[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-aws-amazon-aurora-mysql":3,"mdc-u6vk8o-key":35,"related-org-aws-amazon-aurora-mysql":1670,"related-repo-aws-amazon-aurora-mysql":1832},{"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},"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},"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},"MySQL","mysql","tag",{"name":17,"slug":18,"type":15},"Database","database",{"name":20,"slug":21,"type":15},"Serverless","serverless",{"name":23,"slug":8,"type":15},"AWS",1822,"https:\u002F\u002Fgithub.com\u002Faws\u002Fagent-toolkit-for-aws","2026-07-12T08:43:13.27939",null,157,[],{"repoUrl":25,"stars":24,"forks":28,"topics":31,"description":32},[],"Official, AWS-supported MCP servers, skills, and plugins to help AI agents build on AWS","https:\u002F\u002Fgithub.com\u002Faws\u002Fagent-toolkit-for-aws\u002Ftree\u002FHEAD\u002Fskills\u002Fspecialized-skills\u002Fdatabase-skills\u002Famazon-aurora-mysql","---\nname: amazon-aurora-mysql\ndescription: >-\n  Amazon Aurora MySQL — creates, modifies, and advises on Aurora MySQL clusters specifically\n  (MySQL-compatible engine, Aurora serverless, parallel query). Trigger for Aurora\n  MySQL cluster operations, ACU sizing, I\u002FO-Optimized storage, commitment pricing,\n  or MySQL upgrade planning. Aurora MySQL uses full (VPC-based) configuration — express\n  configuration is PostgreSQL-only. For Aurora PostgreSQL, use amazon-aurora-postgresql\n  instead. Contains safety guardrails and response templates that override defaults.\nversion: 1\n---\n\n# Amazon Aurora MySQL\n\nA modular toolkit for **Aurora MySQL** organized as a registry of sub-skills. Each sub-skill handles one domain of Aurora MySQL work. The router matches user intent to the right sub-skill, then loads only the references needed. (For Aurora PostgreSQL — and its express-configuration quick-start — use the `amazon-aurora-postgresql` skill.)\n\n## Operating procedure (follow in order)\n\n1. **Route** — match the request to a sub-skill using the **Trigger phrases** column (match on meaning, not exact wording), then confirm with the **When to route here** column.\n2. **Load** — `file_read` the matched sub-skill's `references\u002F{id}-instructions.md` and announce the path. Do not answer a matched sub-skill from general knowledge alone.\n3. **Analyze \u002F advise** — perform the sub-skill's work; run a bundled script when the user supplies the inputs (see Scripts).\n4. **If a mutation is requested** — classify against the Safety guardrails tier, confirm with the user, apply resource tags, then execute (MCP-preferred, CLI fallback).\n5. **Present results** — tables with dollar\u002FACU figures and a recommendation label; no derivation or arithmetic steps.\n\nEdge cases: if the request spans multiple sub-skills, run them in sequence (load each instructions.md in turn). If **no** sub-skill matches, answer directly from Aurora MySQL knowledge. If a script or MCP\u002FCLI call fails, show the error and suggest a fix before retrying. The numbered Global rules below are details that hang off these steps.\n\n## Sub-skill registry\n\n**Column semantics:** **Trigger phrases** = the keyword index you match the request against (step 1). **When to route here** = the decision logic confirming the match. **Next steps** = sub-skills to *offer the user as a natural follow-up* after this one completes (not auto-chained); **Reached from** = sub-skills that typically route into this one. Next-steps\u002FReached-from are suggestions for guiding the user, never automatic execution.\n\n| ID | Name | When to route here | Trigger phrases | Reached from | Next steps |\n|----|------|--------|---------------------|----------|------------|\n| `create` | Create Cluster | Routes Aurora MySQL cluster creation requests. Aurora MySQL uses full (VPC-based) configuration — collect VPC\u002Fsubnet group, security group, KMS, parameter group, and engine version, present options, then create. (Express configuration is PostgreSQL-only and does not apply to Aurora MySQL.) | create a cluster, new database, set up Aurora MySQL, get started, need a MySQL database, provision | — | `serverless-advisory`, `io-optimized` |\n| `serverless-advisory` | Aurora serverless Advisory | All Aurora serverless questions: ACU sizing, scale-to-zero behavior and compatibility, provisioned→serverless migration, capacity planning, and feature constraints. | ACU sizing, Aurora serverless, scale-to-zero, provisioned to serverless, how many ACUs, capacity, auto-scaling, RDS Proxy compatibility, scale-to-zero incompatibility, serverless limitations | `create` (optional) | `commitment-pricing` |\n| `io-optimized` | I\u002FO-Optimized Storage | Evaluates whether to switch from Aurora Standard to I\u002FO-Optimized (aurora-iopt1). Uses the 25% I\u002FO cost threshold rule. | I\u002FO-Optimized, aurora-iopt1, storage type switch, 25% threshold, I\u002FO costs too high, storage comparison | — | — |\n| `commitment-pricing` | Commitment Pricing | Compares Reserved Instances vs Database Savings Plans for provisioned clusters, and DSP-only for Aurora serverless. 1yr vs 3yr analysis. | Reserved Instance, RI, Savings Plan, DSP, 1yr vs 3yr, commitment, cost optimization, overpaying | `serverless-advisory` (optional) | — |\n| `upgrade-planning` | Upgrade Planning | Major and minor version upgrade planning for Aurora MySQL. LTS version guidance, pre\u002Fpost-upgrade checklists, blue\u002Fgreen deployment recommendations. | upgrade, version, LTS, pre-upgrade checklist, post-upgrade, major version, minor version, end of life, deprecation | — | — |\n\n## Global rules (apply to every sub-skill)\n\n1. **Execute, don't just suggest.** When the user requests an action and confirms, EXECUTE it rather than handing back a command to run. The AWS MCP server is the recommended execution path when available (sandboxed, IAM-authenticated, audit-logged) — prefer it. When MCP tools are not available (e.g. Claude Code, Cursor, or other non-MCP hosts), use the AWS CLI \u002F SDK directly with the same `aws rds ...` operation. Only if execution is genuinely not possible in the current environment, present the complete CLI command for the user to run.\n\n2. **Confirmation before mutation.** MUST confirm with the user before any create or modify operation. Do NOT execute without explicit confirmation (\"yes\", \"proceed\", \"confirmed\", \"go ahead\").\n\n3. **Resource tagging (always apply on resource creation).** When creating any cluster or instance, ALWAYS include these tags:\n   `--tags Key=created_by,Value=aurora-skill Key=generation_model,Value={your-model-id}`\n   Use your model id if known; if you cannot reliably determine it, use `Value=unknown` — never let tagging block the create. Include these tags even if the user does not mention tagging. If the user provides additional tags, append these to their tags.\n\n4. **Safety guardrails.**\n\n   **Tier 1 — Confirm (a yes\u002Fno confirmation is enough; no risk briefing required):**\n   - `create-db-cluster` (full\u002FVPC configuration — Aurora MySQL does not support express)\n   - `create-db-instance`\n   - `modify-db-cluster --serverless-v2-scaling-configuration` (ACU scaling)\n   - `modify-db-cluster --backup-retention-period`\n   - `modify-db-cluster --deletion-protection` \u002F `--no-deletion-protection`\n   - `modify-db-cluster --enable-cloudwatch-logs-exports`\n   - `modify-db-cluster --preferred-backup-window`\n   - `modify-db-cluster --enable-http-endpoint` (Data API)\n   - `add-tags-to-resource`, `remove-tags-from-resource`\n\n   **Tier 2 — High-impact: state the specific risk, THEN confirm (spell out the impact before asking; do not call any API until the user confirms with that risk in front of them):**\n   - `modify-db-cluster --storage-type` — no downtime for most instance classes; requires restart for NVMe\u002FOptimized Reads instances (r6gd, r6id, r8gd). Switching from Aurora Standard to Aurora I\u002FO-Optimized is limited to once every 30 days; switching from Aurora I\u002FO-Optimized back to Aurora Standard can be done at any time.\n   - `modify-db-instance --db-instance-class` — causes failover in multi-AZ\n   - `modify-db-cluster --engine-version` for a **minor** version upgrade — applied in the maintenance window (or immediately with `--apply-immediately`); brief failover\u002Frestart. State the target version and the restart impact, then confirm. (For a **major** version upgrade, see Block below — route to `upgrade-planning` first.)\n     - **How to tell minor from major (Aurora MySQL):** the Aurora MySQL version is `major.minor.patch` (e.g. `3.06`, `3.08`). The **major** digit (`2` = MySQL 5.7-compatible, `3` = MySQL 8.0-compatible, `8.4`+) is the major version; the second number is the **minor** version. So **3.06 → 3.08 is a MINOR upgrade** (major `3` unchanged) → handle here in Tier 2. A change in the leading major (e.g. `2.x → 3.x`, or 5.7 → 8.0 compatibility) is a **major** upgrade → Block. When unsure, treat it as major and route to `upgrade-planning`.\n   - Any modify with `--apply-immediately` — bypasses maintenance window\n\n   **Tier 3 — Block (refuse, explain why, redirect to console\u002Fchange-control):**\n   - `delete-db-cluster`, `delete-db-instance` — irreversible\n   - `failover-db-cluster`, `switchover-blue-green-deployment` — production impact\n   - `modify-db-cluster --engine-version` across major versions — requires prechecks and rollback plan\n   - `modify-db-cluster --master-user-password`, `--manage-master-user-password` — credential management must be performed by the customer directly. Use AWS Secrets Manager rotation or the AWS Console.\n   - `modify-db-cluster --vpc-security-group-ids` — network security posture change\n   - `modify-db-cluster --db-cluster-parameter-group-name` — can break applications\n   - `create-db-instance --publicly-accessible`, `modify-db-instance --publicly-accessible` — NEVER make Aurora instances publicly accessible. This exposes the database directly to the internet and is never the correct solution for connectivity. See secure connection alternatives below.\n   - `purchase-reserved-db-instances-offering`, `create-savings-plan` — financial commitment\n   - `reboot-db-instance`, `reboot-db-cluster` — production impact\n\n   When blocking, you MUST refuse immediately. Do NOT call any AWS API. Your response MUST have exactly two paragraphs:\n\n   Paragraph 1 — refuse: \"I can't perform [action] because [reason]. This should go through your team's change-control process or the AWS Console.\"\n\n   Paragraph 2 — alternative (from the table below, always included):\n   - `purchase-reserved-db-instances-offering`, `create-savings-plan` → \"I can run a commitment pricing assessment (RI vs DSP comparison) so you have the numbers to bring to procurement.\"\n   - `delete-db-cluster`, `delete-db-instance` → \"I can help with snapshot creation or final-snapshot validation before deletion.\"\n   - `modify-db-cluster --engine-version` (major version) → \"I can run an upgrade assessment — target version recommendation, prechecks, and pre\u002Fpost checklists.\"\n   - `failover-db-cluster`, `switchover-blue-green-deployment` → \"I can validate the cluster's state and review the failover\u002Fswitchover plan with you.\"\n   - `reboot-db-instance`, `reboot-db-cluster` → \"I can check for pending modifications and recommend a maintenance window.\"\n   - `modify-db-cluster --master-user-password` \u002F `--manage-master-user-password` → \"Rotate the password via AWS Secrets Manager or the AWS Console; both are safer than a direct API call. I can walk you through enabling Secrets Manager managed rotation.\"\n   - `--publicly-accessible` → \"Making the instance publicly accessible exposes the database directly to the internet — this is a security anti-pattern even for prototypes. Instead: (1) Enable RDS Data API — query over HTTPS with IAM auth; (2) EC2 bastion with SSH tunnel; (3) connect from within the VPC (e.g. a workload in the same VPC or via VPN\u002FDirect Connect). I can help you set up any of these.\"\n   - `modify-db-cluster --vpc-security-group-ids` → \"I can describe the cluster's current security-group configuration and help you draft the intended change so you can apply it through your team's change-control process or the AWS Console.\"\n   - `modify-db-cluster --db-cluster-parameter-group-name` → \"I can review the current parameter group and compare it against the target group (highlighting reboot-required parameters) so you can prepare the change for your team's change-control process or the AWS Console.\"\n\n   Never omit paragraph 2. A refusal without an alternative is incomplete.\n\n5. **Reference loading.** Before responding to any matched sub-skill request, you MUST read `references\u002F{id}-instructions.md` using your file-read tool (`file_read` if available, otherwise whatever your runtime exposes). Do not answer a matched sub-skill from the registry summary alone. Announce the path in your reply.\n\n6. **Stay in scope.** Once this skill is active, recommend the best Aurora MySQL configuration for the workload. Do not suggest non-AWS alternatives. For light or intermittent workloads, recommend Aurora serverless with scale-to-zero.\n\n7. **Never fabricate.** Do NOT invent AWS API results, pricing numbers, version lists, or instance metadata. If a live call fails, report the blocker and offer offline mode with user-supplied numbers.\n\n8. **Carry context forward.** Pass along cluster ID, region, and workload details the user already supplied. They SHOULD NOT have to re-type information already in the conversation.\n\n9. **Broad requests.** If the user says \"help me with Aurora MySQL\" or \"analyze my cluster\" without specifying a domain (create, sizing, I\u002FO, commitment, upgrade), present the sub-skill domains as one line each and ask which they want to focus on. Do NOT silently pick a sub-skill and run it. Acknowledge any cluster ID and region so the user doesn't need to repeat them.\n\n10. **Out-of-scope topics.** If the user asks about an Aurora feature not covered by a sub-skill (e.g., Global Database, Blue\u002FGreen Deployments, RDS Proxy), note that it is not covered by a specific sub-skill, answer from general Aurora knowledge, and link to the relevant AWS documentation page.\n\n11. **Credential safety.** Do not create, store, or display long-lived credentials or DB passwords. `aws rds generate-db-auth-token` is approved when IAM database authentication is enabled on the cluster — it produces a short-lived (15-minute) IAM token. Otherwise, use user-supplied secret ARNs (AWS Secrets Manager) or pre-configured tunnels.\n\n12. **Present results clearly.** Use tables with dollar figures, ACU numbers, and recommendation labels. Do NOT show derivation or arithmetic steps. Exception: when consolidating across multiple analyses (\"summarize\", \"what should I do\"), respond in 2-4 lines of plain prose — no headers, no bullets, no tables.\n\n## Scripts\n\nBundled scripts in `scripts\u002F` for offline analysis. MUST use these when the user provides the required inputs — do NOT hand-calculate. Each script documents its full flags\u002Fusage in its own `--help` and header docstring; read those on demand rather than relying only on the one-line usage below.\n\n**Script execution model:** If a shell is available, execute the script directly and present the output. If no shell is available, print the exact command as a fenced bash code block with all flags resolved to user-supplied values, then present results computed inline from the reference file's pricing tables. (Result-presentation format is governed by the Operating procedure \u002F Global rules — no derivation steps.)\n\n| Script | Purpose | Usage |\n|--------|---------|-------|\n| `acu_calculator.py` | Aurora serverless ACU sizing | `python3 scripts\u002Facu_calculator.py estimate --instance \u003Ctype> --cpu-p95 \u003Cval> --cpu-max \u003Cval> --storage \u003Cval>` |\n| `io_optimized_analyzer.py` | I\u002FO-Optimized breakeven | `python3 scripts\u002Fio_optimized_analyzer.py offline --instance \u003Ctype> --num-instances \u003Cn> --storage-gib \u003Cval> --monthly-io-millions \u003Cval>` |\n| `commitment_pricing_analyzer.py` | RI vs DSP cost comparison | `python3 scripts\u002Fcommitment_pricing_analyzer.py offline --instance \u003Ctype> --num-instances \u003Cn> --region \u003Cregion>` (provisioned) or `--serverless --avg-acu \u003Cval>` (Aurora serverless) |\n\n## Troubleshooting\n\n- **AccessDenied**: Attach `AmazonRDSReadOnlyAccess` + `CloudWatchReadOnlyAccess` for reads. For creates\u002Fmodifies, use a custom policy scoped to `rds:CreateDBCluster`, `rds:CreateDBInstance`, `rds:ModifyDBCluster`, `rds:ModifyDBInstance`, `rds:AddTagsToResource`, and `rds:Describe*`. See [Identity and access management for Amazon Aurora](https:\u002F\u002Fdocs.aws.amazon.com\u002FAmazonRDS\u002Flatest\u002FAuroraUserGuide\u002FUsingWithRDS.IAM.html).\n- **ExpiredToken \u002F credentials**: Refresh your AWS credentials using whatever mechanism you use (e.g. re-run your SSO\u002F`aws sso login`, `ada credentials update`, assume-role, or refresh the profile), then retry. Do not assume a specific credential tool.\n- **DBClusterNotFoundFault**: Verify region and cluster ID.\n- **Throttling**: Retry once, then narrow scope.\n\n## Additional Resources\n\n- [Aurora User Guide](https:\u002F\u002Fdocs.aws.amazon.com\u002FAmazonRDS\u002Flatest\u002FAuroraUserGuide\u002F)\n- [Aurora pricing](https:\u002F\u002Faws.amazon.com\u002Frds\u002Faurora\u002Fpricing\u002F)\n- [Aurora serverless](https:\u002F\u002Fdocs.aws.amazon.com\u002FAmazonRDS\u002Flatest\u002FAuroraUserGuide\u002Faurora-serverless-v2.html)\n- [Aurora MySQL upgrades](https:\u002F\u002Fdocs.aws.amazon.com\u002FAmazonRDS\u002Flatest\u002FAuroraUserGuide\u002FUSER_UpgradeDBInstance.Upgrading.html)\n\n## Handoff from aws-database-selection\n\nThis skill can be entered from `aws-database-selection` after it produces a `requirements.json`. When you see a path matching `aws_dbs_requirements\u002F*\u002Frequirements.json` in conversation:\n\n1. Read the artifact. Sanity-check it has the fields you'll use — at minimum `engine` (or workload type), `region`, and the workload signals you route on (capacity\u002FACU hints, storage size, connectivity\u002FVPC needs, version). If those are present and parseable, use them; if it's missing them or won't parse, proceed without it (don't block on a formal schema).\n2. Acknowledge relevant facts in 1-2 bold sentences.\n3. Scope-check: if the artifact doesn't match Aurora (e.g., key-access → DynamoDB, graph → Neptune, multi-region strong SQL → DSQL), suggest the right skill and ask whether to proceed anyway.\n4. Continue with this skill's sub-skill routing.\n",{"data":36,"body":38},{"name":4,"description":6,"version":37},1,{"type":39,"children":40},"root",[41,49,72,79,164,176,182,226,472,478,1261,1267,1288,1298,1413,1419,1547,1553,1596,1602,1631],{"type":42,"tag":43,"props":44,"children":45},"element","h1",{"id":4},[46],{"type":47,"value":48},"text","Amazon Aurora MySQL",{"type":42,"tag":50,"props":51,"children":52},"p",{},[53,55,61,63,70],{"type":47,"value":54},"A modular toolkit for ",{"type":42,"tag":56,"props":57,"children":58},"strong",{},[59],{"type":47,"value":60},"Aurora MySQL",{"type":47,"value":62}," organized as a registry of sub-skills. Each sub-skill handles one domain of Aurora MySQL work. The router matches user intent to the right sub-skill, then loads only the references needed. (For Aurora PostgreSQL — and its express-configuration quick-start — use the ",{"type":42,"tag":64,"props":65,"children":67},"code",{"className":66},[],[68],{"type":47,"value":69},"amazon-aurora-postgresql",{"type":47,"value":71}," skill.)",{"type":42,"tag":73,"props":74,"children":76},"h2",{"id":75},"operating-procedure-follow-in-order",[77],{"type":47,"value":78},"Operating procedure (follow in order)",{"type":42,"tag":80,"props":81,"children":82},"ol",{},[83,108,134,144,154],{"type":42,"tag":84,"props":85,"children":86},"li",{},[87,92,94,99,101,106],{"type":42,"tag":56,"props":88,"children":89},{},[90],{"type":47,"value":91},"Route",{"type":47,"value":93}," — match the request to a sub-skill using the ",{"type":42,"tag":56,"props":95,"children":96},{},[97],{"type":47,"value":98},"Trigger phrases",{"type":47,"value":100}," column (match on meaning, not exact wording), then confirm with the ",{"type":42,"tag":56,"props":102,"children":103},{},[104],{"type":47,"value":105},"When to route here",{"type":47,"value":107}," column.",{"type":42,"tag":84,"props":109,"children":110},{},[111,116,118,124,126,132],{"type":42,"tag":56,"props":112,"children":113},{},[114],{"type":47,"value":115},"Load",{"type":47,"value":117}," — ",{"type":42,"tag":64,"props":119,"children":121},{"className":120},[],[122],{"type":47,"value":123},"file_read",{"type":47,"value":125}," the matched sub-skill's ",{"type":42,"tag":64,"props":127,"children":129},{"className":128},[],[130],{"type":47,"value":131},"references\u002F{id}-instructions.md",{"type":47,"value":133}," and announce the path. Do not answer a matched sub-skill from general knowledge alone.",{"type":42,"tag":84,"props":135,"children":136},{},[137,142],{"type":42,"tag":56,"props":138,"children":139},{},[140],{"type":47,"value":141},"Analyze \u002F advise",{"type":47,"value":143}," — perform the sub-skill's work; run a bundled script when the user supplies the inputs (see Scripts).",{"type":42,"tag":84,"props":145,"children":146},{},[147,152],{"type":42,"tag":56,"props":148,"children":149},{},[150],{"type":47,"value":151},"If a mutation is requested",{"type":47,"value":153}," — classify against the Safety guardrails tier, confirm with the user, apply resource tags, then execute (MCP-preferred, CLI fallback).",{"type":42,"tag":84,"props":155,"children":156},{},[157,162],{"type":42,"tag":56,"props":158,"children":159},{},[160],{"type":47,"value":161},"Present results",{"type":47,"value":163}," — tables with dollar\u002FACU figures and a recommendation label; no derivation or arithmetic steps.",{"type":42,"tag":50,"props":165,"children":166},{},[167,169,174],{"type":47,"value":168},"Edge cases: if the request spans multiple sub-skills, run them in sequence (load each instructions.md in turn). If ",{"type":42,"tag":56,"props":170,"children":171},{},[172],{"type":47,"value":173},"no",{"type":47,"value":175}," sub-skill matches, answer directly from Aurora MySQL knowledge. If a script or MCP\u002FCLI call fails, show the error and suggest a fix before retrying. The numbered Global rules below are details that hang off these steps.",{"type":42,"tag":73,"props":177,"children":179},{"id":178},"sub-skill-registry",[180],{"type":47,"value":181},"Sub-skill registry",{"type":42,"tag":50,"props":183,"children":184},{},[185,190,192,196,198,202,204,209,211,217,219,224],{"type":42,"tag":56,"props":186,"children":187},{},[188],{"type":47,"value":189},"Column semantics:",{"type":47,"value":191}," ",{"type":42,"tag":56,"props":193,"children":194},{},[195],{"type":47,"value":98},{"type":47,"value":197}," = the keyword index you match the request against (step 1). ",{"type":42,"tag":56,"props":199,"children":200},{},[201],{"type":47,"value":105},{"type":47,"value":203}," = the decision logic confirming the match. ",{"type":42,"tag":56,"props":205,"children":206},{},[207],{"type":47,"value":208},"Next steps",{"type":47,"value":210}," = sub-skills to ",{"type":42,"tag":212,"props":213,"children":214},"em",{},[215],{"type":47,"value":216},"offer the user as a natural follow-up",{"type":47,"value":218}," after this one completes (not auto-chained); ",{"type":42,"tag":56,"props":220,"children":221},{},[222],{"type":47,"value":223},"Reached from",{"type":47,"value":225}," = sub-skills that typically route into this one. Next-steps\u002FReached-from are suggestions for guiding the user, never automatic execution.",{"type":42,"tag":227,"props":228,"children":229},"table",{},[230,265],{"type":42,"tag":231,"props":232,"children":233},"thead",{},[234],{"type":42,"tag":235,"props":236,"children":237},"tr",{},[238,244,249,253,257,261],{"type":42,"tag":239,"props":240,"children":241},"th",{},[242],{"type":47,"value":243},"ID",{"type":42,"tag":239,"props":245,"children":246},{},[247],{"type":47,"value":248},"Name",{"type":42,"tag":239,"props":250,"children":251},{},[252],{"type":47,"value":105},{"type":42,"tag":239,"props":254,"children":255},{},[256],{"type":47,"value":98},{"type":42,"tag":239,"props":258,"children":259},{},[260],{"type":47,"value":223},{"type":42,"tag":239,"props":262,"children":263},{},[264],{"type":47,"value":208},{"type":42,"tag":266,"props":267,"children":268},"tbody",{},[269,319,364,398,437],{"type":42,"tag":235,"props":270,"children":271},{},[272,282,287,292,297,302],{"type":42,"tag":273,"props":274,"children":275},"td",{},[276],{"type":42,"tag":64,"props":277,"children":279},{"className":278},[],[280],{"type":47,"value":281},"create",{"type":42,"tag":273,"props":283,"children":284},{},[285],{"type":47,"value":286},"Create Cluster",{"type":42,"tag":273,"props":288,"children":289},{},[290],{"type":47,"value":291},"Routes Aurora MySQL cluster creation requests. Aurora MySQL uses full (VPC-based) configuration — collect VPC\u002Fsubnet group, security group, KMS, parameter group, and engine version, present options, then create. (Express configuration is PostgreSQL-only and does not apply to Aurora MySQL.)",{"type":42,"tag":273,"props":293,"children":294},{},[295],{"type":47,"value":296},"create a cluster, new database, set up Aurora MySQL, get started, need a MySQL database, provision",{"type":42,"tag":273,"props":298,"children":299},{},[300],{"type":47,"value":301},"—",{"type":42,"tag":273,"props":303,"children":304},{},[305,311,313],{"type":42,"tag":64,"props":306,"children":308},{"className":307},[],[309],{"type":47,"value":310},"serverless-advisory",{"type":47,"value":312},", ",{"type":42,"tag":64,"props":314,"children":316},{"className":315},[],[317],{"type":47,"value":318},"io-optimized",{"type":42,"tag":235,"props":320,"children":321},{},[322,330,335,340,345,355],{"type":42,"tag":273,"props":323,"children":324},{},[325],{"type":42,"tag":64,"props":326,"children":328},{"className":327},[],[329],{"type":47,"value":310},{"type":42,"tag":273,"props":331,"children":332},{},[333],{"type":47,"value":334},"Aurora serverless Advisory",{"type":42,"tag":273,"props":336,"children":337},{},[338],{"type":47,"value":339},"All Aurora serverless questions: ACU sizing, scale-to-zero behavior and compatibility, provisioned→serverless migration, capacity planning, and feature constraints.",{"type":42,"tag":273,"props":341,"children":342},{},[343],{"type":47,"value":344},"ACU sizing, Aurora serverless, scale-to-zero, provisioned to serverless, how many ACUs, capacity, auto-scaling, RDS Proxy compatibility, scale-to-zero incompatibility, serverless limitations",{"type":42,"tag":273,"props":346,"children":347},{},[348,353],{"type":42,"tag":64,"props":349,"children":351},{"className":350},[],[352],{"type":47,"value":281},{"type":47,"value":354}," (optional)",{"type":42,"tag":273,"props":356,"children":357},{},[358],{"type":42,"tag":64,"props":359,"children":361},{"className":360},[],[362],{"type":47,"value":363},"commitment-pricing",{"type":42,"tag":235,"props":365,"children":366},{},[367,375,380,385,390,394],{"type":42,"tag":273,"props":368,"children":369},{},[370],{"type":42,"tag":64,"props":371,"children":373},{"className":372},[],[374],{"type":47,"value":318},{"type":42,"tag":273,"props":376,"children":377},{},[378],{"type":47,"value":379},"I\u002FO-Optimized Storage",{"type":42,"tag":273,"props":381,"children":382},{},[383],{"type":47,"value":384},"Evaluates whether to switch from Aurora Standard to I\u002FO-Optimized (aurora-iopt1). Uses the 25% I\u002FO cost threshold rule.",{"type":42,"tag":273,"props":386,"children":387},{},[388],{"type":47,"value":389},"I\u002FO-Optimized, aurora-iopt1, storage type switch, 25% threshold, I\u002FO costs too high, storage comparison",{"type":42,"tag":273,"props":391,"children":392},{},[393],{"type":47,"value":301},{"type":42,"tag":273,"props":395,"children":396},{},[397],{"type":47,"value":301},{"type":42,"tag":235,"props":399,"children":400},{},[401,409,414,419,424,433],{"type":42,"tag":273,"props":402,"children":403},{},[404],{"type":42,"tag":64,"props":405,"children":407},{"className":406},[],[408],{"type":47,"value":363},{"type":42,"tag":273,"props":410,"children":411},{},[412],{"type":47,"value":413},"Commitment Pricing",{"type":42,"tag":273,"props":415,"children":416},{},[417],{"type":47,"value":418},"Compares Reserved Instances vs Database Savings Plans for provisioned clusters, and DSP-only for Aurora serverless. 1yr vs 3yr analysis.",{"type":42,"tag":273,"props":420,"children":421},{},[422],{"type":47,"value":423},"Reserved Instance, RI, Savings Plan, DSP, 1yr vs 3yr, commitment, cost optimization, overpaying",{"type":42,"tag":273,"props":425,"children":426},{},[427,432],{"type":42,"tag":64,"props":428,"children":430},{"className":429},[],[431],{"type":47,"value":310},{"type":47,"value":354},{"type":42,"tag":273,"props":434,"children":435},{},[436],{"type":47,"value":301},{"type":42,"tag":235,"props":438,"children":439},{},[440,449,454,459,464,468],{"type":42,"tag":273,"props":441,"children":442},{},[443],{"type":42,"tag":64,"props":444,"children":446},{"className":445},[],[447],{"type":47,"value":448},"upgrade-planning",{"type":42,"tag":273,"props":450,"children":451},{},[452],{"type":47,"value":453},"Upgrade Planning",{"type":42,"tag":273,"props":455,"children":456},{},[457],{"type":47,"value":458},"Major and minor version upgrade planning for Aurora MySQL. LTS version guidance, pre\u002Fpost-upgrade checklists, blue\u002Fgreen deployment recommendations.",{"type":42,"tag":273,"props":460,"children":461},{},[462],{"type":47,"value":463},"upgrade, version, LTS, pre-upgrade checklist, post-upgrade, major version, minor version, end of life, deprecation",{"type":42,"tag":273,"props":465,"children":466},{},[467],{"type":47,"value":301},{"type":42,"tag":273,"props":469,"children":470},{},[471],{"type":47,"value":301},{"type":42,"tag":73,"props":473,"children":475},{"id":474},"global-rules-apply-to-every-sub-skill",[476],{"type":47,"value":477},"Global rules (apply to every sub-skill)",{"type":42,"tag":80,"props":479,"children":480},{},[481,499,509,535,1159,1183,1193,1203,1213,1223,1233,1251],{"type":42,"tag":84,"props":482,"children":483},{},[484,489,491,497],{"type":42,"tag":56,"props":485,"children":486},{},[487],{"type":47,"value":488},"Execute, don't just suggest.",{"type":47,"value":490}," When the user requests an action and confirms, EXECUTE it rather than handing back a command to run. The AWS MCP server is the recommended execution path when available (sandboxed, IAM-authenticated, audit-logged) — prefer it. When MCP tools are not available (e.g. Claude Code, Cursor, or other non-MCP hosts), use the AWS CLI \u002F SDK directly with the same ",{"type":42,"tag":64,"props":492,"children":494},{"className":493},[],[495],{"type":47,"value":496},"aws rds ...",{"type":47,"value":498}," operation. Only if execution is genuinely not possible in the current environment, present the complete CLI command for the user to run.",{"type":42,"tag":84,"props":500,"children":501},{},[502,507],{"type":42,"tag":56,"props":503,"children":504},{},[505],{"type":47,"value":506},"Confirmation before mutation.",{"type":47,"value":508}," MUST confirm with the user before any create or modify operation. Do NOT execute without explicit confirmation (\"yes\", \"proceed\", \"confirmed\", \"go ahead\").",{"type":42,"tag":84,"props":510,"children":511},{},[512,517,519,525,527,533],{"type":42,"tag":56,"props":513,"children":514},{},[515],{"type":47,"value":516},"Resource tagging (always apply on resource creation).",{"type":47,"value":518}," When creating any cluster or instance, ALWAYS include these tags:\n",{"type":42,"tag":64,"props":520,"children":522},{"className":521},[],[523],{"type":47,"value":524},"--tags Key=created_by,Value=aurora-skill Key=generation_model,Value={your-model-id}",{"type":47,"value":526},"\nUse your model id if known; if you cannot reliably determine it, use ",{"type":42,"tag":64,"props":528,"children":530},{"className":529},[],[531],{"type":47,"value":532},"Value=unknown",{"type":47,"value":534}," — never let tagging block the create. Include these tags even if the user does not mention tagging. If the user provides additional tags, append these to their tags.",{"type":42,"tag":84,"props":536,"children":537},{},[538,543,547,552,658,661,666,850,853,858,1000,1003,1005,1008,1010,1016,1018,1023,1025,1028,1030,1154,1157],{"type":42,"tag":56,"props":539,"children":540},{},[541],{"type":47,"value":542},"Safety guardrails.",{"type":42,"tag":544,"props":545,"children":546},"br",{},[],{"type":42,"tag":56,"props":548,"children":549},{},[550],{"type":47,"value":551},"Tier 1 — Confirm (a yes\u002Fno confirmation is enough; no risk briefing required):",{"type":42,"tag":553,"props":554,"children":555},"ul",{},[556,567,576,587,596,613,622,631,642],{"type":42,"tag":84,"props":557,"children":558},{},[559,565],{"type":42,"tag":64,"props":560,"children":562},{"className":561},[],[563],{"type":47,"value":564},"create-db-cluster",{"type":47,"value":566}," (full\u002FVPC configuration — Aurora MySQL does not support express)",{"type":42,"tag":84,"props":568,"children":569},{},[570],{"type":42,"tag":64,"props":571,"children":573},{"className":572},[],[574],{"type":47,"value":575},"create-db-instance",{"type":42,"tag":84,"props":577,"children":578},{},[579,585],{"type":42,"tag":64,"props":580,"children":582},{"className":581},[],[583],{"type":47,"value":584},"modify-db-cluster --serverless-v2-scaling-configuration",{"type":47,"value":586}," (ACU scaling)",{"type":42,"tag":84,"props":588,"children":589},{},[590],{"type":42,"tag":64,"props":591,"children":593},{"className":592},[],[594],{"type":47,"value":595},"modify-db-cluster --backup-retention-period",{"type":42,"tag":84,"props":597,"children":598},{},[599,605,607],{"type":42,"tag":64,"props":600,"children":602},{"className":601},[],[603],{"type":47,"value":604},"modify-db-cluster --deletion-protection",{"type":47,"value":606}," \u002F ",{"type":42,"tag":64,"props":608,"children":610},{"className":609},[],[611],{"type":47,"value":612},"--no-deletion-protection",{"type":42,"tag":84,"props":614,"children":615},{},[616],{"type":42,"tag":64,"props":617,"children":619},{"className":618},[],[620],{"type":47,"value":621},"modify-db-cluster --enable-cloudwatch-logs-exports",{"type":42,"tag":84,"props":623,"children":624},{},[625],{"type":42,"tag":64,"props":626,"children":628},{"className":627},[],[629],{"type":47,"value":630},"modify-db-cluster --preferred-backup-window",{"type":42,"tag":84,"props":632,"children":633},{},[634,640],{"type":42,"tag":64,"props":635,"children":637},{"className":636},[],[638],{"type":47,"value":639},"modify-db-cluster --enable-http-endpoint",{"type":47,"value":641}," (Data API)",{"type":42,"tag":84,"props":643,"children":644},{},[645,651,652],{"type":42,"tag":64,"props":646,"children":648},{"className":647},[],[649],{"type":47,"value":650},"add-tags-to-resource",{"type":47,"value":312},{"type":42,"tag":64,"props":653,"children":655},{"className":654},[],[656],{"type":47,"value":657},"remove-tags-from-resource",{"type":42,"tag":544,"props":659,"children":660},{},[],{"type":42,"tag":56,"props":662,"children":663},{},[664],{"type":47,"value":665},"Tier 2 — High-impact: state the specific risk, THEN confirm (spell out the impact before asking; do not call any API until the user confirms with that risk in front of them):",{"type":42,"tag":553,"props":667,"children":668},{},[669,680,691,838],{"type":42,"tag":84,"props":670,"children":671},{},[672,678],{"type":42,"tag":64,"props":673,"children":675},{"className":674},[],[676],{"type":47,"value":677},"modify-db-cluster --storage-type",{"type":47,"value":679}," — no downtime for most instance classes; requires restart for NVMe\u002FOptimized Reads instances (r6gd, r6id, r8gd). Switching from Aurora Standard to Aurora I\u002FO-Optimized is limited to once every 30 days; switching from Aurora I\u002FO-Optimized back to Aurora Standard can be done at any time.",{"type":42,"tag":84,"props":681,"children":682},{},[683,689],{"type":42,"tag":64,"props":684,"children":686},{"className":685},[],[687],{"type":47,"value":688},"modify-db-instance --db-instance-class",{"type":47,"value":690}," — causes failover in multi-AZ",{"type":42,"tag":84,"props":692,"children":693},{},[694,700,702,707,709,715,717,722,724,729,731],{"type":42,"tag":64,"props":695,"children":697},{"className":696},[],[698],{"type":47,"value":699},"modify-db-cluster --engine-version",{"type":47,"value":701}," for a ",{"type":42,"tag":56,"props":703,"children":704},{},[705],{"type":47,"value":706},"minor",{"type":47,"value":708}," version upgrade — applied in the maintenance window (or immediately with ",{"type":42,"tag":64,"props":710,"children":712},{"className":711},[],[713],{"type":47,"value":714},"--apply-immediately",{"type":47,"value":716},"); brief failover\u002Frestart. State the target version and the restart impact, then confirm. (For a ",{"type":42,"tag":56,"props":718,"children":719},{},[720],{"type":47,"value":721},"major",{"type":47,"value":723}," version upgrade, see Block below — route to ",{"type":42,"tag":64,"props":725,"children":727},{"className":726},[],[728],{"type":47,"value":448},{"type":47,"value":730}," first.)\n",{"type":42,"tag":553,"props":732,"children":733},{},[734],{"type":42,"tag":84,"props":735,"children":736},{},[737,742,744,750,752,758,759,765,767,771,773,779,781,787,789,795,797,801,803,808,810,815,817,823,825,829,831,836],{"type":42,"tag":56,"props":738,"children":739},{},[740],{"type":47,"value":741},"How to tell minor from major (Aurora MySQL):",{"type":47,"value":743}," the Aurora MySQL version is ",{"type":42,"tag":64,"props":745,"children":747},{"className":746},[],[748],{"type":47,"value":749},"major.minor.patch",{"type":47,"value":751}," (e.g. ",{"type":42,"tag":64,"props":753,"children":755},{"className":754},[],[756],{"type":47,"value":757},"3.06",{"type":47,"value":312},{"type":42,"tag":64,"props":760,"children":762},{"className":761},[],[763],{"type":47,"value":764},"3.08",{"type":47,"value":766},"). The ",{"type":42,"tag":56,"props":768,"children":769},{},[770],{"type":47,"value":721},{"type":47,"value":772}," digit (",{"type":42,"tag":64,"props":774,"children":776},{"className":775},[],[777],{"type":47,"value":778},"2",{"type":47,"value":780}," = MySQL 5.7-compatible, ",{"type":42,"tag":64,"props":782,"children":784},{"className":783},[],[785],{"type":47,"value":786},"3",{"type":47,"value":788}," = MySQL 8.0-compatible, ",{"type":42,"tag":64,"props":790,"children":792},{"className":791},[],[793],{"type":47,"value":794},"8.4",{"type":47,"value":796},"+) is the major version; the second number is the ",{"type":42,"tag":56,"props":798,"children":799},{},[800],{"type":47,"value":706},{"type":47,"value":802}," version. So ",{"type":42,"tag":56,"props":804,"children":805},{},[806],{"type":47,"value":807},"3.06 → 3.08 is a MINOR upgrade",{"type":47,"value":809}," (major ",{"type":42,"tag":64,"props":811,"children":813},{"className":812},[],[814],{"type":47,"value":786},{"type":47,"value":816}," unchanged) → handle here in Tier 2. A change in the leading major (e.g. ",{"type":42,"tag":64,"props":818,"children":820},{"className":819},[],[821],{"type":47,"value":822},"2.x → 3.x",{"type":47,"value":824},", or 5.7 → 8.0 compatibility) is a ",{"type":42,"tag":56,"props":826,"children":827},{},[828],{"type":47,"value":721},{"type":47,"value":830}," upgrade → Block. When unsure, treat it as major and route to ",{"type":42,"tag":64,"props":832,"children":834},{"className":833},[],[835],{"type":47,"value":448},{"type":47,"value":837},".",{"type":42,"tag":84,"props":839,"children":840},{},[841,843,848],{"type":47,"value":842},"Any modify with ",{"type":42,"tag":64,"props":844,"children":846},{"className":845},[],[847],{"type":47,"value":714},{"type":47,"value":849}," — bypasses maintenance window",{"type":42,"tag":544,"props":851,"children":852},{},[],{"type":42,"tag":56,"props":854,"children":855},{},[856],{"type":47,"value":857},"Tier 3 — Block (refuse, explain why, redirect to console\u002Fchange-control):",{"type":42,"tag":553,"props":859,"children":860},{},[861,879,897,907,925,936,947,965,983],{"type":42,"tag":84,"props":862,"children":863},{},[864,870,871,877],{"type":42,"tag":64,"props":865,"children":867},{"className":866},[],[868],{"type":47,"value":869},"delete-db-cluster",{"type":47,"value":312},{"type":42,"tag":64,"props":872,"children":874},{"className":873},[],[875],{"type":47,"value":876},"delete-db-instance",{"type":47,"value":878}," — irreversible",{"type":42,"tag":84,"props":880,"children":881},{},[882,888,889,895],{"type":42,"tag":64,"props":883,"children":885},{"className":884},[],[886],{"type":47,"value":887},"failover-db-cluster",{"type":47,"value":312},{"type":42,"tag":64,"props":890,"children":892},{"className":891},[],[893],{"type":47,"value":894},"switchover-blue-green-deployment",{"type":47,"value":896}," — production impact",{"type":42,"tag":84,"props":898,"children":899},{},[900,905],{"type":42,"tag":64,"props":901,"children":903},{"className":902},[],[904],{"type":47,"value":699},{"type":47,"value":906}," across major versions — requires prechecks and rollback plan",{"type":42,"tag":84,"props":908,"children":909},{},[910,916,917,923],{"type":42,"tag":64,"props":911,"children":913},{"className":912},[],[914],{"type":47,"value":915},"modify-db-cluster --master-user-password",{"type":47,"value":312},{"type":42,"tag":64,"props":918,"children":920},{"className":919},[],[921],{"type":47,"value":922},"--manage-master-user-password",{"type":47,"value":924}," — credential management must be performed by the customer directly. Use AWS Secrets Manager rotation or the AWS Console.",{"type":42,"tag":84,"props":926,"children":927},{},[928,934],{"type":42,"tag":64,"props":929,"children":931},{"className":930},[],[932],{"type":47,"value":933},"modify-db-cluster --vpc-security-group-ids",{"type":47,"value":935}," — network security posture change",{"type":42,"tag":84,"props":937,"children":938},{},[939,945],{"type":42,"tag":64,"props":940,"children":942},{"className":941},[],[943],{"type":47,"value":944},"modify-db-cluster --db-cluster-parameter-group-name",{"type":47,"value":946}," — can break applications",{"type":42,"tag":84,"props":948,"children":949},{},[950,956,957,963],{"type":42,"tag":64,"props":951,"children":953},{"className":952},[],[954],{"type":47,"value":955},"create-db-instance --publicly-accessible",{"type":47,"value":312},{"type":42,"tag":64,"props":958,"children":960},{"className":959},[],[961],{"type":47,"value":962},"modify-db-instance --publicly-accessible",{"type":47,"value":964}," — NEVER make Aurora instances publicly accessible. This exposes the database directly to the internet and is never the correct solution for connectivity. See secure connection alternatives below.",{"type":42,"tag":84,"props":966,"children":967},{},[968,974,975,981],{"type":42,"tag":64,"props":969,"children":971},{"className":970},[],[972],{"type":47,"value":973},"purchase-reserved-db-instances-offering",{"type":47,"value":312},{"type":42,"tag":64,"props":976,"children":978},{"className":977},[],[979],{"type":47,"value":980},"create-savings-plan",{"type":47,"value":982}," — financial commitment",{"type":42,"tag":84,"props":984,"children":985},{},[986,992,993,999],{"type":42,"tag":64,"props":987,"children":989},{"className":988},[],[990],{"type":47,"value":991},"reboot-db-instance",{"type":47,"value":312},{"type":42,"tag":64,"props":994,"children":996},{"className":995},[],[997],{"type":47,"value":998},"reboot-db-cluster",{"type":47,"value":896},{"type":42,"tag":544,"props":1001,"children":1002},{},[],{"type":47,"value":1004},"When blocking, you MUST refuse immediately. Do NOT call any AWS API. Your response MUST have exactly two paragraphs:",{"type":42,"tag":544,"props":1006,"children":1007},{},[],{"type":47,"value":1009},"Paragraph 1 — refuse: \"I can't perform ",{"type":42,"tag":1011,"props":1012,"children":1013},"span",{},[1014],{"type":47,"value":1015},"action",{"type":47,"value":1017}," because ",{"type":42,"tag":1011,"props":1019,"children":1020},{},[1021],{"type":47,"value":1022},"reason",{"type":47,"value":1024},". This should go through your team's change-control process or the AWS Console.\"",{"type":42,"tag":544,"props":1026,"children":1027},{},[],{"type":47,"value":1029},"Paragraph 2 — alternative (from the table below, always included):",{"type":42,"tag":553,"props":1031,"children":1032},{},[1033,1049,1065,1075,1091,1107,1123,1134,1144],{"type":42,"tag":84,"props":1034,"children":1035},{},[1036,1041,1042,1047],{"type":42,"tag":64,"props":1037,"children":1039},{"className":1038},[],[1040],{"type":47,"value":973},{"type":47,"value":312},{"type":42,"tag":64,"props":1043,"children":1045},{"className":1044},[],[1046],{"type":47,"value":980},{"type":47,"value":1048}," → \"I can run a commitment pricing assessment (RI vs DSP comparison) so you have the numbers to bring to procurement.\"",{"type":42,"tag":84,"props":1050,"children":1051},{},[1052,1057,1058,1063],{"type":42,"tag":64,"props":1053,"children":1055},{"className":1054},[],[1056],{"type":47,"value":869},{"type":47,"value":312},{"type":42,"tag":64,"props":1059,"children":1061},{"className":1060},[],[1062],{"type":47,"value":876},{"type":47,"value":1064}," → \"I can help with snapshot creation or final-snapshot validation before deletion.\"",{"type":42,"tag":84,"props":1066,"children":1067},{},[1068,1073],{"type":42,"tag":64,"props":1069,"children":1071},{"className":1070},[],[1072],{"type":47,"value":699},{"type":47,"value":1074}," (major version) → \"I can run an upgrade assessment — target version recommendation, prechecks, and pre\u002Fpost checklists.\"",{"type":42,"tag":84,"props":1076,"children":1077},{},[1078,1083,1084,1089],{"type":42,"tag":64,"props":1079,"children":1081},{"className":1080},[],[1082],{"type":47,"value":887},{"type":47,"value":312},{"type":42,"tag":64,"props":1085,"children":1087},{"className":1086},[],[1088],{"type":47,"value":894},{"type":47,"value":1090}," → \"I can validate the cluster's state and review the failover\u002Fswitchover plan with you.\"",{"type":42,"tag":84,"props":1092,"children":1093},{},[1094,1099,1100,1105],{"type":42,"tag":64,"props":1095,"children":1097},{"className":1096},[],[1098],{"type":47,"value":991},{"type":47,"value":312},{"type":42,"tag":64,"props":1101,"children":1103},{"className":1102},[],[1104],{"type":47,"value":998},{"type":47,"value":1106}," → \"I can check for pending modifications and recommend a maintenance window.\"",{"type":42,"tag":84,"props":1108,"children":1109},{},[1110,1115,1116,1121],{"type":42,"tag":64,"props":1111,"children":1113},{"className":1112},[],[1114],{"type":47,"value":915},{"type":47,"value":606},{"type":42,"tag":64,"props":1117,"children":1119},{"className":1118},[],[1120],{"type":47,"value":922},{"type":47,"value":1122}," → \"Rotate the password via AWS Secrets Manager or the AWS Console; both are safer than a direct API call. I can walk you through enabling Secrets Manager managed rotation.\"",{"type":42,"tag":84,"props":1124,"children":1125},{},[1126,1132],{"type":42,"tag":64,"props":1127,"children":1129},{"className":1128},[],[1130],{"type":47,"value":1131},"--publicly-accessible",{"type":47,"value":1133}," → \"Making the instance publicly accessible exposes the database directly to the internet — this is a security anti-pattern even for prototypes. Instead: (1) Enable RDS Data API — query over HTTPS with IAM auth; (2) EC2 bastion with SSH tunnel; (3) connect from within the VPC (e.g. a workload in the same VPC or via VPN\u002FDirect Connect). I can help you set up any of these.\"",{"type":42,"tag":84,"props":1135,"children":1136},{},[1137,1142],{"type":42,"tag":64,"props":1138,"children":1140},{"className":1139},[],[1141],{"type":47,"value":933},{"type":47,"value":1143}," → \"I can describe the cluster's current security-group configuration and help you draft the intended change so you can apply it through your team's change-control process or the AWS Console.\"",{"type":42,"tag":84,"props":1145,"children":1146},{},[1147,1152],{"type":42,"tag":64,"props":1148,"children":1150},{"className":1149},[],[1151],{"type":47,"value":944},{"type":47,"value":1153}," → \"I can review the current parameter group and compare it against the target group (highlighting reboot-required parameters) so you can prepare the change for your team's change-control process or the AWS Console.\"",{"type":42,"tag":544,"props":1155,"children":1156},{},[],{"type":47,"value":1158},"Never omit paragraph 2. A refusal without an alternative is incomplete.",{"type":42,"tag":84,"props":1160,"children":1161},{},[1162,1167,1169,1174,1176,1181],{"type":42,"tag":56,"props":1163,"children":1164},{},[1165],{"type":47,"value":1166},"Reference loading.",{"type":47,"value":1168}," Before responding to any matched sub-skill request, you MUST read ",{"type":42,"tag":64,"props":1170,"children":1172},{"className":1171},[],[1173],{"type":47,"value":131},{"type":47,"value":1175}," using your file-read tool (",{"type":42,"tag":64,"props":1177,"children":1179},{"className":1178},[],[1180],{"type":47,"value":123},{"type":47,"value":1182}," if available, otherwise whatever your runtime exposes). Do not answer a matched sub-skill from the registry summary alone. Announce the path in your reply.",{"type":42,"tag":84,"props":1184,"children":1185},{},[1186,1191],{"type":42,"tag":56,"props":1187,"children":1188},{},[1189],{"type":47,"value":1190},"Stay in scope.",{"type":47,"value":1192}," Once this skill is active, recommend the best Aurora MySQL configuration for the workload. Do not suggest non-AWS alternatives. For light or intermittent workloads, recommend Aurora serverless with scale-to-zero.",{"type":42,"tag":84,"props":1194,"children":1195},{},[1196,1201],{"type":42,"tag":56,"props":1197,"children":1198},{},[1199],{"type":47,"value":1200},"Never fabricate.",{"type":47,"value":1202}," Do NOT invent AWS API results, pricing numbers, version lists, or instance metadata. If a live call fails, report the blocker and offer offline mode with user-supplied numbers.",{"type":42,"tag":84,"props":1204,"children":1205},{},[1206,1211],{"type":42,"tag":56,"props":1207,"children":1208},{},[1209],{"type":47,"value":1210},"Carry context forward.",{"type":47,"value":1212}," Pass along cluster ID, region, and workload details the user already supplied. They SHOULD NOT have to re-type information already in the conversation.",{"type":42,"tag":84,"props":1214,"children":1215},{},[1216,1221],{"type":42,"tag":56,"props":1217,"children":1218},{},[1219],{"type":47,"value":1220},"Broad requests.",{"type":47,"value":1222}," If the user says \"help me with Aurora MySQL\" or \"analyze my cluster\" without specifying a domain (create, sizing, I\u002FO, commitment, upgrade), present the sub-skill domains as one line each and ask which they want to focus on. Do NOT silently pick a sub-skill and run it. Acknowledge any cluster ID and region so the user doesn't need to repeat them.",{"type":42,"tag":84,"props":1224,"children":1225},{},[1226,1231],{"type":42,"tag":56,"props":1227,"children":1228},{},[1229],{"type":47,"value":1230},"Out-of-scope topics.",{"type":47,"value":1232}," If the user asks about an Aurora feature not covered by a sub-skill (e.g., Global Database, Blue\u002FGreen Deployments, RDS Proxy), note that it is not covered by a specific sub-skill, answer from general Aurora knowledge, and link to the relevant AWS documentation page.",{"type":42,"tag":84,"props":1234,"children":1235},{},[1236,1241,1243,1249],{"type":42,"tag":56,"props":1237,"children":1238},{},[1239],{"type":47,"value":1240},"Credential safety.",{"type":47,"value":1242}," Do not create, store, or display long-lived credentials or DB passwords. ",{"type":42,"tag":64,"props":1244,"children":1246},{"className":1245},[],[1247],{"type":47,"value":1248},"aws rds generate-db-auth-token",{"type":47,"value":1250}," is approved when IAM database authentication is enabled on the cluster — it produces a short-lived (15-minute) IAM token. Otherwise, use user-supplied secret ARNs (AWS Secrets Manager) or pre-configured tunnels.",{"type":42,"tag":84,"props":1252,"children":1253},{},[1254,1259],{"type":42,"tag":56,"props":1255,"children":1256},{},[1257],{"type":47,"value":1258},"Present results clearly.",{"type":47,"value":1260}," Use tables with dollar figures, ACU numbers, and recommendation labels. Do NOT show derivation or arithmetic steps. Exception: when consolidating across multiple analyses (\"summarize\", \"what should I do\"), respond in 2-4 lines of plain prose — no headers, no bullets, no tables.",{"type":42,"tag":73,"props":1262,"children":1264},{"id":1263},"scripts",[1265],{"type":47,"value":1266},"Scripts",{"type":42,"tag":50,"props":1268,"children":1269},{},[1270,1272,1278,1280,1286],{"type":47,"value":1271},"Bundled scripts in ",{"type":42,"tag":64,"props":1273,"children":1275},{"className":1274},[],[1276],{"type":47,"value":1277},"scripts\u002F",{"type":47,"value":1279}," for offline analysis. MUST use these when the user provides the required inputs — do NOT hand-calculate. Each script documents its full flags\u002Fusage in its own ",{"type":42,"tag":64,"props":1281,"children":1283},{"className":1282},[],[1284],{"type":47,"value":1285},"--help",{"type":47,"value":1287}," and header docstring; read those on demand rather than relying only on the one-line usage below.",{"type":42,"tag":50,"props":1289,"children":1290},{},[1291,1296],{"type":42,"tag":56,"props":1292,"children":1293},{},[1294],{"type":47,"value":1295},"Script execution model:",{"type":47,"value":1297}," If a shell is available, execute the script directly and present the output. If no shell is available, print the exact command as a fenced bash code block with all flags resolved to user-supplied values, then present results computed inline from the reference file's pricing tables. (Result-presentation format is governed by the Operating procedure \u002F Global rules — no derivation steps.)",{"type":42,"tag":227,"props":1299,"children":1300},{},[1301,1322],{"type":42,"tag":231,"props":1302,"children":1303},{},[1304],{"type":42,"tag":235,"props":1305,"children":1306},{},[1307,1312,1317],{"type":42,"tag":239,"props":1308,"children":1309},{},[1310],{"type":47,"value":1311},"Script",{"type":42,"tag":239,"props":1313,"children":1314},{},[1315],{"type":47,"value":1316},"Purpose",{"type":42,"tag":239,"props":1318,"children":1319},{},[1320],{"type":47,"value":1321},"Usage",{"type":42,"tag":266,"props":1323,"children":1324},{},[1325,1351,1377],{"type":42,"tag":235,"props":1326,"children":1327},{},[1328,1337,1342],{"type":42,"tag":273,"props":1329,"children":1330},{},[1331],{"type":42,"tag":64,"props":1332,"children":1334},{"className":1333},[],[1335],{"type":47,"value":1336},"acu_calculator.py",{"type":42,"tag":273,"props":1338,"children":1339},{},[1340],{"type":47,"value":1341},"Aurora serverless ACU sizing",{"type":42,"tag":273,"props":1343,"children":1344},{},[1345],{"type":42,"tag":64,"props":1346,"children":1348},{"className":1347},[],[1349],{"type":47,"value":1350},"python3 scripts\u002Facu_calculator.py estimate --instance \u003Ctype> --cpu-p95 \u003Cval> --cpu-max \u003Cval> --storage \u003Cval>",{"type":42,"tag":235,"props":1352,"children":1353},{},[1354,1363,1368],{"type":42,"tag":273,"props":1355,"children":1356},{},[1357],{"type":42,"tag":64,"props":1358,"children":1360},{"className":1359},[],[1361],{"type":47,"value":1362},"io_optimized_analyzer.py",{"type":42,"tag":273,"props":1364,"children":1365},{},[1366],{"type":47,"value":1367},"I\u002FO-Optimized breakeven",{"type":42,"tag":273,"props":1369,"children":1370},{},[1371],{"type":42,"tag":64,"props":1372,"children":1374},{"className":1373},[],[1375],{"type":47,"value":1376},"python3 scripts\u002Fio_optimized_analyzer.py offline --instance \u003Ctype> --num-instances \u003Cn> --storage-gib \u003Cval> --monthly-io-millions \u003Cval>",{"type":42,"tag":235,"props":1378,"children":1379},{},[1380,1389,1394],{"type":42,"tag":273,"props":1381,"children":1382},{},[1383],{"type":42,"tag":64,"props":1384,"children":1386},{"className":1385},[],[1387],{"type":47,"value":1388},"commitment_pricing_analyzer.py",{"type":42,"tag":273,"props":1390,"children":1391},{},[1392],{"type":47,"value":1393},"RI vs DSP cost comparison",{"type":42,"tag":273,"props":1395,"children":1396},{},[1397,1403,1405,1411],{"type":42,"tag":64,"props":1398,"children":1400},{"className":1399},[],[1401],{"type":47,"value":1402},"python3 scripts\u002Fcommitment_pricing_analyzer.py offline --instance \u003Ctype> --num-instances \u003Cn> --region \u003Cregion>",{"type":47,"value":1404}," (provisioned) or ",{"type":42,"tag":64,"props":1406,"children":1408},{"className":1407},[],[1409],{"type":47,"value":1410},"--serverless --avg-acu \u003Cval>",{"type":47,"value":1412}," (Aurora serverless)",{"type":42,"tag":73,"props":1414,"children":1416},{"id":1415},"troubleshooting",[1417],{"type":47,"value":1418},"Troubleshooting",{"type":42,"tag":553,"props":1420,"children":1421},{},[1422,1502,1527,1537],{"type":42,"tag":84,"props":1423,"children":1424},{},[1425,1430,1432,1438,1440,1446,1448,1454,1455,1461,1462,1468,1469,1475,1476,1482,1484,1490,1492,1501],{"type":42,"tag":56,"props":1426,"children":1427},{},[1428],{"type":47,"value":1429},"AccessDenied",{"type":47,"value":1431},": Attach ",{"type":42,"tag":64,"props":1433,"children":1435},{"className":1434},[],[1436],{"type":47,"value":1437},"AmazonRDSReadOnlyAccess",{"type":47,"value":1439}," + ",{"type":42,"tag":64,"props":1441,"children":1443},{"className":1442},[],[1444],{"type":47,"value":1445},"CloudWatchReadOnlyAccess",{"type":47,"value":1447}," for reads. For creates\u002Fmodifies, use a custom policy scoped to ",{"type":42,"tag":64,"props":1449,"children":1451},{"className":1450},[],[1452],{"type":47,"value":1453},"rds:CreateDBCluster",{"type":47,"value":312},{"type":42,"tag":64,"props":1456,"children":1458},{"className":1457},[],[1459],{"type":47,"value":1460},"rds:CreateDBInstance",{"type":47,"value":312},{"type":42,"tag":64,"props":1463,"children":1465},{"className":1464},[],[1466],{"type":47,"value":1467},"rds:ModifyDBCluster",{"type":47,"value":312},{"type":42,"tag":64,"props":1470,"children":1472},{"className":1471},[],[1473],{"type":47,"value":1474},"rds:ModifyDBInstance",{"type":47,"value":312},{"type":42,"tag":64,"props":1477,"children":1479},{"className":1478},[],[1480],{"type":47,"value":1481},"rds:AddTagsToResource",{"type":47,"value":1483},", and ",{"type":42,"tag":64,"props":1485,"children":1487},{"className":1486},[],[1488],{"type":47,"value":1489},"rds:Describe*",{"type":47,"value":1491},". See ",{"type":42,"tag":1493,"props":1494,"children":1498},"a",{"href":1495,"rel":1496},"https:\u002F\u002Fdocs.aws.amazon.com\u002FAmazonRDS\u002Flatest\u002FAuroraUserGuide\u002FUsingWithRDS.IAM.html",[1497],"nofollow",[1499],{"type":47,"value":1500},"Identity and access management for Amazon Aurora",{"type":47,"value":837},{"type":42,"tag":84,"props":1503,"children":1504},{},[1505,1510,1512,1518,1519,1525],{"type":42,"tag":56,"props":1506,"children":1507},{},[1508],{"type":47,"value":1509},"ExpiredToken \u002F credentials",{"type":47,"value":1511},": Refresh your AWS credentials using whatever mechanism you use (e.g. re-run your SSO\u002F",{"type":42,"tag":64,"props":1513,"children":1515},{"className":1514},[],[1516],{"type":47,"value":1517},"aws sso login",{"type":47,"value":312},{"type":42,"tag":64,"props":1520,"children":1522},{"className":1521},[],[1523],{"type":47,"value":1524},"ada credentials update",{"type":47,"value":1526},", assume-role, or refresh the profile), then retry. Do not assume a specific credential tool.",{"type":42,"tag":84,"props":1528,"children":1529},{},[1530,1535],{"type":42,"tag":56,"props":1531,"children":1532},{},[1533],{"type":47,"value":1534},"DBClusterNotFoundFault",{"type":47,"value":1536},": Verify region and cluster ID.",{"type":42,"tag":84,"props":1538,"children":1539},{},[1540,1545],{"type":42,"tag":56,"props":1541,"children":1542},{},[1543],{"type":47,"value":1544},"Throttling",{"type":47,"value":1546},": Retry once, then narrow scope.",{"type":42,"tag":73,"props":1548,"children":1550},{"id":1549},"additional-resources",[1551],{"type":47,"value":1552},"Additional Resources",{"type":42,"tag":553,"props":1554,"children":1555},{},[1556,1566,1576,1586],{"type":42,"tag":84,"props":1557,"children":1558},{},[1559],{"type":42,"tag":1493,"props":1560,"children":1563},{"href":1561,"rel":1562},"https:\u002F\u002Fdocs.aws.amazon.com\u002FAmazonRDS\u002Flatest\u002FAuroraUserGuide\u002F",[1497],[1564],{"type":47,"value":1565},"Aurora User Guide",{"type":42,"tag":84,"props":1567,"children":1568},{},[1569],{"type":42,"tag":1493,"props":1570,"children":1573},{"href":1571,"rel":1572},"https:\u002F\u002Faws.amazon.com\u002Frds\u002Faurora\u002Fpricing\u002F",[1497],[1574],{"type":47,"value":1575},"Aurora pricing",{"type":42,"tag":84,"props":1577,"children":1578},{},[1579],{"type":42,"tag":1493,"props":1580,"children":1583},{"href":1581,"rel":1582},"https:\u002F\u002Fdocs.aws.amazon.com\u002FAmazonRDS\u002Flatest\u002FAuroraUserGuide\u002Faurora-serverless-v2.html",[1497],[1584],{"type":47,"value":1585},"Aurora serverless",{"type":42,"tag":84,"props":1587,"children":1588},{},[1589],{"type":42,"tag":1493,"props":1590,"children":1593},{"href":1591,"rel":1592},"https:\u002F\u002Fdocs.aws.amazon.com\u002FAmazonRDS\u002Flatest\u002FAuroraUserGuide\u002FUSER_UpgradeDBInstance.Upgrading.html",[1497],[1594],{"type":47,"value":1595},"Aurora MySQL upgrades",{"type":42,"tag":73,"props":1597,"children":1599},{"id":1598},"handoff-from-aws-database-selection",[1600],{"type":47,"value":1601},"Handoff from aws-database-selection",{"type":42,"tag":50,"props":1603,"children":1604},{},[1605,1607,1613,1615,1621,1623,1629],{"type":47,"value":1606},"This skill can be entered from ",{"type":42,"tag":64,"props":1608,"children":1610},{"className":1609},[],[1611],{"type":47,"value":1612},"aws-database-selection",{"type":47,"value":1614}," after it produces a ",{"type":42,"tag":64,"props":1616,"children":1618},{"className":1617},[],[1619],{"type":47,"value":1620},"requirements.json",{"type":47,"value":1622},". When you see a path matching ",{"type":42,"tag":64,"props":1624,"children":1626},{"className":1625},[],[1627],{"type":47,"value":1628},"aws_dbs_requirements\u002F*\u002Frequirements.json",{"type":47,"value":1630}," in conversation:",{"type":42,"tag":80,"props":1632,"children":1633},{},[1634,1655,1660,1665],{"type":42,"tag":84,"props":1635,"children":1636},{},[1637,1639,1645,1647,1653],{"type":47,"value":1638},"Read the artifact. Sanity-check it has the fields you'll use — at minimum ",{"type":42,"tag":64,"props":1640,"children":1642},{"className":1641},[],[1643],{"type":47,"value":1644},"engine",{"type":47,"value":1646}," (or workload type), ",{"type":42,"tag":64,"props":1648,"children":1650},{"className":1649},[],[1651],{"type":47,"value":1652},"region",{"type":47,"value":1654},", and the workload signals you route on (capacity\u002FACU hints, storage size, connectivity\u002FVPC needs, version). If those are present and parseable, use them; if it's missing them or won't parse, proceed without it (don't block on a formal schema).",{"type":42,"tag":84,"props":1656,"children":1657},{},[1658],{"type":47,"value":1659},"Acknowledge relevant facts in 1-2 bold sentences.",{"type":42,"tag":84,"props":1661,"children":1662},{},[1663],{"type":47,"value":1664},"Scope-check: if the artifact doesn't match Aurora (e.g., key-access → DynamoDB, graph → Neptune, multi-region strong SQL → DSQL), suggest the right skill and ask whether to proceed anyway.",{"type":42,"tag":84,"props":1666,"children":1667},{},[1668],{"type":47,"value":1669},"Continue with this skill's sub-skill routing.",{"items":1671,"total":1831},[1672,1689,1704,1719,1734,1744,1759,1775,1782,1794,1806,1821],{"slug":1673,"name":1673,"fn":1674,"description":1675,"org":1676,"tags":1677,"stars":24,"repoUrl":25,"updatedAt":1688},"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},[1678,1681,1684,1685],{"name":1679,"slug":1680,"type":15},"Agents","agents",{"name":1682,"slug":1683,"type":15},"Automation","automation",{"name":23,"slug":8,"type":15},{"name":1686,"slug":1687,"type":15},"Engineering","engineering","2026-07-12T08:42:53.812877",{"slug":1690,"name":1690,"fn":1691,"description":1692,"org":1693,"tags":1694,"stars":24,"repoUrl":25,"updatedAt":1703},"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},[1695,1696,1699,1702],{"name":1679,"slug":1680,"type":15},{"name":1697,"slug":1698,"type":15},"API Development","api-development",{"name":1700,"slug":1701,"type":15},"Authentication","authentication",{"name":23,"slug":8,"type":15},"2026-07-16T06:00:38.866147",{"slug":1705,"name":1705,"fn":1706,"description":1707,"org":1708,"tags":1709,"stars":24,"repoUrl":25,"updatedAt":1718},"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},[1710,1711,1712,1715],{"name":1679,"slug":1680,"type":15},{"name":23,"slug":8,"type":15},{"name":1713,"slug":1714,"type":15},"Debugging","debugging",{"name":1716,"slug":1717,"type":15},"Observability","observability","2026-07-16T06:00:44.679093",{"slug":1720,"name":1720,"fn":1721,"description":1722,"org":1723,"tags":1724,"stars":24,"repoUrl":25,"updatedAt":1733},"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},[1725,1726,1727,1730],{"name":1679,"slug":1680,"type":15},{"name":23,"slug":8,"type":15},{"name":1728,"slug":1729,"type":15},"CI\u002FCD","ci-cd",{"name":1731,"slug":1732,"type":15},"Deployment","deployment","2026-07-12T08:42:55.059577",{"slug":1735,"name":1735,"fn":1736,"description":1737,"org":1738,"tags":1739,"stars":24,"repoUrl":25,"updatedAt":1743},"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},[1740,1741,1742],{"name":1679,"slug":1680,"type":15},{"name":23,"slug":8,"type":15},{"name":1731,"slug":1732,"type":15},"2026-07-12T08:42:51.963247",{"slug":1745,"name":1745,"fn":1746,"description":1747,"org":1748,"tags":1749,"stars":24,"repoUrl":25,"updatedAt":1758},"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},[1750,1751,1752,1755],{"name":1679,"slug":1680,"type":15},{"name":23,"slug":8,"type":15},{"name":1753,"slug":1754,"type":15},"Best Practices","best-practices",{"name":1756,"slug":1757,"type":15},"Security","security","2026-07-16T06:00:42.174705",{"slug":1760,"name":1760,"fn":1761,"description":1762,"org":1763,"tags":1764,"stars":24,"repoUrl":25,"updatedAt":1774},"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},[1765,1766,1767,1770,1771],{"name":1679,"slug":1680,"type":15},{"name":23,"slug":8,"type":15},{"name":1768,"slug":1769,"type":15},"Evals","evals",{"name":1716,"slug":1717,"type":15},{"name":1772,"slug":1773,"type":15},"Performance","performance","2026-07-12T08:42:56.488105",{"slug":4,"name":4,"fn":5,"description":6,"org":1776,"tags":1777,"stars":24,"repoUrl":25,"updatedAt":26},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1778,1779,1780,1781],{"name":23,"slug":8,"type":15},{"name":17,"slug":18,"type":15},{"name":13,"slug":14,"type":15},{"name":20,"slug":21,"type":15},{"slug":69,"name":69,"fn":1783,"description":1784,"org":1785,"tags":1786,"stars":24,"repoUrl":25,"updatedAt":1793},"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},[1787,1788,1789,1792],{"name":23,"slug":8,"type":15},{"name":17,"slug":18,"type":15},{"name":1790,"slug":1791,"type":15},"PostgreSQL","postgresql",{"name":20,"slug":21,"type":15},"2026-07-16T06:00:34.789624",{"slug":1795,"name":1795,"fn":1796,"description":1797,"org":1798,"tags":1799,"stars":24,"repoUrl":25,"updatedAt":1805},"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},[1800,1801,1802],{"name":1679,"slug":1680,"type":15},{"name":23,"slug":8,"type":15},{"name":1803,"slug":1804,"type":15},"LLM","llm","2026-07-25T05:30:35.20899",{"slug":1807,"name":1807,"fn":1808,"description":1809,"org":1810,"tags":1811,"stars":24,"repoUrl":25,"updatedAt":1820},"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},[1812,1813,1814,1817],{"name":23,"slug":8,"type":15},{"name":17,"slug":18,"type":15},{"name":1815,"slug":1816,"type":15},"MongoDB","mongodb",{"name":1818,"slug":1819,"type":15},"NoSQL","nosql","2026-07-12T08:43:00.455878",{"slug":1822,"name":1822,"fn":1823,"description":1824,"org":1825,"tags":1826,"stars":24,"repoUrl":25,"updatedAt":1830},"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},[1827,1828,1829],{"name":23,"slug":8,"type":15},{"name":17,"slug":18,"type":15},{"name":1818,"slug":1819,"type":15},"2026-07-16T06:00:37.690386",115,{"items":1833,"total":1883},[1834,1841,1848,1855,1862,1868,1875],{"slug":1673,"name":1673,"fn":1674,"description":1675,"org":1835,"tags":1836,"stars":24,"repoUrl":25,"updatedAt":1688},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1837,1838,1839,1840],{"name":1679,"slug":1680,"type":15},{"name":1682,"slug":1683,"type":15},{"name":23,"slug":8,"type":15},{"name":1686,"slug":1687,"type":15},{"slug":1690,"name":1690,"fn":1691,"description":1692,"org":1842,"tags":1843,"stars":24,"repoUrl":25,"updatedAt":1703},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1844,1845,1846,1847],{"name":1679,"slug":1680,"type":15},{"name":1697,"slug":1698,"type":15},{"name":1700,"slug":1701,"type":15},{"name":23,"slug":8,"type":15},{"slug":1705,"name":1705,"fn":1706,"description":1707,"org":1849,"tags":1850,"stars":24,"repoUrl":25,"updatedAt":1718},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1851,1852,1853,1854],{"name":1679,"slug":1680,"type":15},{"name":23,"slug":8,"type":15},{"name":1713,"slug":1714,"type":15},{"name":1716,"slug":1717,"type":15},{"slug":1720,"name":1720,"fn":1721,"description":1722,"org":1856,"tags":1857,"stars":24,"repoUrl":25,"updatedAt":1733},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1858,1859,1860,1861],{"name":1679,"slug":1680,"type":15},{"name":23,"slug":8,"type":15},{"name":1728,"slug":1729,"type":15},{"name":1731,"slug":1732,"type":15},{"slug":1735,"name":1735,"fn":1736,"description":1737,"org":1863,"tags":1864,"stars":24,"repoUrl":25,"updatedAt":1743},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1865,1866,1867],{"name":1679,"slug":1680,"type":15},{"name":23,"slug":8,"type":15},{"name":1731,"slug":1732,"type":15},{"slug":1745,"name":1745,"fn":1746,"description":1747,"org":1869,"tags":1870,"stars":24,"repoUrl":25,"updatedAt":1758},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1871,1872,1873,1874],{"name":1679,"slug":1680,"type":15},{"name":23,"slug":8,"type":15},{"name":1753,"slug":1754,"type":15},{"name":1756,"slug":1757,"type":15},{"slug":1760,"name":1760,"fn":1761,"description":1762,"org":1876,"tags":1877,"stars":24,"repoUrl":25,"updatedAt":1774},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1878,1879,1880,1881,1882],{"name":1679,"slug":1680,"type":15},{"name":23,"slug":8,"type":15},{"name":1768,"slug":1769,"type":15},{"name":1716,"slug":1717,"type":15},{"name":1772,"slug":1773,"type":15},114]