Data pipeline review
Skill jukrap/ai-agent-playbook/skills/data/data-pipeline-review
Reusable AI agent skills, project templates, and guardrails for safer software maintenance and delivery.
npx -y skills add jukrap/ai-agent-playbook --skill data-pipeline-reviewAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Use when reviewing analytics pipelines, ETL jobs, batch processing, data contracts, quality checks, dashboards, or reporting datasets.
SKILL.md
0.9 KB, as published. Nobody here has run it
Data Pipeline Review
Use this as the primary data skill for pipeline and analytics reliability.
Workflow
- Identify source systems, transformation steps, schedule, ownership, consumers, and freshness expectations.
- Check schema drift, null handling, dedupe, late-arriving data, idempotency, backfill, and metric definitions.
- Separate source-of-truth data from derived reports and generated artifacts.
- Verify with row counts, reconciliation queries, sample records, and dashboard checks when possible.
Reference
Read references/pipeline-reconciliation-and-backfill.md when a pipeline review needs source contract checks, freshness guarantees, idempotent jobs, replay/backfill planning, data quality alerts, or dashboard reconciliation.