From data-engineering
Inspects dbt changes before PR/review/merge to assess blast radius, test coverage, and missing checks.
How this skill is triggered — by the user, by Claude, or both
Slash command
/data-engineering:dbt-preflightThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Inspect a dbt change set before it ships: identify which assets changed, estimate downstream impact, detect likely gaps in testing, contracts, documentation, and YAML alignment, and recommend the narrowest safe validation path. Preflight is read-only — do not edit code unless explicitly asked.
Inspect a dbt change set before it ships: identify which assets changed, estimate downstream impact, detect likely gaps in testing, contracts, documentation, and YAML alignment, and recommend the narrowest safe validation path. Preflight is read-only — do not edit code unless explicitly asked.
Enumerate changed assets:
git diff --name-status origin/main...HEAD
Classify each change: models, snapshots, seeds, macros, tests, schema YAML, semantic models, metrics, saved queries, exposures or BI-facing assets.
Estimate blast radius. For each changed model, list downstream dependents:
dbt ls --select <model>+
If a production manifest is available, cover the whole change set at once:
dbt ls --select state:modified+ --state <path-to-prod-artifacts>
Run the review checklist. Check for:
Recommend the narrowest meaningful validation path first:
dbt build --select <changed_model>dbt build --select <changed_model>+1dbt build --select state:modified+ --state <path>If exact commands are available in the repo (Makefile, CI config, docs), prefer them. If not, say what should be validated conceptually.
dbt ls), not guessednpx claudepluginhub yeaight7/agent-powerups --plugin data-engineeringCreates, edits, and verifies skills using a test-driven development approach with pressure scenarios and subagents.