opensite-ai/opensite-skills / aws-database
aws-database
VerifiedRoutes 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.
| File | Kind | Size |
|---|---|---|
| .aws-skill-metadata | other | 18 B |
| SKILL.md | skill md | 7.8 KB |
| assets/aurora-dsql.md | markdown | 1.4 KB |
| assets/aurora-mysql.md | markdown | 1.9 KB |
| assets/aurora-postgresql.md | markdown | 2.5 KB |
| assets/documentdb.md | markdown | 1.4 KB |
| assets/dynamodb.md | markdown | 2.9 KB |
| assets/elasticache.md | markdown | 3.4 KB |
| assets/keyspaces.md | markdown | 2.0 KB |
| assets/memorydb.md | markdown | 1.7 KB |
| assets/neptune.md | markdown | 2.1 KB |
| assets/odb-aws.md | markdown | 1.9 KB |
| assets/rds-db2.md | markdown | 1.1 KB |
| assets/rds-mariadb.md | markdown | 1.5 KB |
| assets/rds-mysql.md | markdown | 1.2 KB |
| assets/rds-oracle.md | markdown | 1.5 KB |
| assets/rds-postgresql.md | markdown | 1.4 KB |
| assets/rds-sqlserver.md | markdown | 1.3 KB |
| assets/timestream.md | markdown | 1.8 KB |
| references/handoff.md | markdown | 4.1 KB |
| references/report-issue.md | markdown | 3.9 KB |
| references/select.md | markdown | 19.5 KB |
references/report-issue.md
View on GitHub# 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
1. **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.
2. **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 |
3. **Capture as an assertion.** Structure the feedback as a test case — this is the most actionable format for improving the skill:
```json
{
"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`.
4. **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.
5. **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/"
6. **Confirm.** Share the issue or support case URL with the user, or confirm they have the link to proceed.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |