AWS Database

AWSOfficialPublished by AWS

Skill
Meta (authoring, orchestration, planning, memory)
Data and AI
Apache-2.0
No issues found

From the author

Routes any task involving AWS databases — choosing, comparing, recommending, getting started with, or operating a database — to the correct service-specific skill. Supersedes general training-data knowledge with post-training service updates, corrected limitations, and decision procedures for relational (Aurora, DSQL, RDS), key-value (DynamoDB), wide-column (Keyspaces), document (DocumentDB), graph (Neptune), time-series (Timestream), and in-memory/caching (ElastiCache, MemoryDB) workloads. Activates when a user describes building an application on AWS that will store, retrieve, or manage data, even if they do not mention 'database' explicitly.

— the description by AWS

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

The aws-database skill acts as a primary interface for all interactions involving AWS database services. It manages the lifecycle of database tasks by routing requests to specialized sub-skills for selection, configuration, and operational support. By utilizing a registry of service-specific knowledge and handoff procedures, it ensures that users receive accurate, up-to-date guidance for relational, NoSQL, graph, and in-memory workloads on AWS.

What it does

Routes database-related queries to the appropriate service-specific skill.
Assists in selecting the optimal AWS database engine based on workload requirements.
Provides operational guidance for provisioning, scaling, and managing database instances.
Verifies facts against service-specific knowledge cards and documentation.
Handles user feedback and reports regarding incorrect or outdated recommendations.
Integrates with AWS MCP servers for enhanced auditing and sandboxed execution.

When to use it

When you need to choose a database service for a new application on AWS.
When you have questions about configuring, monitoring, or troubleshooting an existing AWS database.
When you need a cost estimate for a specific database workload.
When you are unsure which AWS database service best fits your data model or performance needs.

Advantages

Prevents reliance on outdated training data by prioritizing live documentation and service-specific knowledge.
Ensures consistent and accurate routing to specialized tools for complex database tasks.
Supports a wide range of AWS database engines including Aurora, DynamoDB, and ElastiCache.
Provides a structured feedback loop for reporting issues or missing information.

Usage examples

“I am building a new web app and need a database that supports SQL joins. What should I use?”: The skill will analyze your requirements and guide you through selecting the most appropriate relational database service like Amazon Aurora or RDS.
“How do I scale my existing DynamoDB table to handle higher throughput?”: The skill will identify the request as an operational task and route you to the DynamoDB-specific skill for detailed scaling instructions.

Install

Download the skill as a ZIP:
https://mp-staging.autogineer.com/agent-skills/aws/aws-database/download

Unzip it into the cross-client skills folder of your project:

mkdir -p .agents/skills && unzip aws-database.zip -d .agents/skills

Documentation by AWS

AWS Database

STOP — Do not answer from general knowledge. Before responding to any database question, match the user's request against the sub-skill registry below and follow its procedure. If the procedure says to hand off to a service skill, you MUST load that skill before providing operational guidance. Never skip the routing step.

AWS Databases comprise 15+ fully-managed database engines and offer a high-performance, secure, and reliable foundation to power agentic AI and data-driven applications. Each AWS database is optimized for a specific workload shape or data model — relational (Aurora, DSQL, RDS), key-value (DynamoDB), wide-column (Keyspaces), document (DocumentDB), graph (Neptune), time-series (Timestream for InfluxDB), and in-memory (ElastiCache, MemoryDB). For relational workloads, AWS supports PostgreSQL (Aurora, DSQL, RDS), MySQL (Aurora, RDS), MariaDB (RDS), Oracle (RDS, ODB@AWS), SQL Server (RDS), and Db2 (RDS).

Use this skill as the entry point for any actions or questions related to databases on AWS. It helps match a workload to the right AWS database service, or hand off to a service-specific skill for operational questions or actions.

This skill works with or without the AWS MCP server. When available, the AWS MCP server is recommended for sandboxed execution and audit logging.

Global rules

Match the user's language. Respond in the same language the user writes in. Default to non-technical explanations. Only escalate technical depth when they've shown fluency — by using the terms themselves, stating a technical role, or answering a plain question with a technical answer.
Revise when new information arrives. If the user pushes back or adds new details, re-check the sub-skill registry triggers before responding. Pushback that matches report-issue triggers (e.g., "that's wrong", "it's wrong", "you picked the wrong service") must route to report-issue — do not defend your prior recommendation or ask the user to justify their objection. The goal is the right answer, not consistency with your first response.
Do not rely on training data for facts. AWS databases change frequently. Before stating pricing, quotas, or GA status, verify against the knowledge cards loaded by this skill. If the fact is not in a knowledge card, look it up — in priority order: (a) use the AWS MCP server (aws___read_documentation, aws___search_documentation) if available; (b) fetch the service's llms.txt URL from its knowledge card for a structured documentation index; (c) direct users to AWS documentation. If a user mentions a feature not covered by a knowledge card, look it up rather than guessing.
Verify, don't guess. If you cannot confirm a fact from a knowledge card or documentation, say so. "I'm not sure — check the docs" is better than a confident wrong answer.

How this skill works

Find the sub-skill — Match the user's request against the sub-skill registry below. Match on meaning, not exact wording. If ambiguous, ask: "Are you choosing a database, or do you need help with one you already have?" This matching applies to every user message, not just the first. If a subsequent message matches a different sub-skill's triggers (e.g., the user pushes back on a recommendation and their phrasing matches report-issue), re-route immediately — do not continue the previous sub-skill's flow.
If a sub-skill matches — read references/{sub-skill-id}.md and follow its procedure.
If no sub-skill matches — answer from the knowledge cards in assets/. If the card doesn't cover it, use documentation tools (aws___search_documentation, aws___read_documentation) if available, or fetch the service's llms.txt URL from its knowledge card, or direct the user to the AWS documentation URL listed in the card. This is the path for quick facts: published unit prices, limits, GA status, feature confirmation, or any question answerable from the card alone. Do not load a service skill merely to answer a quick fact covered by the card. A workload-specific cost estimate is not a quick fact: when the user names a service and asks for an estimate based on throughput, storage, topology, or other workload inputs, route to handoff and load the available service skill. Offer deeper service-skill guidance only when it would be useful or the user asks for operational help.

Sub-skill registry

ID	Name	Trigger Phrases	When to Route Here	Next Steps
`select`	Database Selection	"which database", "help me choose", "recommend", "what should I use", "starting a new project", "picking a database", "I need a database", "I'm building", "build a", "how should I store", "best way to handle", "need to support", "design for"	User hasn't chosen a service yet, is comparing options, or describes a workload/data problem without naming a specific service	`handoff`
`handoff`	Service Handoff	"how do I", "configure", "optimize", "troubleshoot", "set up", "migrate to", "connect to", "scale", "upgrade", "monitor", "backup", "restore", "estimate cost", "pricing estimate", "cost for my workload", "build", "create", "deploy", "provision", + named service	User names a specific AWS database service and has an operational, advisory, or action question, including a workload-specific cost estimate	—
`report-issue`	Report Issue	"that's wrong", "incorrect", "bad recommendation", "you should have said", "missing", "skill is wrong", "report this", "file a bug", "report an issue"	User reports that the skill gave incorrect or incomplete guidance	—

Service reference

Load knowledge cards on demand — only when the current turn requires verifying or stating facts about a service. Read assets/{filename} for the relevant service(s). Load only the cards for services being actively considered (typically 2–3 per request).

Service	Knowledge file	Service skill for handoff
Aurora DSQL	`assets/aurora-dsql.md`	`aurora-dsql`
Aurora MySQL	`assets/aurora-mysql.md`	`amazon-aurora-mysql`
Aurora PostgreSQL	`assets/aurora-postgresql.md`	`amazon-aurora-postgresql`
DocumentDB	`assets/documentdb.md`	`amazon-documentdb`
DynamoDB	`assets/dynamodb.md`	`amazon-dynamodb`
ElastiCache	`assets/elasticache.md`	`amazon-elasticache`
Keyspaces	`assets/keyspaces.md`	`amazon-keyspaces`
MemoryDB	`assets/memorydb.md`	—
Neptune	`assets/neptune.md`	`amazon-neptune`
ODB @ AWS	`assets/odb-aws.md`	—
RDS for Db2	`assets/rds-db2.md`	`rds-db2`
RDS for MariaDB	`assets/rds-mariadb.md`	`rds-oss`
RDS for MySQL	`assets/rds-mysql.md`	`rds-oss`
RDS for Oracle	`assets/rds-oracle.md`	`rds-oracle`
RDS for PostgreSQL	`assets/rds-postgresql.md`	`rds-oss`
RDS for SQL Server	`assets/rds-sqlserver.md`	`rds-sqlserver`
Timestream for InfluxDB	`assets/timestream.md`	`timestream-influxdb`

Files

ATTRIBUTION.mdAdded by AutoGineer889 B
LICENSELicence file added by AutoGineer9.9 KiB
NOTICELicence file added by AutoGineer67 B
SKILL.md7.8 KiB
assets/aurora-dsql.md1.4 KiB
assets/aurora-mysql.md1.9 KiB
assets/aurora-postgresql.md2.5 KiB
assets/documentdb.md1.4 KiB
assets/dynamodb.md2.9 KiB
assets/elasticache.md3.4 KiB
assets/keyspaces.md2.0 KiB
assets/memorydb.md1.7 KiB
assets/neptune.md2.1 KiB
assets/odb-aws.md1.9 KiB
assets/rds-db2.md1.1 KiB
assets/rds-mariadb.md1.5 KiB
assets/rds-mysql.md1.2 KiB
assets/rds-oracle.md1.5 KiB
assets/rds-postgresql.md1.4 KiB
assets/rds-sqlserver.md1.3 KiB
assets/timestream.md1.8 KiB
references/handoff.md4.1 KiB
references/report-issue.md3.9 KiB
references/select.md19.5 KiB

references/report-issue.md

Report Issue

Use this when the user reports that the skill gave incorrect guidance, a wrong recommendation, missing information, or could be improved. This is feedback about the skill instructions — not about an AWS service itself.

Procedure

Offer to help. Let the user know you can help them submit feedback, and present the available channels:
- GitHub (primary) — for bug reports and feature requests on the skill itself. Publicly tracked at aws/agent-toolkit-for-aws.
- AWS Support — for issues tied to their AWS account, service behavior, or billing. Requires an AWS Support plan.
- Security concerns — should not be filed publicly. Direct to AWS vulnerability disclosure.
Ask which channel they'd prefer. If they decline to submit anything, thank them and move on.

Categorize. Determine which type of feedback this is:

Category	Signals	Example
Wrong recommendation	"you should have said X not Y", "that's the wrong service"	Skill recommended DynamoDB but the user needed SQL joins
Outdated fact	"that's not true anymore", "pricing changed", "that feature launched"	Knowledge card says no free tier but one exists now
Missing service or feature	"you didn't mention X", "what about Y"	Skill didn't consider MemoryDB for a vector search workload
Unclear guidance	"I don't understand", "that's confusing", "contradicts itself"	Selection logic was ambiguous about serverless
Handoff failure	"it didn't load the skill", "I got stuck after choosing", "no service skill"	Skill chose Aurora PostgreSQL but couldn't hand off to the service skill

Capture as an assertion. Structure the feedback as a test case — this is the most actionable format for improving the skill:

{
  "prompt": "<what the user asked, paraphrased>",
  "expected_service": "<what the correct answer should be>",
  "actual_service": "<what the skill recommended>",
  "category": "<wrong-recommendation | outdated-fact | missing-coverage | unclear-guidance | handoff-failure>",
  "detail": "<brief explanation of why the expected answer is correct>"
}

For non-selection feedback (outdated facts, unclear guidance), omit expected_service and actual_service and expand detail.

Confirm with the user. Summarize what you captured in a sentence or two and ask if it's accurate. Let them correct anything before you proceed to submission.
Route to the right channel.
Based on what the user chose in step 1:
GitHub — Bug report (wrong recommendation, outdated fact, missing coverage, unclear guidance, handoff failure):
- Direct the user to: https://github.com/aws/agent-toolkit-for-aws/issues/new/choose and select the bug report template.
- If you have access to GitHub tools (gh CLI, GitHub MCP), help pre-fill the template from the assertion captured above.
GitHub — Feature request (new capability, new service coverage, workflow suggestion):
- Direct the user to: https://github.com/aws/agent-toolkit-for-aws/issues/new/choose and select the feature request template.
AWS Support (private, or account-specific issues):
- Some users prefer not to file publicly. AWS Support is the right channel for private feedback, account-specific issues, service behavior, billing, or quotas.
- Direct them to: https://console.aws.amazon.com/support/home#/case/create
- Help them identify the right category: the AWS service involved, whether it's technical or account/billing, and the severity.
Security issue:
- Do NOT file as a public GitHub Issue. Tell the user: "Security issues should not be reported publicly. Please report security concerns through AWS's vulnerability disclosure process at https://aws.amazon.com/security/vulnerability-reporting/"
Confirm. Share the issue or support case URL with the user, or confirm they have the link to proceed.

Requirements and compatibility

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Needs: Needs an MCP server

Security

No issues found by our static scan· No issues found

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Attribution and licence

Published by

AWS

Publisher

AWS (Official)

Source

aws/agent-toolkit-for-aws · skills/core-skills/aws-database · commit 0a218f8

Licence

Apache License 2.0 (redistribution allowed)

LICENSE (added by AutoGineer from LICENSE)
NOTICE (added by AutoGineer from NOTICE)
ATTRIBUTION.md (written by AutoGineer)

Synced

2026-11-08

Also distributed in

aws/agent-toolkit-for-aws

AutoGineer is not affiliated with or endorsed by AWS.

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download aws-database.zip

From the author

AutoGineer summary

What it does

When to use it

Advantages

Usage examples

Install

Documentation by AWS

AWS Database

Global rules

How this skill works

Sub-skill registry

Service reference

Files

references/report-issue.md

Report Issue

Procedure

Requirements and compatibility

Security

Attribution and licence

Related skills

Anndata

Liteparse

Usfiscaldata

Geopandas

Markitdown

Zarr Python

Download ZIP