creating-amazon-aurora-db-cluster-with-instances
An agent skill by aws, from aws/agent-toolkit-for-aws. Tags: aurora, cloud, database, deployment, setup.
What it does
Creates a complete Amazon Aurora database cluster with instances, handling cluster creation, instance provisioning, and Secrets Manager password management in the proper sequence. Use when setting up new Aurora MySQL or PostgreSQL clusters with production-ready configuration.
Install
With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:
npx skills add aws/agent-toolkit-for-aws --skill creating-amazon-aurora-db-cluster-with-instances
Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):
git clone --depth 1 https://github.com/aws/agent-toolkit-for-aws
cp -r agent-toolkit-for-aws/skills/specialized-skills/database-skills/creating-amazon-aurora-db-cluster-with-instances ~/.claude/skills/creating-amazon-aurora-db-cluster-with-instances
Safety box score
Grade C, moderate risk: 30 of 100 risk points, rated 2026-10-15. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.
This skill provisions an Amazon Aurora cluster and a database instance in the user’s AWS account, then polls AWS until both are available. The main risks are cloud-side autonomy/cost, repeated API traffic to AWS, and handling of Secrets Manager-managed database credentials.
| Category | Level | Why |
|---|---|---|
| Code & shell execution | 2 (moderate) | It drives AWS CLI operations through `call_aws` (`aws sts get-caller-identity`, `aws rds create-db-cluster`, `aws rds create-db-instance`, `aws rds describe-db-*`), so it executes commands, though only against the AWS API surface. |
| Network access | 2 (moderate) | It sends requests to AWS for identity checks, provisioning, status polling, and endpoint retrieval, so outbound network traffic is inherent to the skill (`get-caller-identity`, `create-db-cluster`, `describe-db-clusters`, `describe-db-instances`). |
| Filesystem reach | 0 (none) | No file reads, writes, deletes, or edits outside the repo are described; the skill is entirely cloud-API driven. |
| Secrets & credentials | 1 (low) | It uses `--manage-master-user-password` and AWS Secrets Manager, but explicitly says not to retrieve or display the password value; the main exposure is secret metadata/ARN handling. |
| Privilege & persistence | 0 (none) | There is no sudo, service installation, shell startup modification, or other local privilege change; the only elevated access is AWS IAM permissions. |
| Instruction hijack surface | 0 (none) | The files do not instruct the agent to ignore higher-level rules, hide actions, or follow remote content; the `MUST` wording is procedural, not prompt injection. |
| Irreversible actions | 3 (high) | The skill directly provisions live AWS resources and waits for them to become available (`create-db-cluster`, `create-db-instance`), which is a high-blast-radius deployment action and can incur charges. |
| Transparency | 0 (none) | There are no binaries, base64 blobs, downloaded installers, or unreadable artifacts; the skill is plain markdown. |
Before installing
- Run it first in a sandbox AWS account, since it creates billable Aurora resources.
- Verify the IAM principal has only the RDS, Secrets Manager, and any KMS permissions it needs.
- Confirm the default engine, instance class, retention, and encryption settings match your policy.
- Decide whether you are comfortable with repeated AWS polling for up to 20 minutes during creation.
Rated 2026-10-15 by an automated review of 2 files from the skill's repository.
Source
- Repository
- aws/agent-toolkit-for-aws (all skills from this repository)
- Path
- skills/specialized-skills/database-skills/creating-amazon-aurora-db-cluster-with-instances/SKILL.md
- Branch
- main
- Updated
- 2026-09-19
Related skills
- amazon-aurora-mysql — Amazon Aurora MySQL — creates, modifies, and advises on Aurora MySQL clusters specifically (MySQL-compatible engine, Aurora serverless, parallel query).
- amazon-aurora-postgresql — Amazon Aurora PostgreSQL — creates, modifies, and advises on Aurora PostgreSQL clusters specifically (PostgreSQL-compatible engine, Aurora serverless.
- agents-deploy — Use when deploying your agent to AWS, or when a deploy has failed.
- aws-ai-ml — Selects, deploys, and customizes AI models on Amazon SageMaker.
- aws-database — Routes any task involving AWS databases — choosing, comparing, recommending, getting started with.
- aws-deployment — Configures CI/CD pipelines using AWS CodePipeline, CodeBuild, CodeDeploy, CodeConnections, and CodeArtifact.