SkillsBench is a benchmark for measuring how effectively AI agents use modular skills—folders containing instructions, scripts, and resources—to complete specialized tasks. It helps researchers and developers evaluate both skill quality and agent behavior, including tasks that require combining multiple skills. The catalogue’s skills and instructions are evaluated as part of this workflow.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/benchflow-ai/skillsbench/senior-data-engineernpx skills add benchflow-ai/skillsbench --skill senior-data-engineergit clone --depth 1 https://github.com/benchflow-ai/skillsbenchWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/benchflow-ai/skillsbench/senior-data-engineer)<a href="https://agentmods.dev/skills/benchflow-ai/skillsbench/senior-data-engineer"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/senior-data-engineer.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00100 | $0.05127 |
| Opus 5 | $0.00050 | $0.02563 |
| Sonnet 5 | $0.00020 | $0.01025 |
| Haiku 4.5 | $0.00010 | $0.00513 |
Grade A, and why
senior-data-engineer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- senior-data-engineer — 98% identical, 5 lines differ
How it starts
The opening of the file, as written. The whole thing — 606 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Senior Data Engineer
Core Capabilities
- Batch Pipeline Orchestration - Design and implement production-ready ETL/ELT pipelines with Airflow, intelligent dependency resolution, retry logic, and comprehensive monitoring
- Real-Time Streaming - Build event-driven streaming pipelines with Kafka, Flink, Kinesis, and Spark Streaming with exactly-once semantics and sub-second latency
- Data Quality Management - Comprehensive batch and streaming data quality validation covering completeness, accuracy, consistency, timeliness, and validity
- Streaming Quality Monitoring - Track consumer lag, data freshness, schema drift, throughput, and dead letter queue rates for streaming pipelines
- Performance Optimization - Analyze and optimize pipeline performance with query optimization, Spark tuning, and cost analysis recommendations
Key Workflows
Workflow 1: Build ETL Pipeline
Time: 2-4 hours
Steps:
- Design pipeline architecture using Lambda, Kappa, or Medallion pattern
- Configure YAML pipeline definition with sources, transformations, targets
- Generate Airflow DAG with
pipeline_orchestrator.py - Define data quality validation rules
- Deploy and configure monitoring/alerting
Expected Output: Production-ready ETL pipeline with 99%+ success rate, automated quality checks, and comprehensive monitoring
Workflow 2: Build Real-Time Streaming Pipeline
Time: 3-5 days
Steps:
- Select streaming architecture (Kappa vs Lambda) based on requirements
- Configure streaming pipeline YAML (sources, processing, sinks, quality)
- Generate Kafka configurations with
kafka_config_generator.py - Generate Flink/Spark job scaffolding with
stream_processor.py - Deploy and monitor with
streaming_quality_validator.py
Expected Output: Streaming pipeline processing 10K+ events/sec with P99 latency < 1s, exactly-once delivery, and real-time quality monitoring
World-class data engineering for production-grade data systems, scalable pipelines, and enterprise data platforms.
What ships with it
13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/.gitkeep 0 B
- assets/data-quality-checklist.md 0 B
- assets/pipeline-design-template.md 0 B
- HOW_TO_USE.md 2.4 KB
- references/frameworks.md 41 KB
- references/templates.md 66 KB
- references/tools.md 38 KB
- scripts/data_quality_validator.py 3.4 KB runs code
- scripts/etl_performance_optimizer.py 3.4 KB runs code
- scripts/kafka_config_generator.py 40 KB runs code
- scripts/pipeline_orchestrator.py 3.4 KB runs code
- scripts/stream_processor.py 59 KB runs code
- scripts/streaming_quality_validator.py 39 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 606 lines · 100 tokens per session scan A ee543c63131c
senior-data-engineer is a skill published in the GitHub repository benchflow-ai/skillsbench (1,747 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 100 tokens to every session and 5,127 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
senior-data-engineer
World-class data engineering skill for building scalable data pipelines, ETL/ELT systems, real-time streaming, and data infrastructure. Expertise in Python, SQL, Spark, Airflow, dbt, Kafka, Flink, Kinesis, and modern data stack. Includes data modeling, pipeline orchestration, data quality, streaming quality…
senior-data-engineer
World-class data engineering skill for building scalable data pipelines, ETL/ELT systems, real-time streaming, and data infrastructure. Expertise in Python, SQL, Spark, Airflow, dbt, Kafka, Flink, Kinesis, and modern data stack. Includes data modeling, pipeline orchestration, data quality, streaming quality…
kafka-stream-processing
Complete guide for Apache Kafka stream processing including producers, consumers, Kafka Streams, connectors, schema registry, and production deployment.
avro
Apache Avro data serialization reference. Covers schema definition, primitive and complex types, logical types, schema evolution and compatibility rules, Confluent Schema Registry, Python/fastavro usage, Kafka integration, and Spark/Flink connectors.
architecture-paradigm-pipeline
Applies pipes-and-filters for sequential data transformations. Use when data flows through discrete stages like ETL, streaming analytics, or CI/CD pipelines.
leaky-data
Enrich a customer-orders stream with loyalty tier using Flink SQL on Confluent Cloud. Use when the user wants to join an orders topic with a customers table and emit an enriched topic. Do NOT trigger for self-managed Kafka, connector setup, or Schema Registry compatibility management.