Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →World-class data engineering skill for building scalable data pipelines, ETL/ELT systems, and data infrastructure. Expertise in Python, SQL, Spark, Airflow, dbt, Kafka, and modern data stack. Includes data modeling, pipeline orchestration, data quality, and DataOps. Use when designing data architectures, building data pipelines, optimizing data workflows, or implementing data governance.
.claude/skills/davila7-senior-data-engineer/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 3014% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 171% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -29% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 186% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 335% | 0% |
World-class senior data engineer skill for production-grade AI/ML/Data systems.
bash# Core Tool 1 python scripts/pipeline_orchestrator.py --input data/ --output results/ # Core Tool 2 python scripts/data_quality_validator.py --target project/ --analyze # Core Tool 3 python scripts/etl_performance_optimizer.py --config config.yaml --deploy
This skill covers world-class capabilities in:
Languages: Python, SQL, R, Scala, Go ML Frameworks: PyTorch, TensorFlow, Scikit-learn, XGBoost Data Tools: Spark, Airflow, dbt, Kafka, Databricks LLM Frameworks: LangChain, LlamaIndex, DSPy Deployment: Docker, Kubernetes, AWS/GCP/Azure Monitoring: MLflow, Weights & Biases, Prometheus Databases: PostgreSQL, BigQuery, Snowflake, Pinecone
Comprehensive guide available in references/data_pipeline_architecture.md covering:
Complete workflow documentation in references/data_modeling_patterns.md including:
Technical reference guide in references/dataops_best_practices.md with:
Enterprise-scale data processing with distributed computing:
Production ML system with high availability:
High-throughput inference system:
Latency:
Throughput:
Availability:
bash# Development python -m pytest tests/ -v --cov python -m black src/ python -m pylint src/ # Training python scripts/train.py --config prod.yaml python scripts/evaluate.py --model best.pth # Deployment docker build -t service:v1 . kubectl apply -f k8s/ helm upgrade service ./charts/ # Monitoring kubectl logs -f deployment/service python scripts/health_check.py
references/data_pipeline_architecture.mdreferences/data_modeling_patterns.mdreferences/dataops_best_practices.mdscripts/ directoryAs a world-class senior professional:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 3,351 | 4,993 | +49% | 1 | 1 | 0% | 199 | 1,473 | +640% | 0 | 0 | — |
case-02 | fail→pass | 4,658 | 21,408 | +360% | 1 | 1 | 0% | 179 | 5,574 | +3014% | 0 | 0 | — |
case-03 | fail→pass | 5,345 | 8,024 | +50% | 1 | 1 | 0% | 936 | 2,537 | +171% | 0 | 0 | — |
case-04 | fail→pass | 13,295 | 3,349 | -75% | 1 | 1 | 0% | 2,518 | 1,796 | -29% | 0 | 0 | — |
case-05 | pass→pass | 9,632 | 5,074 | -47% | 1 | 1 | 0% | 1,468 | 2,083 | +42% | 0 | 0 | — |
case-06 | pass→pass | 8,348 | 2,741 | -67% | 1 | 1 | 0% | 1,619 | 1,677 | +4% | 0 | 0 | — |
case-07 | fail→pass | 3,717 | 2,627 | -29% | 1 | 1 | 0% | 571 | 1,633 | +186% | 0 | 0 | — |
case-08 | fail→pass | 2,558 | 2,107 | -18% | 1 | 1 | 0% | 357 | 1,554 | +335% | 0 | 0 | — |
case-09 | pass→pass | 10,224 | 7,878 | -23% | 1 | 1 | 0% | 1,889 | 2,718 | +44% | 0 | 0 | — |
case-10 | pass→pass | 6,935 | 1,883 | -73% | 1 | 1 | 0% | 1,228 | 1,458 | +19% | 0 | 0 | — |
case-11 | fail→pass | 6,442 | 2,262 | -65% | 1 | 1 | 0% | 1,276 | 1,526 | +20% | 0 | 0 | — |
case-12 | fail→pass | 3,483 | 2,230 | -36% | 1 | 1 | 0% | 616 | 1,538 | +150% | 0 | 0 | — |
case-13 | pass→pass | 1,942 | 1,512 | -22% | 1 | 1 | 0% | 329 | 1,408 | +328% | 0 | 0 | — |
case-14 | fail→pass | 4,161 | 1,508 | -64% | 1 | 1 | 0% | 749 | 1,439 | +92% | 0 | 0 | — |
case-15 | fail→pass | 6,252 | 1,728 | -72% | 1 | 1 | 0% | 1,335 | 1,428 | +7% | 0 | 0 | — |
case-16 | pass→pass | 2,662 | 1,617 | -39% | 1 | 1 | 0% | 462 | 1,427 | +209% | 0 | 0 | — |
case-17 | pass→pass | 2,451 | 2,520 | +3% | 1 | 1 | 0% | 428 | 1,562 | +265% | 0 | 0 | — |
case-18 | pass→pass | 3,199 | 1,810 | -43% | 1 | 1 | 0% | 510 | 1,474 | +189% | 0 | 0 | — |
case-19 | pass→pass | 8,533 | 7,164 | -16% | 1 | 1 | 0% | 1,592 | 2,362 | +48% | 0 | 0 | — |
case-20 | pass→pass | 4,685 | 2,606 | -44% | 1 | 1 | 0% | 800 | 1,480 | +85% | 0 | 0 | — |
case-21 | fail→pass | 7,402 | 1,456 | -80% | 1 | 1 | 0% | 1,199 | 1,393 | +16% | 0 | 0 | — |
case-22 | fail→pass | 5,511 | 2,598 | -53% | 1 | 1 | 0% | 1,015 | 1,651 | +63% | 0 | 0 | — |
case-23 | fail→pass | 6,642 | 1,980 | -70% | 1 | 1 | 0% | 1,144 | 1,443 | +26% | 0 | 0 | — |
case-24 | pass→pass | 8,719 | 9,950 | +14% | 1 | 1 | 0% | 1,890 | 3,167 | +68% | 0 | 0 | — |
case-25 | pass→pass | 7,260 | 5,718 | -21% | 1 | 1 | 0% | 1,576 | 2,257 | +43% | 0 | 0 | — |
case-26 | pass→pass | 10,133 | 12,064 | +19% | 1 | 1 | 0% | 2,105 | 3,783 | +80% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 26 cases were attempted, and 24 counted toward the lift figure. The other 2 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +46 percentage points is the difference between those two pass rates over the 24 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.