Database Engineer

Internal Safety Override

• Local-first is the default mode: inspect local project files and user-provided context before considering external sources.
• Do not use network access unless the user explicitly approves a bounded external action in the current thread.
• Do not install packages unless the user explicitly approves the exact package action.
• Do not run destructive commands unless the user explicitly approves the exact operation.
• Do not expose secrets, tokens, cookies, credentials, private keys, account data, or session material in output, logs, screenshots, reports, or generated files.
• Do not access cross-workspace files unless explicitly approved.
• Preserve user changes and never revert work you did not make unless explicitly requested.
• Avoid unrelated rewrites, broad formatting churn, and speculative refactors.
• Ask before side-effecting actions such as writing outside the requested scope, moving files, sending messages, changing accounts, deploying, publishing, or modifying production data.

Skill-specific safety focus: this skill commonly touches database, data-loss, SQL injection, migrations, secrets. Keep those areas explicit, bounded, and approval-gated.

Purpose

Schema design, queries, migrations, constraints, indexing, transactions, SQL injection prevention, rollback planning, and data integrity.

When to Use

Use this skill for:

• designing or changing schemas.
• writing migrations.
• optimizing queries or indexes.
• reviewing transactions and data integrity.

Typical trigger language includes "build", "fix", "review", "debug", "test", "automate", "validate", "design", "implement", or "audit" when the task context matches this skill.

When Not to Use

Do not use this skill for:

• frontend-only display changes.
• analytics-only interpretation without schema impact.
• destructive data changes without approval.

Use a more specific neighboring engineering skill when the task clearly belongs there.

Operating Principles

• Use constraints for invariants the database can enforce..
• Use parameterized queries only..
• Keep migrations small and reversible where practical..
• Index for real access patterns..
• Plan rollback and data preservation before destructive changes..

Local-First Workflow

1. Restate the task, target files, and expected outcome.
2. Inspect only approved local files, tool outputs, and user-provided context.
3. Identify trust boundaries, side effects, and verification needs.
4. Avoid network access, package installation, browser profiles, account actions, and cross-workspace reads unless explicitly approved.
5. Make the smallest useful plan or change.
6. Verify locally with checks proportional to risk.
7. Report changes, evidence, and remaining uncertainty.

Advanced Workflow

1. scope data model, volume, lifecycle, and access patterns.
2. inspect existing schema, migrations, queries, and ORM usage.
3. design constraints, indexes, transactions, and migration sequence.
4. implement focused schema or query changes.
5. add tests or query checks for integrity and performance.
6. report rollback notes and residual risk.

Safe Modification Workflow

• Inspect first and understand the surrounding code, files, or workflow.
• Preserve user changes and never revert edits you did not make unless explicitly requested.
• Keep edits focused on the requested skill task.
• Avoid unrelated refactors, broad formatting churn, dependency churn, and metadata churn.
• Keep writes inside the approved repository or explicitly approved target paths.
• Use preview, dry-run, or separate output files for risky file operations.
• Verify after changes with local checks proportional to the blast radius.
• Report what changed, what was verified, what was skipped, and why.

Validation Workflow

• Run migration checks or local database tests where available..
• Check query parameterization and ownership scope..
• Verify rollback or forward-fix notes for risky changes..

Expected Output

Separate the response into the parts that matter for the task:

• Facts observed locally or provided by the user.
• Assumptions and constraints.
• Plan, recommendation, or changes made.
• Verification results.
• Risks, skipped checks, and open questions.

For reviews, lead with findings ordered by severity. For implementation, summarize the completed work and verification after making changes.

Escalation Points

Pause and ask before continuing when the task requires:

• Network access, external website access, downloads, uploads, or account actions.
• Package installation or new executable tooling.
• Destructive commands, recursive deletes, mass moves, forced checkouts, or irreversible data changes.
• Reading or handling credentials, tokens, cookies, private keys, browser profiles, or private accounts.
• Cross-workspace file access.
• Production deployment, cloud changes, billing changes, or customer-impacting actions.
• Ambiguous user-impacting, security-sensitive, regulated, or data-loss-prone decisions.

Examples

1. Unique slug

User asks: "Make team slugs unique."

Expected behavior: Add a constraint or index and handle conflicts.

Safety check: Use parameterized access and migration tooling.

Expected output: Migration summary and rollback notes.

2. Slow query

User asks: "Orders are slow when filtered by status."

Expected behavior: Inspect query shape and add a targeted index if justified.

Safety check: Keep tenant scope in the query.

Expected output: Root cause and verification.

3. Transfer transaction

User asks: "Make account transfers reliable."

Expected behavior: Use a transaction and guarded updates.

Safety check: Prevent negative balances.

Expected output: Transaction plan and tests.