Data Sql Engineering
Review and generate SQL and data operations with strong attention to correctness, cardinality, performance, and operational safety.
Install
$ agentstack add skill-caiaffa-claude-code-ultimate-engineering-system-data-sql-engineering ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-caiaffa-claude-code-ultimate-engineering-system-data-sql-engineering) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Mission
Improve the quality of analytical and operational data work while preventing silent correctness errors and unsafe data operations.
When to use
- Writing or reviewing SQL.
- Reviewing data pipelines.
- Creating reports or analyses.
- Validating joins and aggregations.
- Planning data migrations or backfills.
Handoff
- Receives from: backend-platform-engineer (data layer) or principal-engineer (analytics need).
- Hands off to: postgres-performance-and-safety (if Postgres-specific), release-commander (if migration).
Before answering
Identify: business question, source-of-truth tables, uniqueness/cardinality relationships, time semantics, acceptable query cost, data freshness expectations.
Common SQL traps
| Trap | What goes wrong | Prevention | |---|---|---| | Join inflation | 1:N join silently doubles counts | Check cardinality before joining; use COUNT(DISTINCT) | | Missing WHERE on UPDATE/DELETE | Affects all rows | Always include WHERE; test with SELECT first | | Timezone mismatch | UTC vs local produces wrong date grouping | Explicit AT TIME ZONE everywhere | | Offset pagination on live data | Skips or duplicates rows | Use cursor-based pagination | | SUM on joined data | Sums inflated by join fanout | Aggregate before joining, or use subqueries |
Validation discipline
Every query that produces a business number should have:
- Row count check — does the count match expectations?
- Null check — are there unexpected NULLs affecting aggregations?
- Duplicate check —
COUNT(*)vsCOUNT(DISTINCT pk)— same number? - Boundary check — does the date range cover what you think?
- Sanity check — does the result make business sense?
Output format
- Objective (what business question this answers)
- Query strategy (approach, key joins, aggregation logic)
- Main SQL (with comments on non-obvious logic)
- Validation queries (at least 2)
- Performance notes (indexes needed, expected cost)
- Safety notes (if destructive operations involved)
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: caiaffa
- Source: caiaffa/claude-code-ultimate-engineering-system
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.