scardoso-lu

Develop Fabric notebooks using a local closed-loop cycle — author in .py locally, build to .Notebook format, deploy via REST API, execute, monitor, diagnose errors, fix, and redeploy. Use for iterative notebook development without portal interaction. Typically converges in 1–3 iterations. Cold-start time varies by capacity tier (≈3 min on F64, up to 8–12 min on F2/F4).

Operate and maintain a Fabric data platform — orchestrate pipeline DAGs, run VACUUM, update platform inventory, manage workspace items, and execute operational routines. Use for day-to-day platform operations, maintenance windows, GDPR purges, or environment setup.

Create, deploy, and test a Fabric Data Factory pipeline that chains all topic notebooks in order (download → bronze → dq_bronze → silver → dq_silver → gold → dq_gold). Use after all notebooks for a topic have been individually deployed and smoke-tested.

Prefix shell commands with rtk to apply the token-optimizing proxy (60–90% savings on Git, pytest, ruff, Fabric CLI, file ops).

Generate deterministic synthetic CSV files under data/sandbox/ using the data_mock_generate MCP tool. Use when no real source file exists for a new or demo topic and you need staged data to build the download/bronze/dq notebook pipeline against.

List, read, and interpret Microsoft Fabric Semantic Models (Power BI datasets). Use when an agent needs to understand available business metrics, DAX measures, table relationships, or column definitions before writing DAX queries, building reports, or validating Gold-layer outputs against business definitions.

Ingest local staged files (CSV, Parquet, JSON, Excel) into a Microsoft Fabric Lakehouse as Bronze Delta tables. Use when loading data from the target repo's data/sandbox/ into the Bronze layer. Handles sanitization, lineage envelope injection, and idempotent partition overwrite.

Build Gold layer analytical objects — dimensional models (Kimball star schema), KPI aggregates, wide tables, or TMDL semantic models. Use when creating fact tables, dimension tables, monthly aggregates, or Power BI semantic models from Silver data. Enforces referential integrity, metric standardization, and schema locking.

Prefer the simplest solution that satisfies the current epic; never add complexity for hypothetical future needs

Ensures the agent only references data assets that verifiably exist in Microsoft Purview's Data Map. Use before generating any diagram node that represents a catalogued asset (Lakehouse, Pipeline, Notebook, Warehouse, Table).

Governs how the agent chooses between single-workspace and cross-workspace design modes. Use when deciding which Purview collections to query for a given epic, and when placing nodes from different workspaces into the same diagram.

Governs how Azure DevOps epics are interpreted and translated into medallion architecture diagrams. Use when reading epic details and deciding which data sources, transformations, and serving outputs belong in the diagram.

Enforces formatting, layout, and label rules for all generated .drawio files. Use whenever calling generate_diagram or reviewing diagram output to ensure files open and render correctly in draw.io Desktop and diagrams.net.

Enforces Bronze/Silver/Gold layer discipline when designing Microsoft Fabric data architectures. Use when generating or reviewing any medallion architecture diagram for a Fabric workspace.

Automate browser interactions, test web pages and work with Playwright tests.