Data Engineer
Skills of a data engineer for building reliable pipelines (ETL/ELT) between the operational database, an analytical warehouse and reporting tools. Trigger this skill for ingestion, transformation, data quality or pipeline architecture tasks — distinct from the Data Analyst, who works on data that's already ready to query.
Install
$ agentstack add skill-benbasse-claude-skills-digital-solutions-data-engineer ✓ 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-benbasse-claude-skills-digital-solutions-data-engineer) 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
Data Engineer
The Data Engineer builds and hardens data flows between operational systems (orders, transactions, users) and analytics tooling, guaranteeing quality, freshness and traceability.
When to trigger this skill
- Setting up an ETL/ELT pipeline (operational DB -> warehouse)
- Cleaning or deduplicating data at scale
- Designing a star schema for reporting
- Data quality or freshness problems
- Orchestrating scheduled jobs (daily aggregates, exports)
Skills, responsibilities and best practices
- Idempotent, replayable pipelines
- Dimensional modeling (facts/dimensions) for reporting
- Data quality tests (nulls, duplicates, referential integrity)
- Orchestration via scheduled jobs or a dedicated tool (Airflow, Dagster) once volume justifies it
- Schema evolution handled without breaking existing pipelines
- Documented metric definitions (e.g. what exactly counts as a 'completed order'?)
Common pitfalls to avoid
- Building a pipeline with no data quality tests, propagating bad data downstream
- Not handling retries after failure (non-idempotent pipeline)
- Over-engineering with heavy tooling before the data volume justifies it
- Multiple teams defining the same metric differently (numbers stop matching)
Reference stack and tools
- Your operational database as the source, materialized views for aggregates
- A lightweight BI/warehouse tool matched to your actual volume (Metabase, dbt, or a full warehouse if justified)
- Scheduled jobs or an orchestrator for pipeline execution
Typical deliverables
- Documented and tested pipelines
- Warehouse schema (facts/dimensions)
- Metrics dictionary
Example prompts that should trigger this skill
- 'Build a pipeline that aggregates daily transactions by region every night'
- 'The dashboard numbers don't match the database, help me investigate'
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: benbasse
- Source: benbasse/claude-skills-digital-solutions
- 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.