[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-aws-durable-insight":3,"mdc--ebwi4x-key":35,"related-org-aws-durable-insight":321,"related-repo-aws-durable-insight":496},{"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},"durable-insight","query AWS Lambda execution history","Query AWS Lambda durable function execution history through the durable-insight MCP server — use when investigating workflow failures, execution timing, or step-level errors across DynamoDB, Athena\u002FS3, Aurora, Redshift, OpenSearch, or CloudWatch Logs destinations.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"aws","AWS (Amazon)","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Faws.png",[12,16,19,21],{"name":13,"slug":14,"type":15},"Observability","observability","tag",{"name":17,"slug":18,"type":15},"MCP","mcp",{"name":20,"slug":8,"type":15},"AWS",{"name":22,"slug":23,"type":15},"Debugging","debugging",85,"https:\u002F\u002Fgithub.com\u002Faws\u002Faws-durable-execution-sdk-js","2026-08-14T04:51:57.49997",null,27,[],{"repoUrl":25,"stars":24,"forks":28,"topics":31,"description":32},[],"Lambda durable functions SDK, Testing SDK and fully functional examples","https:\u002F\u002Fgithub.com\u002Faws\u002Faws-durable-execution-sdk-js\u002Ftree\u002FHEAD\u002Fpackages\u002Faws-durable-execution-sdk-js-insight-mcp\u002Fsrc\u002Fskill","---\nname: durable-insight\ndescription: Query AWS Lambda durable function execution history through the durable-insight MCP server — use when investigating workflow failures, execution timing, or step-level errors across DynamoDB, Athena\u002FS3, Aurora, Redshift, OpenSearch, or CloudWatch Logs destinations.\n---\n\n# Durable Insight\n\nThe durable-insight MCP server gives you READ-ONLY access to the execution\nhistory that AWS Lambda durable functions emit to a configured destination. Use\nit to investigate failures, timing, and step-level errors. The destination is\nchosen by the operator through `DURABLE_INSIGHT_*` environment variables; you do\nnot pick it and must not assume which one is in play.\n\n## The one rule that makes this skill correct: ask the server for the schema\n\nThis skill deliberately contains ZERO destination-specific schema facts — no\nfield names, no column casing, no dialect syntax. That is not an omission; it is\nthe design:\n\n- **Drift becomes impossible, not merely detectable.** Any schema prose copied\n  here would silently rot the moment the server's schema changed. There is\n  nothing to keep in sync because there is nothing duplicated.\n- **Token economy.** One destination's guidance alone is over ten thousand\n  characters. Inlining every destination's schema would load all of it on every\n  invocation, whether or not you are on that destination.\n- **Correctness.** Only the running server knows the configured destination. A\n  static file would have to hedge across every backend and would be wrong for\n  six of them at any given moment.\n\nSo: **call `describe_schema` before you write a `query`.** It returns the record\nfields and query idioms for whatever destination is actually configured,\nauthoritatively. Writing a query without it is guessing.\n\n## The five tools, and when to reach for each\n\n- `test_destination` — Run first. Confirms the destination is reachable and its\n  configuration is complete. If required environment variables are unset it\n  names them and returns without any AWS call. Stop and report if it fails.\n- `describe_schema` — Call before any `query`. Returns the configured\n  destination's record schema, query engine\u002Fdialect, the table or log group in\n  play, and the row cap. Makes no AWS call, so it is safe even before setup is\n  complete.\n- `list_executions` — The common case: list executions filtered by any of\n  status, functionName, since, and until, with no SQL required. Prefer this over\n  a hand-written `query` — it cannot be got wrong and costs fewer tokens.\n- `get_execution` — Fetch a single execution record by its execution ARN. A\n  record that does not exist is a success with found=false, not an error.\n- `query` — Escape hatch for questions the structured tools cannot express. Only\n  after `describe_schema`, so field names and syntax match the destination.\n\n## Guarantees and limits you can rely on\n\n- **Read-only.** For the SQL destinations, any statement that is not a\n  SELECT\u002FWITH is refused before any AWS call is made; the CloudWatch Logs query\n  language has no write forms at all. You cannot mutate data through this server.\n- **Row cap.** Every result is capped at a fixed maximum row count (MAX_ROWS,\n  currently 1000). A truncated flag tells you when the cap was hit — narrow\n  your filters rather than assuming you saw everything.\n- **Log destinations need a lookback window.** CloudWatch Logs queries have no\n  \"all time\"; pass a lookback window (hours) or accept the 24-hour default. This\n  is ignored by the SQL destinations, which are not time-windowed.\n\n## Suggested order for a failure investigation\n\n1. `test_destination` — confirm reachability and configuration.\n2. `describe_schema` — learn this destination's fields and idioms.\n3. `list_executions` — narrow to the executions of interest (start with FAILED).\n4. `get_execution` — drill into a specific record for step-level detail.\n5. `query` — only when the structured tools cannot express the question.\n",{"data":36,"body":37},{"name":4,"description":6},{"type":38,"children":39},"root",[40,48,63,70,75,111,139,145,222,228,261,267],{"type":41,"tag":42,"props":43,"children":44},"element","h1",{"id":4},[45],{"type":46,"value":47},"text","Durable Insight",{"type":41,"tag":49,"props":50,"children":51},"p",{},[52,54,61],{"type":46,"value":53},"The durable-insight MCP server gives you READ-ONLY access to the execution\nhistory that AWS Lambda durable functions emit to a configured destination. Use\nit to investigate failures, timing, and step-level errors. The destination is\nchosen by the operator through ",{"type":41,"tag":55,"props":56,"children":58},"code",{"className":57},[],[59],{"type":46,"value":60},"DURABLE_INSIGHT_*",{"type":46,"value":62}," environment variables; you do\nnot pick it and must not assume which one is in play.",{"type":41,"tag":64,"props":65,"children":67},"h2",{"id":66},"the-one-rule-that-makes-this-skill-correct-ask-the-server-for-the-schema",[68],{"type":46,"value":69},"The one rule that makes this skill correct: ask the server for the schema",{"type":41,"tag":49,"props":71,"children":72},{},[73],{"type":46,"value":74},"This skill deliberately contains ZERO destination-specific schema facts — no\nfield names, no column casing, no dialect syntax. That is not an omission; it is\nthe design:",{"type":41,"tag":76,"props":77,"children":78},"ul",{},[79,91,101],{"type":41,"tag":80,"props":81,"children":82},"li",{},[83,89],{"type":41,"tag":84,"props":85,"children":86},"strong",{},[87],{"type":46,"value":88},"Drift becomes impossible, not merely detectable.",{"type":46,"value":90}," Any schema prose copied\nhere would silently rot the moment the server's schema changed. There is\nnothing to keep in sync because there is nothing duplicated.",{"type":41,"tag":80,"props":92,"children":93},{},[94,99],{"type":41,"tag":84,"props":95,"children":96},{},[97],{"type":46,"value":98},"Token economy.",{"type":46,"value":100}," One destination's guidance alone is over ten thousand\ncharacters. Inlining every destination's schema would load all of it on every\ninvocation, whether or not you are on that destination.",{"type":41,"tag":80,"props":102,"children":103},{},[104,109],{"type":41,"tag":84,"props":105,"children":106},{},[107],{"type":46,"value":108},"Correctness.",{"type":46,"value":110}," Only the running server knows the configured destination. A\nstatic file would have to hedge across every backend and would be wrong for\nsix of them at any given moment.",{"type":41,"tag":49,"props":112,"children":113},{},[114,116,137],{"type":46,"value":115},"So: ",{"type":41,"tag":84,"props":117,"children":118},{},[119,121,127,129,135],{"type":46,"value":120},"call ",{"type":41,"tag":55,"props":122,"children":124},{"className":123},[],[125],{"type":46,"value":126},"describe_schema",{"type":46,"value":128}," before you write a ",{"type":41,"tag":55,"props":130,"children":132},{"className":131},[],[133],{"type":46,"value":134},"query",{"type":46,"value":136},".",{"type":46,"value":138}," It returns the record\nfields and query idioms for whatever destination is actually configured,\nauthoritatively. Writing a query without it is guessing.",{"type":41,"tag":64,"props":140,"children":142},{"id":141},"the-five-tools-and-when-to-reach-for-each",[143],{"type":46,"value":144},"The five tools, and when to reach for each",{"type":41,"tag":76,"props":146,"children":147},{},[148,159,176,194,205],{"type":41,"tag":80,"props":149,"children":150},{},[151,157],{"type":41,"tag":55,"props":152,"children":154},{"className":153},[],[155],{"type":46,"value":156},"test_destination",{"type":46,"value":158}," — Run first. Confirms the destination is reachable and its\nconfiguration is complete. If required environment variables are unset it\nnames them and returns without any AWS call. Stop and report if it fails.",{"type":41,"tag":80,"props":160,"children":161},{},[162,167,169,174],{"type":41,"tag":55,"props":163,"children":165},{"className":164},[],[166],{"type":46,"value":126},{"type":46,"value":168}," — Call before any ",{"type":41,"tag":55,"props":170,"children":172},{"className":171},[],[173],{"type":46,"value":134},{"type":46,"value":175},". Returns the configured\ndestination's record schema, query engine\u002Fdialect, the table or log group in\nplay, and the row cap. Makes no AWS call, so it is safe even before setup is\ncomplete.",{"type":41,"tag":80,"props":177,"children":178},{},[179,185,187,192],{"type":41,"tag":55,"props":180,"children":182},{"className":181},[],[183],{"type":46,"value":184},"list_executions",{"type":46,"value":186}," — The common case: list executions filtered by any of\nstatus, functionName, since, and until, with no SQL required. Prefer this over\na hand-written ",{"type":41,"tag":55,"props":188,"children":190},{"className":189},[],[191],{"type":46,"value":134},{"type":46,"value":193}," — it cannot be got wrong and costs fewer tokens.",{"type":41,"tag":80,"props":195,"children":196},{},[197,203],{"type":41,"tag":55,"props":198,"children":200},{"className":199},[],[201],{"type":46,"value":202},"get_execution",{"type":46,"value":204}," — Fetch a single execution record by its execution ARN. A\nrecord that does not exist is a success with found=false, not an error.",{"type":41,"tag":80,"props":206,"children":207},{},[208,213,215,220],{"type":41,"tag":55,"props":209,"children":211},{"className":210},[],[212],{"type":46,"value":134},{"type":46,"value":214}," — Escape hatch for questions the structured tools cannot express. Only\nafter ",{"type":41,"tag":55,"props":216,"children":218},{"className":217},[],[219],{"type":46,"value":126},{"type":46,"value":221},", so field names and syntax match the destination.",{"type":41,"tag":64,"props":223,"children":225},{"id":224},"guarantees-and-limits-you-can-rely-on",[226],{"type":46,"value":227},"Guarantees and limits you can rely on",{"type":41,"tag":76,"props":229,"children":230},{},[231,241,251],{"type":41,"tag":80,"props":232,"children":233},{},[234,239],{"type":41,"tag":84,"props":235,"children":236},{},[237],{"type":46,"value":238},"Read-only.",{"type":46,"value":240}," For the SQL destinations, any statement that is not a\nSELECT\u002FWITH is refused before any AWS call is made; the CloudWatch Logs query\nlanguage has no write forms at all. You cannot mutate data through this server.",{"type":41,"tag":80,"props":242,"children":243},{},[244,249],{"type":41,"tag":84,"props":245,"children":246},{},[247],{"type":46,"value":248},"Row cap.",{"type":46,"value":250}," Every result is capped at a fixed maximum row count (MAX_ROWS,\ncurrently 1000). A truncated flag tells you when the cap was hit — narrow\nyour filters rather than assuming you saw everything.",{"type":41,"tag":80,"props":252,"children":253},{},[254,259],{"type":41,"tag":84,"props":255,"children":256},{},[257],{"type":46,"value":258},"Log destinations need a lookback window.",{"type":46,"value":260}," CloudWatch Logs queries have no\n\"all time\"; pass a lookback window (hours) or accept the 24-hour default. This\nis ignored by the SQL destinations, which are not time-windowed.",{"type":41,"tag":64,"props":262,"children":264},{"id":263},"suggested-order-for-a-failure-investigation",[265],{"type":46,"value":266},"Suggested order for a failure investigation",{"type":41,"tag":268,"props":269,"children":270},"ol",{},[271,281,291,301,311],{"type":41,"tag":80,"props":272,"children":273},{},[274,279],{"type":41,"tag":55,"props":275,"children":277},{"className":276},[],[278],{"type":46,"value":156},{"type":46,"value":280}," — confirm reachability and configuration.",{"type":41,"tag":80,"props":282,"children":283},{},[284,289],{"type":41,"tag":55,"props":285,"children":287},{"className":286},[],[288],{"type":46,"value":126},{"type":46,"value":290}," — learn this destination's fields and idioms.",{"type":41,"tag":80,"props":292,"children":293},{},[294,299],{"type":41,"tag":55,"props":295,"children":297},{"className":296},[],[298],{"type":46,"value":184},{"type":46,"value":300}," — narrow to the executions of interest (start with FAILED).",{"type":41,"tag":80,"props":302,"children":303},{},[304,309],{"type":41,"tag":55,"props":305,"children":307},{"className":306},[],[308],{"type":46,"value":202},{"type":46,"value":310}," — drill into a specific record for step-level detail.",{"type":41,"tag":80,"props":312,"children":313},{},[314,319],{"type":41,"tag":55,"props":315,"children":317},{"className":316},[],[318],{"type":46,"value":134},{"type":46,"value":320}," — only when the structured tools cannot express the question.",{"items":322,"total":495},[323,342,357,368,383,393,408,424,438,455,468,480],{"slug":324,"name":324,"fn":325,"description":326,"org":327,"tags":328,"stars":339,"repoUrl":340,"updatedAt":341},"agents-build","add capabilities to existing agent projects","Use to extend an existing agent project with memory, app integration, VPC, multi-agent, migration, model, browser, code interpreter, payments, or resource removal. Triggers: \"add memory\", \"remember across sessions\", \"call agent from app\", \"invoke agent from code\", \"agent auth\", \"streaming\", \"VPC\", \"VPC connectivity\", \"can't reach from VPC\", \"multi-agent\", \"A2A\", \"A2A auth\", \"orchestrator not delegating\", \"specialist not called\", \"migrate Bedrock Agent\", \"migration issue\", \"change model\", \"browser tool\", \"code interpreter\", \"delete agent\", \"tear down\", \"agentcore remove\", \"cross-account memory\", \"add payments capability to my agent\", \"wire payments plugin\", \"payments middleware for my agent\", \"integrate x402 payments with the agent I'm building\", \"enable my agent project with x402 payments\". External APIs via Gateway: use agents-connect. New project: use agents-get-started. CLI\u002Fdev-server errors: use agents-debug. Runtime x402 payments: use agents-pay. Migration-specific Strands vs LangGraph routes here.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[329,332,335,336],{"name":330,"slug":331,"type":15},"Agents","agents",{"name":333,"slug":334,"type":15},"Automation","automation",{"name":20,"slug":8,"type":15},{"name":337,"slug":338,"type":15},"Engineering","engineering",1822,"https:\u002F\u002Fgithub.com\u002Faws\u002Fagent-toolkit-for-aws","2026-08-07T04:38:08.981896",{"slug":343,"name":343,"fn":344,"description":345,"org":346,"tags":347,"stars":339,"repoUrl":340,"updatedAt":356},"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},[348,349,352,355],{"name":330,"slug":331,"type":15},{"name":350,"slug":351,"type":15},"API Development","api-development",{"name":353,"slug":354,"type":15},"Authentication","authentication",{"name":20,"slug":8,"type":15},"2026-07-16T06:00:38.866147",{"slug":358,"name":358,"fn":359,"description":360,"org":361,"tags":362,"stars":339,"repoUrl":340,"updatedAt":367},"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},[363,364,365,366],{"name":330,"slug":331,"type":15},{"name":20,"slug":8,"type":15},{"name":22,"slug":23,"type":15},{"name":13,"slug":14,"type":15},"2026-07-16T06:00:44.679093",{"slug":369,"name":369,"fn":370,"description":371,"org":372,"tags":373,"stars":339,"repoUrl":340,"updatedAt":382},"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},[374,375,376,379],{"name":330,"slug":331,"type":15},{"name":20,"slug":8,"type":15},{"name":377,"slug":378,"type":15},"CI\u002FCD","ci-cd",{"name":380,"slug":381,"type":15},"Deployment","deployment","2026-07-12T08:42:55.059577",{"slug":384,"name":384,"fn":385,"description":386,"org":387,"tags":388,"stars":339,"repoUrl":340,"updatedAt":392},"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},[389,390,391],{"name":330,"slug":331,"type":15},{"name":20,"slug":8,"type":15},{"name":380,"slug":381,"type":15},"2026-07-12T08:42:51.963247",{"slug":394,"name":394,"fn":395,"description":396,"org":397,"tags":398,"stars":339,"repoUrl":340,"updatedAt":407},"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},[399,400,401,404],{"name":330,"slug":331,"type":15},{"name":20,"slug":8,"type":15},{"name":402,"slug":403,"type":15},"Best Practices","best-practices",{"name":405,"slug":406,"type":15},"Security","security","2026-07-16T06:00:42.174705",{"slug":409,"name":409,"fn":410,"description":411,"org":412,"tags":413,"stars":339,"repoUrl":340,"updatedAt":423},"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},[414,415,416,419,420],{"name":330,"slug":331,"type":15},{"name":20,"slug":8,"type":15},{"name":417,"slug":418,"type":15},"Evals","evals",{"name":13,"slug":14,"type":15},{"name":421,"slug":422,"type":15},"Performance","performance","2026-07-12T08:42:56.488105",{"slug":425,"name":425,"fn":426,"description":427,"org":428,"tags":429,"stars":339,"repoUrl":340,"updatedAt":437},"agents-pay","handle x402 payments for agent tasks","Use when THIS agent needs to pay for x402-protected content at runtime: hitting a paywall mid-task, settling it via AgentCore Payments, and applying operator-defined spend limits. Covers payment setup, policy, session budgets, and troubleshooting. Triggers on: \"my agent hit a 402 while calling an API\", \"a tool call returned 402 Payment Required\", \"my agent needs to pay for x402-protected content\", \"let the agent pay for content, capped at $5 per session\", \"set a spend limit for the agent\", \"ProcessPayment failed\", or \"why did my agent refuse to pay\". Not for BUILDING payment capability for end users, including wallets and framework middleware; use agents-build and references\u002Fpayments.md. For non-paid APIs via Gateway use agents-connect. For inbound auth use agents-harden. For project scaffolding use agents-get-started.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[430,431,432,435],{"name":330,"slug":331,"type":15},{"name":333,"slug":334,"type":15},{"name":433,"slug":434,"type":15},"Payments","payments",{"name":436,"slug":436,"type":15},"x402","2026-08-10T04:16:31.844309",{"slug":439,"name":439,"fn":440,"description":441,"org":442,"tags":443,"stars":339,"repoUrl":340,"updatedAt":454},"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},[444,445,448,451],{"name":20,"slug":8,"type":15},{"name":446,"slug":447,"type":15},"Database","database",{"name":449,"slug":450,"type":15},"MySQL","mysql",{"name":452,"slug":453,"type":15},"Serverless","serverless","2026-07-12T08:43:13.27939",{"slug":456,"name":456,"fn":457,"description":458,"org":459,"tags":460,"stars":339,"repoUrl":340,"updatedAt":467},"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},[461,462,463,466],{"name":20,"slug":8,"type":15},{"name":446,"slug":447,"type":15},{"name":464,"slug":465,"type":15},"PostgreSQL","postgresql",{"name":452,"slug":453,"type":15},"2026-07-16T06:00:34.789624",{"slug":469,"name":469,"fn":470,"description":471,"org":472,"tags":473,"stars":339,"repoUrl":340,"updatedAt":479},"amazon-bedrock","build generative AI apps with Amazon Bedrock","Builds generative AI applications on Amazon Bedrock. Covers model invocation (Converse API, InvokeModel), RAG with Knowledge Bases, Bedrock Agents, Guardrails, and AgentCore (including the Harness managed agent loop). Use when invoking models, setting up Knowledge Bases, creating agents, applying guardrails, deploying to AgentCore, migrating\u002Fporting\u002Fconverting a Bedrock Agent (including inline agents) to an AgentCore Harness, troubleshooting Bedrock errors (ThrottlingException, AccessDeniedException), or choosing models (Claude, Llama, Nova, Titan). ALSO USE for prompt caching, quota health checks and throttling diagnosis, cost attribution, migrating between Claude model generations, chunking strategies, API selection (Converse vs InvokeModel), and model selection. Also covers AgentCore Payments setup (x402, microtransactions, Payment Manager, Coinbase CDP, Stripe Privy, 402 Payment Required, paid endpoint). NOT for custom model training, Rekognition, or Comprehend.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[474,475,476],{"name":330,"slug":331,"type":15},{"name":20,"slug":8,"type":15},{"name":477,"slug":478,"type":15},"LLM","llm","2026-08-07T04:38:13.03499",{"slug":481,"name":481,"fn":482,"description":483,"org":484,"tags":485,"stars":339,"repoUrl":340,"updatedAt":494},"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},[486,487,488,491],{"name":20,"slug":8,"type":15},{"name":446,"slug":447,"type":15},{"name":489,"slug":490,"type":15},"MongoDB","mongodb",{"name":492,"slug":493,"type":15},"NoSQL","nosql","2026-07-12T08:43:00.455878",122,{"items":497,"total":505},[498],{"slug":4,"name":4,"fn":5,"description":6,"org":499,"tags":500,"stars":24,"repoUrl":25,"updatedAt":26},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[501,502,503,504],{"name":20,"slug":8,"type":15},{"name":22,"slug":23,"type":15},{"name":17,"slug":18,"type":15},{"name":13,"slug":14,"type":15},1]