aws-database
An agent skill by aws, from aws/agent-toolkit-for-aws. Tags: analysis, architecture, cloud, database, validation.
What it does
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.
Install
With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:
npx skills add aws/agent-toolkit-for-aws --skill aws-databaseOr 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/plugins/aws-core/skills/aws-database ~/.claude/skills/aws-databaseSafety box score
Grade B, low risk: 12 of 100 risk points, rated 2026-10-14. 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 is a routing-only AWS database skill: it chooses the right database service or hands off to a service-specific skill, rather than running code or changing AWS resources itself. The main exposure is indirect — it pushes the agent to use remote AWS docs/MCP lookups and to follow a fairly strong instruction hierarchy when deciding how to answer.
| Category | Level | Why |
|---|---|---|
| Code & shell execution | 0 (none) | No shell commands, scripts, or code execution are shipped here; the files are plain markdown guidance and registry tables. |
| Network access | 1 (low) | It explicitly directs the agent to use AWS MCP documentation tools and to fetch remote `llms.txt` docs, e.g. `aws___read_documentation`, `aws___search_documentation`, and `fetch the service's llms.txt URL`. |
| Filesystem reach | 0 (none) | The skill only refers to reading its own `assets/` and `references/` files; it does not write or delete files outside the workspace. |
| Secrets & credentials | 0 (none) | There is no handling of tokens, passwords, `.env` files, keychains, browser sessions, or CLI logins. |
| Privilege & persistence | 0 (none) | No sudo, global installs, services, scheduled tasks, or OS/shell configuration changes are requested. |
| Instruction hijack surface | 1 (low) | The skill uses strong control language such as `STOP — Do not answer from general knowledge` and `Never skip the routing step`, which steers the agent's behavior but does not ask it to hide instructions or ignore confirmations. |
| Irreversible actions | 1 (low) | It can route the agent into service-specific handoff workflows for operational help, but `references/handoff.md` says to confirm before any provisioning action. |
| Transparency | 0 (none) | All shipped content is readable markdown; there are no binaries, minified blobs, or decoded-at-runtime code. |
Before installing
- Confirm you want a router skill that will steer database questions to AWS docs and service-specific skills.
- Check that remote AWS documentation lookups via MCP/llms.txt are acceptable in your environment.
- If you plan to use it for provisioning later, review the downstream service skill too, not just this router.
Rated 2026-10-14 by an automated review of 21 files from the skill's repository.
Source
- Repository
- aws/agent-toolkit-for-aws (all skills from this repository)
- Path
- plugins/aws-core/skills/aws-database/SKILL.md
- Branch
- main
- Collection
- aws-core
- Updated
- 2026-09-19
Related skills
- agents-harden — Use when preparing your agent for production — IAM scoping, inbound auth (JWT, SigV4), secrets management, cold start optimization, session lifecycle.
- chatting-with-aws-devops-agent — Have a fast, conversational analysis with the AWS DevOps Agent.
- domain-modeling — Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.
- aws-ai-ml — Selects, deploys, and customizes AI models on Amazon SageMaker.
- aws-blocks — Guides building full-stack applications with AWS Blocks — an Infrastructure-from-Code framework.
- aws-cloudformation — Authors, validates, and troubleshoots AWS CloudFormation templates.