What problem does it solve? Debugging failed Cloud Composer (Apache Airflow) DAGs requires manually digging through logs, locating the actual remote code, and correlating errors with source lines. This Skill automates that evidence-gathering process and produces a structured Root Cause Analysis (RCA) report. ## Core Features & Use Cases - Log-Based Evidence Gathering: Uses gcloud logging with severity, DAG ID, and environment filters to find failures and stack traces. - Remote Code Retrieval: Downloads the actual DAG code running in the Composer environment via gcloud storage, avoiding assumptions based on stale local copies. - RCA Report Generation: Correlates log errors with code lines, pinpoints the root cause, proposes a fix, and saves a formal RCA report. - Use Case: A user says "My DAG daily_sales_agg failed yesterday around 2pm." The Skill fetches the failed task logs, downloads the remote DAG, identifies a KeyError at a specific line, and produces an RCA report with a recommended fix. ## Quick Start Ask the assistant to troubleshoot a failed Composer DAG by providing the DAG ID, environment name, and approximate failure time, and request an RCA report.