Skills Explorer Add Skills

amazon-aurora-mysql

An agent skill by aws, from aws/agent-toolkit-for-aws. Tags: aurora, cloud, database, mysql, performance.

What it does

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/O-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.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add aws/agent-toolkit-for-aws --skill amazon-aurora-mysql

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/amazon-aurora-mysql ~/.claude/skills/amazon-aurora-mysql

Safety box score

Grade D, elevated risk: 56 of 100 risk points, rated 2026-10-19. 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 manages Aurora MySQL cluster creation, modification, upgrade planning, and cost-analysis workflows. The main risks are live cloud mutations, AWS/network calls, credential-touching prechecks, and a few bundled scripts that could not be inspected here.

Category levels, from 0 (none) to 3 (high)
CategoryLevelWhy
Code & shell execution2 (moderate)The skill is designed to run bundled analysis scripts and shell/AWS CLI commands such as `python3 scripts/io_optimized_analyzer.py ...` and `aws rds ...`, so it can execute code and commands beyond passive advice.
Network access2 (moderate)It makes live AWS API calls for RDS, CloudWatch, Pricing, SSM, and Data API, and even downloads the RDS CA bundle with `curl -o /tmp/global-bundle.pem ...`.
Filesystem reach1 (low)Local filesystem impact appears limited to temporary files like `/tmp/global-bundle.pem`; most writes are to AWS resources rather than the user's disk.
Secrets & credentials2 (moderate)The precheck workflow uses short-lived IAM auth tokens (`aws rds generate-db-auth-token`) and Secrets Manager secret ARNs, so it can touch database credentials and auth material even though it avoids storing passwords.
Privilege & persistence2 (moderate)The precheck docs include system-wide package installs with `sudo yum/dnf/apt-get install ...`, which can require elevated privileges on the host.
Instruction hijack surface0 (none)I did not find instructions to ignore safeguards, hide actions, follow remote content, or otherwise subvert the agent's control flow; the skill instead adds confirmation and blocking guardrails.
Irreversible actions3 (high)Inherent to the skill's purpose, it can create and modify Aurora clusters/instances and change storage or scaling after confirmation, so the blast radius includes real cloud resource changes.
Transparency2 (moderate)Two shipped scripts were not readable here (`scripts/acu_calculator.py` and `scripts/commitment_pricing_analyzer.py`), so some executable behavior could not be fully reviewed.

Before installing

Rated 2026-10-19 by an automated review of 31 files from the skill's repository.

Source

Repository
aws/agent-toolkit-for-aws (all skills from this repository)
Path
skills/specialized-skills/database-skills/amazon-aurora-mysql/SKILL.md
Branch
main
Updated
2026-09-19