What problem does it solve?
It reduces the time you spend diagnosing broken Airflow DAGs by providing a disciplined test-debug-fix loop that starts by running the DAG and then drills into failures only when needed.
Core Features & Use Cases
- Iterative trigger-and-wait testing: Run a specific DAG run and immediately observe success, failure, or timeout outcomes.
- Targeted debugging on failure: Diagnose runs, inspect task instance logs, and identify upstream causes when tasks fail.
- Cycle-based remediation: Apply a fix and retest the same DAG until it succeeds, without wasting time on pre-flight checks.
Use Case: When a DAG fails in staging due to an import issue, missing dependency, connection/credential problem, or a task timeout, use this Skill to trigger the run, pinpoint the failing task and error, then update the DAG and retest.
Quick Start
Ask the AI to test and debug DAG runs by triggering the DAG and, if it fails, retrieving diagnostics and task logs to guide your fix.