execution — results must be captured via the MCP tool or `aws athena` CLI so output location and cost are tracked\n- You MUST confirm credentials with `aws sts get-caller-identity` and inform the user about any missing tools\n\n### 2. Resolve Workgroup\n\nCheck caller identity, list workgroups, auto-select the best one (see [workgroup-selection.md](references\u002Fworkgroup-selection.md)).\n\n**Constraints:**\n\n- You MUST select a workgroup before submitting any query (prevents output-location errors)\n- You MUST present the selected workgroup and its output location to the user\n- You MUST NOT auto-escalate to a different workgroup on failure without user confirmation\n\n### 3. Resolve the Target Asset\n\nIf the user refers to a table by name, by business concept (\"our quarterly report\", \"the sales data\"), by S3 path, or by catalog without specifying the table, delegate to `finding-data-lake-assets` to return the concrete `database.table` (and catalog if non-default).\n\n**Constraints:**\n\n- You MUST NOT attempt to resolve fuzzy asset references with `athena list-data-catalogs` or by iterating `get-tables` — those miss federated catalogs and waste tokens\n- You SHOULD skip this step only when the user provides a fully-qualified reference (exact `database.table`) or raw SQL they want executed as-is\n- You MUST state the resolved asset explicitly before building the query: \"Found [table] in [catalog]. Using this for the query.\"\n- You SHOULD default to the default Glue catalog unless the user mentions \"federated\", \"Redshift\", \"S3 Tables\", or `finding-data-lake-assets` returns a different catalog\n\n### 4. Discover Schema\n\nFor analytical queries, You SHOULD profile the target table before building the final query. You MUST show sample rows (`SELECT ... LIMIT 5`) as part of profiling.\n\n### 5. Build Query\n\nTable addressing depends on catalog type:\n\n- Default Glue catalog: `database.table` (omit the catalog prefix for single-catalog queries). In cross-catalog queries, qualify default-catalog tables with `\"awsdatacatalog\".database.table`.\n- Registered data source: `datasource.database.table`\n- Unregistered Glue catalog: `\"catalog\u002Fsubcatalog\".database.table`\n\n### 6. Classify and Execute\n\nClassify the SQL statement before executing:\n\n| Statement | Behavior |\n|---|---|\n| `SELECT`, `SHOW`, `DESCRIBE`, `EXPLAIN` | Safe — execute |\n| `INSERT`, `UPDATE`, `DELETE`, `DROP`, `ALTER`, `CREATE`, `TRUNCATE`, `MERGE` | Destructive — warn the user and require explicit confirmation |\n| Unsure | Treat as destructive; confirm |\n\nExample tool call (via AWS MCP server):\n\n```\naws___call_aws(command=\"aws athena start-query-execution --work-group \u003CWORKGROUP_NAME> --query-string '\u003Csql>' --query-execution-context Database=\u003Cdb>\")\n```\n\nFor federated or S3 Tables catalogs, also set `Catalog=\u003CCATALOG_PATH>` in the execution context (e.g. `Catalog=s3tablescatalog\u002F\u003CBUCKET_NAME>`).\n\n**Constraints:**\n\n- You MUST warn the user before executing when the target is Redshift-federated (\"No partition pruning — every query scans the full table\")\n- You MUST warn the user before executing a cross-catalog join (\"Cross-catalog joins incur network overhead and may be slow\")\n- You MUST confirm the output S3 location before executing\n- You MUST explain which tool is being called before executing\n- You MUST respect the user's decision to abort\n\n### 7. Present and Recover\n\nPresent results with cost, data scanned, duration, and actionable insights. On failure, list available workgroups and let the user choose which to retry with.\n\n### Argument Routing\n\nResolve in this order; stop at the first match:\n\n1. Contains SQL keywords (`SELECT`, `SHOW`, `DESCRIBE`, `INSERT`, etc.) — SQL text, execute directly\n2. `profile TABLE_NAME` — run comprehensive table profiling (see [query-patterns.md](references\u002Fquery-patterns.md))\n3. Matches a known named query — look up and execute\n4. Matches a known workgroup — show workgroup status and recent queries\n5. Matches a known catalog — delegate to `exploring-data-catalog` to enumerate databases and tables\n6. No args — show recent query activity and available tables\n\n### Principles\n\n- Always select workgroup before executing (prevents output-location errors)\n- Profile unfamiliar tables before running analytical queries\n- Present cost alongside results so users build cost awareness\n- Suggest `LIMIT` for exploratory queries on large tables\n- Never ask domain questions with obvious answers, but always confirm security-relevant actions (workgroup switches, output location changes, non-SELECT statements)\n\n## Troubleshooting\n\n| Error | Cause | Fix |\n|---|---|---|\n| Redshift identifier error with mixed case | Redshift-federated names are lowercase only | Lowercase the identifier |\n| `CatalogId` validation failure | ARN passed instead of catalog name | Pass the catalog name, not the ARN |\n| Cross-catalog `information_schema` returns nothing | Missing catalog qualifier | Use catalog-qualified path: `\"catalog\".information_schema.tables` |\n| Query fails with output-location error | Workgroup has no output location configured | Select a different workgroup with an output location, or configure one |\n| Destructive statement executed without confirmation | Statement classification skipped | Always classify `INSERT`\u002F`UPDATE`\u002F`DELETE`\u002F`DROP`\u002F`ALTER`\u002F`CREATE`\u002F`TRUNCATE`\u002F`MERGE` and confirm with the user |\n\n## Additional Resources\n\n- [Workgroup selection logic](references\u002Fworkgroup-selection.md)\n- [Common query patterns](references\u002Fquery-patterns.md)\n- [Athena best practices](https:\u002F\u002Fdocs.aws.amazon.com\u002Fathena\u002Flatest\u002Fug\u002Fperformance-tuning.html)\n- [Athena federated query](https:\u002F\u002Fdocs.aws.amazon.com\u002Fathena\u002Flatest\u002Fug\u002Fconnect-to-a-data-source.html)\n",{"data":36,"body":39},{"name":4,"description":6,"version":37,"argument-hint":38},1,"[SQL-query|query-name|workgroup-name|catalog-name|'profile TABLE_NAME']",{"type":40,"children":41},"root",[42,51,57,64,78,87,123,129,136,141,149,191,197,211,218,236,242,262,269,337,343,356,362,367,412,418,423,568,573,585,605,612,640,646,651,657,662,742,748,784,790,977,983],{"type":43,"tag":44,"props":45,"children":47},"element","h1",{"id":46},"query-data-lake",[48],{"type":49,"value":50},"text","Query Data Lake",{"type":43,"tag":52,"props":53,"children":54},"p",{},[55],{"type":49,"value":56},"Execute SQL queries on Amazon Athena across default and federated catalogs (Glue, S3 Tables, Redshift) with workgroup selection, statement classification, and error recovery.",{"type":43,"tag":58,"props":59,"children":61},"h2",{"id":60},"overview",[62],{"type":49,"value":63},"Overview",{"type":43,"tag":52,"props":65,"children":66},{},[67,69,76],{"type":49,"value":68},"Executes and manages Athena SQL queries across default and federated catalogs. Selects a workgroup, resolves target assets (delegating fuzzy references to ",{"type":43,"tag":70,"props":71,"children":73},"code",{"className":72},[],[74],{"type":49,"value":75},"finding-data-lake-assets",{"type":49,"value":77},"), classifies statements for safety, and reports cost and data scanned. Use the AWS MCP server for sandboxed execution and audit logging; the same AWS CLI commands work directly when the MCP server is not available.",{"type":43,"tag":52,"props":79,"children":80},{},[81],{"type":43,"tag":82,"props":83,"children":84},"strong",{},[85],{"type":49,"value":86},"Constraints for parameter acquisition:",{"type":43,"tag":88,"props":89,"children":90},"ul",{},[91,103,108,113,118],{"type":43,"tag":92,"props":93,"children":94},"li",{},[95,97],{"type":49,"value":96},"You MUST accept a single optional argument: SQL text, a named-query name, a workgroup name, a catalog name, or ",{"type":43,"tag":70,"props":98,"children":100},{"className":99},[],[101],{"type":49,"value":102},"profile TABLE_NAME",{"type":43,"tag":92,"props":104,"children":105},{},[106],{"type":49,"value":107},"You MUST accept the argument as direct text or a pointer to a file containing SQL",{"type":43,"tag":92,"props":109,"children":110},{},[111],{"type":49,"value":112},"You MUST ask the user for the target AWS region if not already set",{"type":43,"tag":92,"props":114,"children":115},{},[116],{"type":49,"value":117},"You MUST confirm the output S3 location before executing any non-trivial query",{"type":43,"tag":92,"props":119,"children":120},{},[121],{"type":49,"value":122},"You MUST respect the user's decision to abort at any step",{"type":43,"tag":58,"props":124,"children":126},{"id":125},"common-tasks",[127],{"type":49,"value":128},"Common Tasks",{"type":43,"tag":130,"props":131,"children":133},"h3",{"id":132},"_1-verify-dependencies",[134],{"type":49,"value":135},"1. Verify Dependencies",{"type":43,"tag":52,"props":137,"children":138},{},[139],{"type":49,"value":140},"Check for required tools and AWS access before running queries.",{"type":43,"tag":52,"props":142,"children":143},{},[144],{"type":43,"tag":82,"props":145,"children":146},{},[147],{"type":49,"value":148},"Constraints:",{"type":43,"tag":88,"props":150,"children":151},{},[152,165,178],{"type":43,"tag":92,"props":153,"children":154},{},[155,157,163],{"type":49,"value":156},"You MUST verify AWS MCP server tools are available (",{"type":43,"tag":70,"props":158,"children":160},{"className":159},[],[161],{"type":49,"value":162},"aws___call_aws",{"type":49,"value":164},") and run queries through them when present; fall back to AWS CLI only if the MCP server is unavailable",{"type":43,"tag":92,"props":166,"children":167},{},[168,170,176],{"type":49,"value":169},"You MUST NOT fall back to shell or Bash for query execution — results must be captured via the MCP tool or ",{"type":43,"tag":70,"props":171,"children":173},{"className":172},[],[174],{"type":49,"value":175},"aws athena",{"type":49,"value":177}," CLI so output location and cost are tracked",{"type":43,"tag":92,"props":179,"children":180},{},[181,183,189],{"type":49,"value":182},"You MUST confirm credentials with ",{"type":43,"tag":70,"props":184,"children":186},{"className":185},[],[187],{"type":49,"value":188},"aws sts get-caller-identity",{"type":49,"value":190}," and inform the user about any missing tools",{"type":43,"tag":130,"props":192,"children":194},{"id":193},"_2-resolve-workgroup",[195],{"type":49,"value":196},"2. Resolve Workgroup",{"type":43,"tag":52,"props":198,"children":199},{},[200,202,209],{"type":49,"value":201},"Check caller identity, list workgroups, auto-select the best one (see ",{"type":43,"tag":203,"props":204,"children":206},"a",{"href":205},"references\u002Fworkgroup-selection.md",[207],{"type":49,"value":208},"workgroup-selection.md",{"type":49,"value":210},").",{"type":43,"tag":52,"props":212,"children":213},{},[214],{"type":43,"tag":82,"props":215,"children":216},{},[217],{"type":49,"value":148},{"type":43,"tag":88,"props":219,"children":220},{},[221,226,231],{"type":43,"tag":92,"props":222,"children":223},{},[224],{"type":49,"value":225},"You MUST select a workgroup before submitting any query (prevents output-location errors)",{"type":43,"tag":92,"props":227,"children":228},{},[229],{"type":49,"value":230},"You MUST present the selected workgroup and its output location to the user",{"type":43,"tag":92,"props":232,"children":233},{},[234],{"type":49,"value":235},"You MUST NOT auto-escalate to a different workgroup on failure without user confirmation",{"type":43,"tag":130,"props":237,"children":239},{"id":238},"_3-resolve-the-target-asset",[240],{"type":49,"value":241},"3. Resolve the Target Asset",{"type":43,"tag":52,"props":243,"children":244},{},[245,247,252,254,260],{"type":49,"value":246},"If the user refers to a table by name, by business concept (\"our quarterly report\", \"the sales data\"), by S3 path, or by catalog without specifying the table, delegate to ",{"type":43,"tag":70,"props":248,"children":250},{"className":249},[],[251],{"type":49,"value":75},{"type":49,"value":253}," to return the concrete ",{"type":43,"tag":70,"props":255,"children":257},{"className":256},[],[258],{"type":49,"value":259},"database.table",{"type":49,"value":261}," (and catalog if non-default).",{"type":43,"tag":52,"props":263,"children":264},{},[265],{"type":43,"tag":82,"props":266,"children":267},{},[268],{"type":49,"value":148},{"type":43,"tag":88,"props":270,"children":271},{},[272,293,305,325],{"type":43,"tag":92,"props":273,"children":274},{},[275,277,283,285,291],{"type":49,"value":276},"You MUST NOT attempt to resolve fuzzy asset references with ",{"type":43,"tag":70,"props":278,"children":280},{"className":279},[],[281],{"type":49,"value":282},"athena list-data-catalogs",{"type":49,"value":284}," or by iterating ",{"type":43,"tag":70,"props":286,"children":288},{"className":287},[],[289],{"type":49,"value":290},"get-tables",{"type":49,"value":292}," — those miss federated catalogs and waste tokens",{"type":43,"tag":92,"props":294,"children":295},{},[296,298,303],{"type":49,"value":297},"You SHOULD skip this step only when the user provides a fully-qualified reference (exact ",{"type":43,"tag":70,"props":299,"children":301},{"className":300},[],[302],{"type":49,"value":259},{"type":49,"value":304},") or raw SQL they want executed as-is",{"type":43,"tag":92,"props":306,"children":307},{},[308,310,316,318,323],{"type":49,"value":309},"You MUST state the resolved asset explicitly before building the query: \"Found ",{"type":43,"tag":311,"props":312,"children":313},"span",{},[314],{"type":49,"value":315},"table",{"type":49,"value":317}," in ",{"type":43,"tag":311,"props":319,"children":320},{},[321],{"type":49,"value":322},"catalog",{"type":49,"value":324},". Using this for the query.\"",{"type":43,"tag":92,"props":326,"children":327},{},[328,330,335],{"type":49,"value":329},"You SHOULD default to the default Glue catalog unless the user mentions \"federated\", \"Redshift\", \"S3 Tables\", or ",{"type":43,"tag":70,"props":331,"children":333},{"className":332},[],[334],{"type":49,"value":75},{"type":49,"value":336}," returns a different catalog",{"type":43,"tag":130,"props":338,"children":340},{"id":339},"_4-discover-schema",[341],{"type":49,"value":342},"4. Discover Schema",{"type":43,"tag":52,"props":344,"children":345},{},[346,348,354],{"type":49,"value":347},"For analytical queries, You SHOULD profile the target table before building the final query. You MUST show sample rows (",{"type":43,"tag":70,"props":349,"children":351},{"className":350},[],[352],{"type":49,"value":353},"SELECT ... LIMIT 5",{"type":49,"value":355},") as part of profiling.",{"type":43,"tag":130,"props":357,"children":359},{"id":358},"_5-build-query",[360],{"type":49,"value":361},"5. Build Query",{"type":43,"tag":52,"props":363,"children":364},{},[365],{"type":49,"value":366},"Table addressing depends on catalog type:",{"type":43,"tag":88,"props":368,"children":369},{},[370,390,401],{"type":43,"tag":92,"props":371,"children":372},{},[373,375,380,382,388],{"type":49,"value":374},"Default Glue catalog: ",{"type":43,"tag":70,"props":376,"children":378},{"className":377},[],[379],{"type":49,"value":259},{"type":49,"value":381}," (omit the catalog prefix for single-catalog queries). In cross-catalog queries, qualify default-catalog tables with ",{"type":43,"tag":70,"props":383,"children":385},{"className":384},[],[386],{"type":49,"value":387},"\"awsdatacatalog\".database.table",{"type":49,"value":389},".",{"type":43,"tag":92,"props":391,"children":392},{},[393,395],{"type":49,"value":394},"Registered data source: ",{"type":43,"tag":70,"props":396,"children":398},{"className":397},[],[399],{"type":49,"value":400},"datasource.database.table",{"type":43,"tag":92,"props":402,"children":403},{},[404,406],{"type":49,"value":405},"Unregistered Glue catalog: ",{"type":43,"tag":70,"props":407,"children":409},{"className":408},[],[410],{"type":49,"value":411},"\"catalog\u002Fsubcatalog\".database.table",{"type":43,"tag":130,"props":413,"children":415},{"id":414},"_6-classify-and-execute",[416],{"type":49,"value":417},"6. Classify and Execute",{"type":43,"tag":52,"props":419,"children":420},{},[421],{"type":49,"value":422},"Classify the SQL statement before executing:",{"type":43,"tag":315,"props":424,"children":425},{},[426,445],{"type":43,"tag":427,"props":428,"children":429},"thead",{},[430],{"type":43,"tag":431,"props":432,"children":433},"tr",{},[434,440],{"type":43,"tag":435,"props":436,"children":437},"th",{},[438],{"type":49,"value":439},"Statement",{"type":43,"tag":435,"props":441,"children":442},{},[443],{"type":49,"value":444},"Behavior",{"type":43,"tag":446,"props":447,"children":448},"tbody",{},[449,489,555],{"type":43,"tag":431,"props":450,"children":451},{},[452,484],{"type":43,"tag":453,"props":454,"children":455},"td",{},[456,462,464,470,471,477,478],{"type":43,"tag":70,"props":457,"children":459},{"className":458},[],[460],{"type":49,"value":461},"SELECT",{"type":49,"value":463},", ",{"type":43,"tag":70,"props":465,"children":467},{"className":466},[],[468],{"type":49,"value":469},"SHOW",{"type":49,"value":463},{"type":43,"tag":70,"props":472,"children":474},{"className":473},[],[475],{"type":49,"value":476},"DESCRIBE",{"type":49,"value":463},{"type":43,"tag":70,"props":479,"children":481},{"className":480},[],[482],{"type":49,"value":483},"EXPLAIN",{"type":43,"tag":453,"props":485,"children":486},{},[487],{"type":49,"value":488},"Safe — execute",{"type":43,"tag":431,"props":490,"children":491},{},[492,550],{"type":43,"tag":453,"props":493,"children":494},{},[495,501,502,508,509,515,516,522,523,529,530,536,537,543,544],{"type":43,"tag":70,"props":496,"children":498},{"className":497},[],[499],{"type":49,"value":500},"INSERT",{"type":49,"value":463},{"type":43,"tag":70,"props":503,"children":505},{"className":504},[],[506],{"type":49,"value":507},"UPDATE",{"type":49,"value":463},{"type":43,"tag":70,"props":510,"children":512},{"className":511},[],[513],{"type":49,"value":514},"DELETE",{"type":49,"value":463},{"type":43,"tag":70,"props":517,"children":519},{"className":518},[],[520],{"type":49,"value":521},"DROP",{"type":49,"value":463},{"type":43,"tag":70,"props":524,"children":526},{"className":525},[],[527],{"type":49,"value":528},"ALTER",{"type":49,"value":463},{"type":43,"tag":70,"props":531,"children":533},{"className":532},[],[534],{"type":49,"value":535},"CREATE",{"type":49,"value":463},{"type":43,"tag":70,"props":538,"children":540},{"className":539},[],[541],{"type":49,"value":542},"TRUNCATE",{"type":49,"value":463},{"type":43,"tag":70,"props":545,"children":547},{"className":546},[],[548],{"type":49,"value":549},"MERGE",{"type":43,"tag":453,"props":551,"children":552},{},[553],{"type":49,"value":554},"Destructive — warn the user and require explicit confirmation",{"type":43,"tag":431,"props":556,"children":557},{},[558,563],{"type":43,"tag":453,"props":559,"children":560},{},[561],{"type":49,"value":562},"Unsure",{"type":43,"tag":453,"props":564,"children":565},{},[566],{"type":49,"value":567},"Treat as destructive; confirm",{"type":43,"tag":52,"props":569,"children":570},{},[571],{"type":49,"value":572},"Example tool call (via AWS MCP server):",{"type":43,"tag":574,"props":575,"children":579},"pre",{"className":576,"code":578,"language":49},[577],"language-text","aws___call_aws(command=\"aws athena start-query-execution --work-group \u003CWORKGROUP_NAME> --query-string '\u003Csql>' --query-execution-context Database=\u003Cdb>\")\n",[580],{"type":43,"tag":70,"props":581,"children":583},{"__ignoreMap":582},"",[584],{"type":49,"value":578},{"type":43,"tag":52,"props":586,"children":587},{},[588,590,596,598,604],{"type":49,"value":589},"For federated or S3 Tables catalogs, also set ",{"type":43,"tag":70,"props":591,"children":593},{"className":592},[],[594],{"type":49,"value":595},"Catalog=\u003CCATALOG_PATH>",{"type":49,"value":597}," in the execution context (e.g. ",{"type":43,"tag":70,"props":599,"children":601},{"className":600},[],[602],{"type":49,"value":603},"Catalog=s3tablescatalog\u002F\u003CBUCKET_NAME>",{"type":49,"value":210},{"type":43,"tag":52,"props":606,"children":607},{},[608],{"type":43,"tag":82,"props":609,"children":610},{},[611],{"type":49,"value":148},{"type":43,"tag":88,"props":613,"children":614},{},[615,620,625,630,635],{"type":43,"tag":92,"props":616,"children":617},{},[618],{"type":49,"value":619},"You MUST warn the user before executing when the target is Redshift-federated (\"No partition pruning — every query scans the full table\")",{"type":43,"tag":92,"props":621,"children":622},{},[623],{"type":49,"value":624},"You MUST warn the user before executing a cross-catalog join (\"Cross-catalog joins incur network overhead and may be slow\")",{"type":43,"tag":92,"props":626,"children":627},{},[628],{"type":49,"value":629},"You MUST confirm the output S3 location before executing",{"type":43,"tag":92,"props":631,"children":632},{},[633],{"type":49,"value":634},"You MUST explain which tool is being called before executing",{"type":43,"tag":92,"props":636,"children":637},{},[638],{"type":49,"value":639},"You MUST respect the user's decision to abort",{"type":43,"tag":130,"props":641,"children":643},{"id":642},"_7-present-and-recover",[644],{"type":49,"value":645},"7. Present and Recover",{"type":43,"tag":52,"props":647,"children":648},{},[649],{"type":49,"value":650},"Present results with cost, data scanned, duration, and actionable insights. On failure, list available workgroups and let the user choose which to retry with.",{"type":43,"tag":130,"props":652,"children":654},{"id":653},"argument-routing",[655],{"type":49,"value":656},"Argument Routing",{"type":43,"tag":52,"props":658,"children":659},{},[660],{"type":49,"value":661},"Resolve in this order; stop at the first match:",{"type":43,"tag":663,"props":664,"children":665},"ol",{},[666,696,714,719,724,737],{"type":43,"tag":92,"props":667,"children":668},{},[669,671,676,677,682,683,688,689,694],{"type":49,"value":670},"Contains SQL keywords (",{"type":43,"tag":70,"props":672,"children":674},{"className":673},[],[675],{"type":49,"value":461},{"type":49,"value":463},{"type":43,"tag":70,"props":678,"children":680},{"className":679},[],[681],{"type":49,"value":469},{"type":49,"value":463},{"type":43,"tag":70,"props":684,"children":686},{"className":685},[],[687],{"type":49,"value":476},{"type":49,"value":463},{"type":43,"tag":70,"props":690,"children":692},{"className":691},[],[693],{"type":49,"value":500},{"type":49,"value":695},", etc.) — SQL text, execute directly",{"type":43,"tag":92,"props":697,"children":698},{},[699,704,706,712],{"type":43,"tag":70,"props":700,"children":702},{"className":701},[],[703],{"type":49,"value":102},{"type":49,"value":705}," — run comprehensive table profiling (see ",{"type":43,"tag":203,"props":707,"children":709},{"href":708},"references\u002Fquery-patterns.md",[710],{"type":49,"value":711},"query-patterns.md",{"type":49,"value":713},")",{"type":43,"tag":92,"props":715,"children":716},{},[717],{"type":49,"value":718},"Matches a known named query — look up and execute",{"type":43,"tag":92,"props":720,"children":721},{},[722],{"type":49,"value":723},"Matches a known workgroup — show workgroup status and recent queries",{"type":43,"tag":92,"props":725,"children":726},{},[727,729,735],{"type":49,"value":728},"Matches a known catalog — delegate to ",{"type":43,"tag":70,"props":730,"children":732},{"className":731},[],[733],{"type":49,"value":734},"exploring-data-catalog",{"type":49,"value":736}," to enumerate databases and tables",{"type":43,"tag":92,"props":738,"children":739},{},[740],{"type":49,"value":741},"No args — show recent query activity and available tables",{"type":43,"tag":130,"props":743,"children":745},{"id":744},"principles",[746],{"type":49,"value":747},"Principles",{"type":43,"tag":88,"props":749,"children":750},{},[751,756,761,766,779],{"type":43,"tag":92,"props":752,"children":753},{},[754],{"type":49,"value":755},"Always select workgroup before executing (prevents output-location errors)",{"type":43,"tag":92,"props":757,"children":758},{},[759],{"type":49,"value":760},"Profile unfamiliar tables before running analytical queries",{"type":43,"tag":92,"props":762,"children":763},{},[764],{"type":49,"value":765},"Present cost alongside results so users build cost awareness",{"type":43,"tag":92,"props":767,"children":768},{},[769,771,777],{"type":49,"value":770},"Suggest ",{"type":43,"tag":70,"props":772,"children":774},{"className":773},[],[775],{"type":49,"value":776},"LIMIT",{"type":49,"value":778}," for exploratory queries on large tables",{"type":43,"tag":92,"props":780,"children":781},{},[782],{"type":49,"value":783},"Never ask domain questions with obvious answers, but always confirm security-relevant actions (workgroup switches, output location changes, non-SELECT statements)",{"type":43,"tag":58,"props":785,"children":787},{"id":786},"troubleshooting",[788],{"type":49,"value":789},"Troubleshooting",{"type":43,"tag":315,"props":791,"children":792},{},[793,814],{"type":43,"tag":427,"props":794,"children":795},{},[796],{"type":43,"tag":431,"props":797,"children":798},{},[799,804,809],{"type":43,"tag":435,"props":800,"children":801},{},[802],{"type":49,"value":803},"Error",{"type":43,"tag":435,"props":805,"children":806},{},[807],{"type":49,"value":808},"Cause",{"type":43,"tag":435,"props":810,"children":811},{},[812],{"type":49,"value":813},"Fix",{"type":43,"tag":446,"props":815,"children":816},{},[817,835,859,891,909],{"type":43,"tag":431,"props":818,"children":819},{},[820,825,830],{"type":43,"tag":453,"props":821,"children":822},{},[823],{"type":49,"value":824},"Redshift identifier error with mixed case",{"type":43,"tag":453,"props":826,"children":827},{},[828],{"type":49,"value":829},"Redshift-federated names are lowercase only",{"type":43,"tag":453,"props":831,"children":832},{},[833],{"type":49,"value":834},"Lowercase the identifier",{"type":43,"tag":431,"props":836,"children":837},{},[838,849,854],{"type":43,"tag":453,"props":839,"children":840},{},[841,847],{"type":43,"tag":70,"props":842,"children":844},{"className":843},[],[845],{"type":49,"value":846},"CatalogId",{"type":49,"value":848}," validation failure",{"type":43,"tag":453,"props":850,"children":851},{},[852],{"type":49,"value":853},"ARN passed instead of catalog name",{"type":43,"tag":453,"props":855,"children":856},{},[857],{"type":49,"value":858},"Pass the catalog name, not the ARN",{"type":43,"tag":431,"props":860,"children":861},{},[862,875,880],{"type":43,"tag":453,"props":863,"children":864},{},[865,867,873],{"type":49,"value":866},"Cross-catalog ",{"type":43,"tag":70,"props":868,"children":870},{"className":869},[],[871],{"type":49,"value":872},"information_schema",{"type":49,"value":874}," returns nothing",{"type":43,"tag":453,"props":876,"children":877},{},[878],{"type":49,"value":879},"Missing catalog qualifier",{"type":43,"tag":453,"props":881,"children":882},{},[883,885],{"type":49,"value":884},"Use catalog-qualified path: ",{"type":43,"tag":70,"props":886,"children":888},{"className":887},[],[889],{"type":49,"value":890},"\"catalog\".information_schema.tables",{"type":43,"tag":431,"props":892,"children":893},{},[894,899,904],{"type":43,"tag":453,"props":895,"children":896},{},[897],{"type":49,"value":898},"Query fails with output-location error",{"type":43,"tag":453,"props":900,"children":901},{},[902],{"type":49,"value":903},"Workgroup has no output location configured",{"type":43,"tag":453,"props":905,"children":906},{},[907],{"type":49,"value":908},"Select a different workgroup with an output location, or configure one",{"type":43,"tag":431,"props":910,"children":911},{},[912,917,922],{"type":43,"tag":453,"props":913,"children":914},{},[915],{"type":49,"value":916},"Destructive statement executed without confirmation",{"type":43,"tag":453,"props":918,"children":919},{},[920],{"type":49,"value":921},"Statement classification skipped",{"type":43,"tag":453,"props":923,"children":924},{},[925,927,932,934,939,940,945,946,951,952,957,958,963,964,969,970,975],{"type":49,"value":926},"Always classify ",{"type":43,"tag":70,"props":928,"children":930},{"className":929},[],[931],{"type":49,"value":500},{"type":49,"value":933},"\u002F",{"type":43,"tag":70,"props":935,"children":937},{"className":936},[],[938],{"type":49,"value":507},{"type":49,"value":933},{"type":43,"tag":70,"props":941,"children":943},{"className":942},[],[944],{"type":49,"value":514},{"type":49,"value":933},{"type":43,"tag":70,"props":947,"children":949},{"className":948},[],[950],{"type":49,"value":521},{"type":49,"value":933},{"type":43,"tag":70,"props":953,"children":955},{"className":954},[],[956],{"type":49,"value":528},{"type":49,"value":933},{"type":43,"tag":70,"props":959,"children":961},{"className":960},[],[962],{"type":49,"value":535},{"type":49,"value":933},{"type":43,"tag":70,"props":965,"children":967},{"className":966},[],[968],{"type":49,"value":542},{"type":49,"value":933},{"type":43,"tag":70,"props":971,"children":973},{"className":972},[],[974],{"type":49,"value":549},{"type":49,"value":976}," and confirm with the user",{"type":43,"tag":58,"props":978,"children":980},{"id":979},"additional-resources",[981],{"type":49,"value":982},"Additional Resources",{"type":43,"tag":88,"props":984,"children":985},{},[986,994,1002,1013],{"type":43,"tag":92,"props":987,"children":988},{},[989],{"type":43,"tag":203,"props":990,"children":991},{"href":205},[992],{"type":49,"value":993},"Workgroup selection logic",{"type":43,"tag":92,"props":995,"children":996},{},[997],{"type":43,"tag":203,"props":998,"children":999},{"href":708},[1000],{"type":49,"value":1001},"Common query patterns",{"type":43,"tag":92,"props":1003,"children":1004},{},[1005],{"type":43,"tag":203,"props":1006,"children":1010},{"href":1007,"rel":1008},"https:\u002F\u002Fdocs.aws.amazon.com\u002Fathena\u002Flatest\u002Fug\u002Fperformance-tuning.html",[1009],"nofollow",[1011],{"type":49,"value":1012},"Athena best practices",{"type":43,"tag":92,"props":1014,"children":1015},{},[1016],{"type":43,"tag":203,"props":1017,"children":1020},{"href":1018,"rel":1019},"https:\u002F\u002Fdocs.aws.amazon.com\u002Fathena\u002Flatest\u002Fug\u002Fconnect-to-a-data-source.html",[1009],[1021],{"type":49,"value":1022},"Athena federated query",{"items":1024,"total":1128},[1025,1042,1057,1072,1087,1097,1112],{"slug":1026,"name":1026,"fn":1027,"description":1028,"org":1029,"tags":1030,"stars":24,"repoUrl":25,"updatedAt":1041},"agents-build","add capabilities to existing agent projects","Use when adding capabilities to an existing agent project — memory, app integration, VPC, multi-agent, migration, model changes, browser, code interpreter, or resource removal. Triggers on: \"add memory\", \"remember across sessions\", \"call agent from app\", \"invoke agent from code\", \"auth to call agent\", \"streaming responses\", \"VPC\", \"VPC connectivity\", \"VPC error\", \"can't reach from VPC\", \"multi-agent\", \"A2A\", \"A2A auth\", \"orchestrator not delegating\", \"specialist not called\", \"migrate Bedrock Agent\", \"after import\", \"migration issue\", \"framework for migration\", \"change model\", \"browser tool\", \"code interpreter\", \"delete agent\", \"tear down\", \"agentcore remove\", \"cross-account memory\", \"resource-based policy on memory\", \"pay for x402 content\", \"402 Payment Required\", \"microtransactions\", \"paid API or tool\". Not for connecting to external APIs via Gateway — use agents-connect. Not for scaffolding a new project — use agents-get-started. Not for CLI\u002Fdev server errors — use agents-debug. Strands vs LangGraph in a migration context routes here.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1031,1034,1037,1038],{"name":1032,"slug":1033,"type":15},"Agents","agents",{"name":1035,"slug":1036,"type":15},"Automation","automation",{"name":23,"slug":8,"type":15},{"name":1039,"slug":1040,"type":15},"Engineering","engineering","2026-07-12T08:42:53.812877",{"slug":1043,"name":1043,"fn":1044,"description":1045,"org":1046,"tags":1047,"stars":24,"repoUrl":25,"updatedAt":1056},"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},[1048,1049,1052,1055],{"name":1032,"slug":1033,"type":15},{"name":1050,"slug":1051,"type":15},"API Development","api-development",{"name":1053,"slug":1054,"type":15},"Authentication","authentication",{"name":23,"slug":8,"type":15},"2026-07-16T06:00:38.866147",{"slug":1058,"name":1058,"fn":1059,"description":1060,"org":1061,"tags":1062,"stars":24,"repoUrl":25,"updatedAt":1071},"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},[1063,1064,1065,1068],{"name":1032,"slug":1033,"type":15},{"name":23,"slug":8,"type":15},{"name":1066,"slug":1067,"type":15},"Debugging","debugging",{"name":1069,"slug":1070,"type":15},"Observability","observability","2026-07-16T06:00:44.679093",{"slug":1073,"name":1073,"fn":1074,"description":1075,"org":1076,"tags":1077,"stars":24,"repoUrl":25,"updatedAt":1086},"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},[1078,1079,1080,1083],{"name":1032,"slug":1033,"type":15},{"name":23,"slug":8,"type":15},{"name":1081,"slug":1082,"type":15},"CI\u002FCD","ci-cd",{"name":1084,"slug":1085,"type":15},"Deployment","deployment","2026-07-12T08:42:55.059577",{"slug":1088,"name":1088,"fn":1089,"description":1090,"org":1091,"tags":1092,"stars":24,"repoUrl":25,"updatedAt":1096},"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},[1093,1094,1095],{"name":1032,"slug":1033,"type":15},{"name":23,"slug":8,"type":15},{"name":1084,"slug":1085,"type":15},"2026-07-12T08:42:51.963247",{"slug":1098,"name":1098,"fn":1099,"description":1100,"org":1101,"tags":1102,"stars":24,"repoUrl":25,"updatedAt":1111},"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},[1103,1104,1105,1108],{"name":1032,"slug":1033,"type":15},{"name":23,"slug":8,"type":15},{"name":1106,"slug":1107,"type":15},"Best Practices","best-practices",{"name":1109,"slug":1110,"type":15},"Security","security","2026-07-16T06:00:42.174705",{"slug":1113,"name":1113,"fn":1114,"description":1115,"org":1116,"tags":1117,"stars":24,"repoUrl":25,"updatedAt":1127},"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},[1118,1119,1120,1123,1124],{"name":1032,"slug":1033,"type":15},{"name":23,"slug":8,"type":15},{"name":1121,"slug":1122,"type":15},"Evals","evals",{"name":1069,"slug":1070,"type":15},{"name":1125,"slug":1126,"type":15},"Performance","performance","2026-07-12T08:42:56.488105",114,{"items":1130,"total":1247},[1131,1138,1145,1152,1159,1165,1172,1180,1197,1210,1222,1237],{"slug":1026,"name":1026,"fn":1027,"description":1028,"org":1132,"tags":1133,"stars":24,"repoUrl":25,"updatedAt":1041},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1134,1135,1136,1137],{"name":1032,"slug":1033,"type":15},{"name":1035,"slug":1036,"type":15},{"name":23,"slug":8,"type":15},{"name":1039,"slug":1040,"type":15},{"slug":1043,"name":1043,"fn":1044,"description":1045,"org":1139,"tags":1140,"stars":24,"repoUrl":25,"updatedAt":1056},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1141,1142,1143,1144],{"name":1032,"slug":1033,"type":15},{"name":1050,"slug":1051,"type":15},{"name":1053,"slug":1054,"type":15},{"name":23,"slug":8,"type":15},{"slug":1058,"name":1058,"fn":1059,"description":1060,"org":1146,"tags":1147,"stars":24,"repoUrl":25,"updatedAt":1071},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1148,1149,1150,1151],{"name":1032,"slug":1033,"type":15},{"name":23,"slug":8,"type":15},{"name":1066,"slug":1067,"type":15},{"name":1069,"slug":1070,"type":15},{"slug":1073,"name":1073,"fn":1074,"description":1075,"org":1153,"tags":1154,"stars":24,"repoUrl":25,"updatedAt":1086},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1155,1156,1157,1158],{"name":1032,"slug":1033,"type":15},{"name":23,"slug":8,"type":15},{"name":1081,"slug":1082,"type":15},{"name":1084,"slug":1085,"type":15},{"slug":1088,"name":1088,"fn":1089,"description":1090,"org":1160,"tags":1161,"stars":24,"repoUrl":25,"updatedAt":1096},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1162,1163,1164],{"name":1032,"slug":1033,"type":15},{"name":23,"slug":8,"type":15},{"name":1084,"slug":1085,"type":15},{"slug":1098,"name":1098,"fn":1099,"description":1100,"org":1166,"tags":1167,"stars":24,"repoUrl":25,"updatedAt":1111},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1168,1169,1170,1171],{"name":1032,"slug":1033,"type":15},{"name":23,"slug":8,"type":15},{"name":1106,"slug":1107,"type":15},{"name":1109,"slug":1110,"type":15},{"slug":1113,"name":1113,"fn":1114,"description":1115,"org":1173,"tags":1174,"stars":24,"repoUrl":25,"updatedAt":1127},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1175,1176,1177,1178,1179],{"name":1032,"slug":1033,"type":15},{"name":23,"slug":8,"type":15},{"name":1121,"slug":1122,"type":15},{"name":1069,"slug":1070,"type":15},{"name":1125,"slug":1126,"type":15},{"slug":1181,"name":1181,"fn":1182,"description":1183,"org":1184,"tags":1185,"stars":24,"repoUrl":25,"updatedAt":1196},"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},[1186,1187,1190,1193],{"name":23,"slug":8,"type":15},{"name":1188,"slug":1189,"type":15},"Database","database",{"name":1191,"slug":1192,"type":15},"MySQL","mysql",{"name":1194,"slug":1195,"type":15},"Serverless","serverless","2026-07-12T08:43:13.27939",{"slug":1198,"name":1198,"fn":1199,"description":1200,"org":1201,"tags":1202,"stars":24,"repoUrl":25,"updatedAt":1209},"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},[1203,1204,1205,1208],{"name":23,"slug":8,"type":15},{"name":1188,"slug":1189,"type":15},{"name":1206,"slug":1207,"type":15},"PostgreSQL","postgresql",{"name":1194,"slug":1195,"type":15},"2026-07-16T06:00:34.789624",{"slug":1211,"name":1211,"fn":1212,"description":1213,"org":1214,"tags":1215,"stars":24,"repoUrl":25,"updatedAt":1221},"amazon-bedrock","build generative AI apps with Amazon Bedrock","Builds generative AI applications on Amazon Bedrock. Covers model invocation (Converse API, InvokeModel), RAG with Knowledge Bases, Bedrock Agents, Guardrails, and AgentCore. Use when invoking models, setting up Knowledge Bases, creating agents, applying guardrails, deploying to AgentCore, migrating\u002Fporting\u002Fconverting a Bedrock Agent (including inline agents) to an AgentCore Harness, troubleshooting Bedrock errors (ThrottlingException, AccessDeniedException), or choosing models (Claude, Llama, Nova, Titan). ALSO USE for prompt caching setup and debugging, quota health checks and throttling diagnosis, cost attribution and tracking, migrating between Claude model generations (4.5 to 4.6 to 4.7), chunking strategies, API selection (Converse vs InvokeModel), guardrail capabilities, and model selection. Also covers AgentCore Payments setup (x402, microtransactions, Payment Manager, Connector, Instrument, Coinbase CDP, Stripe Privy, 402 Payment Required, pay for content, paid endpoint, agent payments). NOT for custom model training, Rekognition, or Comprehend.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1216,1217,1218],{"name":1032,"slug":1033,"type":15},{"name":23,"slug":8,"type":15},{"name":1219,"slug":1220,"type":15},"LLM","llm","2026-07-25T05:30:35.20899",{"slug":1223,"name":1223,"fn":1224,"description":1225,"org":1226,"tags":1227,"stars":24,"repoUrl":25,"updatedAt":1236},"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},[1228,1229,1230,1233],{"name":23,"slug":8,"type":15},{"name":1188,"slug":1189,"type":15},{"name":1231,"slug":1232,"type":15},"MongoDB","mongodb",{"name":1234,"slug":1235,"type":15},"NoSQL","nosql","2026-07-12T08:43:00.455878",{"slug":1238,"name":1238,"fn":1239,"description":1240,"org":1241,"tags":1242,"stars":24,"repoUrl":25,"updatedAt":1246},"amazon-dynamodb","design and debug DynamoDB data layers","Designs, reviews, and debugs DynamoDB data layers from design axioms — enumerates access patterns, chooses partition\u002Fsort keys and GSIs, decides single-table vs. multi-table, configures Streams, Global Tables, TTL, and zero-ETL integrations to OpenSearch\u002FRedshift\u002FSageMaker Lakehouse, and produces a defensible data-layer design with a monthly cost estimate and optional live validation. Applies whenever a user is designing, reviewing, or refactoring anything backed by DynamoDB — schemas, access patterns, GSIs, single- vs. multi-table choices, Streams consumers, transactional outboxes, Global Tables, zero-ETL pipelines — even when they don't say \"axioms\" or \"design review.\" Also applies when debugging hot partitions, throttling, unbounded Scans, LWW conflicts, or surprise bills on DynamoDB workloads.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1243,1244,1245],{"name":23,"slug":8,"type":15},{"name":1188,"slug":1189,"type":15},{"name":1234,"slug":1235,"type":15},"2026-07-16T06:00:37.690386",115]