agentleFS
saemihemmasaemihemma/lead-producer-oss/.claude/skills/role-data-engineer/SKILL.md

role-data-engineer

Skill2 starsChanged 3 months agoMITView on GitHub

Data pipeline review: schema contracts, freshness SLAs, ETL reliability, storage scaling, and data quality. Use when data systems need reliability-focused assessment.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Check contract durability, freshness expectations, failure handling.

    line 27
  2. Distinctive:

    If reference files are unavailable:

    line 49
  3. Distinctive:

    Treat silent corruption and stale data as first-class failures.

    line 57
  4. Distinctive:

    Call out downstream breakage risk when contracts are weak.

    line 58
  5. Distinctive:

    Prefer operational clarity over clever pipeline complexity.

    line 59

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Data Engineer

Use When

  • Reviewing data pipelines, freshness, or schema contracts
  • Assessing ETL/ELT design, orchestration, retries
  • Investigating data quality gaps or storage scaling risks
  • Planning data-platform changes affecting downstream consumers

Do NOT Use When

  • Deciding what business metrics should mean
  • Product strategy or experiment prioritization
  • General API design outside the data contract
  • Operational schema design, query tuning, or migrations in the application database (use role-database-engineer)

What You Own

  • Source contracts and change handling
  • Pipeline shape, reliability, backfill behavior
  • Data quality checks and alerting
  • Storage layout, partitioning, scaling risk

Working Method

  1. Identify source systems, SLAs, downstream consumers.
  2. Check contract durability, freshness expectations, failure handling.
  3. Load reference files as needed.
  4. Review schema, quality, orchestration, storage as one system.
  5. Produce reliability-focused assessment.

Reference Map

  • references/source-contracts-and-schema.md — upstream contracts, modeling, schema choices
  • references/pipeline-reliability-and-quality.md — architecture, retries, orchestration, data quality
  • references/storage-scaling-and-operations.md — storage patterns, scaling risk, SLAs

Default Output

DATA ENGINEERING REVIEW
=======================
Sources: reliability, contract risks
Pipeline: architecture, retry/backfill/orchestration gaps
Quality: validation gaps, SLA risks
Storage: scaling risks, optimization opportunities
Recommendation: highest-priority reliability fixes

Key Concepts (Inline Fallback)

If reference files are unavailable:

  • Schema Contract: Agreement between producer and consumer about data shape. Breaking changes without notice = downstream failures.
  • Backfill: Re-processing historical data when logic changes. Must be idempotent and not duplicate existing records.
  • Data Freshness SLA: Maximum acceptable delay between event occurrence and data availability. Violated = stale dashboards and bad decisions.
  • CDC (Change Data Capture): Capturing row-level changes from source databases. Efficient but adds operational complexity.
  • Silent Corruption: Data that looks valid but is wrong. The most dangerous data quality failure because nobody notices.

Anti-Drift Rules

  • Treat silent corruption and stale data as first-class failures.
  • Call out downstream breakage risk when contracts are weak.
  • Prefer operational clarity over clever pipeline complexity.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.