What problem does it solve? Refreshing Power BI semantic models reliably requires coordinating the Enhanced Refresh REST API, validating that data actually changed, and diagnosing failures like credential errors, schema mismatches, and timeouts. This Skill automates that entire workflow so refreshes are triggered, monitored, and verified without manual portal work. ## Core Features & Use Cases - Full Refresh Lifecycle: Resolve workspace and model IDs, capture a pre-refresh DAX baseline, trigger refreshes (full, automatic, dataOnly, calculate, clearValues, defragment), monitor status, and validate post-refresh data changes. - Targeted and Large-Model Refreshes: Refresh specific tables or partitions, run two-phase dataOnly + calculate patterns, control commit modes, parallelism, retries, and incremental refresh policy behavior. - Troubleshooting Guidance: Diagnose credential errors, gateway-free Fabric source refresh via workspace identity and shareable cloud connections, type mismatches, timeouts, throttling, and incremental refresh issues. - Use Case: After an ETL pipeline loads new data into a Fabric lakehouse, trigger a partition-level refresh of FactSales, poll until completion, and confirm via DAX that row counts and max dates increased. ## Quick Start Ask the agent to refresh the semantic model in a given Power BI workspace and verify that new data arrived.