AnalyticsPlatformAgents

Verify a skill PR locally before submitting. Walks workload-team contributors through the three local checks that mirror what CI runs on every PR: quality_checker structural lint, Vally eval for changed skills, and filtered full-eval for changed skills. Vally is the primary harness; legacy smoke is break-glass only. Use before opening or pushing to a PR that touches `skills/`, `common/`, `agents/`, or `tests/`. Triggers: "pre-PR check", "verify my PR locally", "run vally locally", "run full eval locally", "validate my skill before submit", "check my changes before push", "what should I run before opening a PR".

Self-review your skill PR before requesting human / bot review. Runs three independent parallel reviews across different models, cross-verifies findings against Microsoft Learn, removes false positives, and presents consolidated findings for you to fix BEFORE you push the next commit. Adapted from the deep-review pattern used by maintainers. Use when your skill PR is functionally complete and you want a high-confidence pass catching the issues bot and reviewers usually flag. Triggers: "review my PR", "self-review", "pre-review", "deep review my PR", "review before submitting", "what will reviewers flag".

Run local quality checks on skills-for-fabric before committing. Validates all skills in the skills/ folder for structural compliance, semantic disambiguation, broken references, and content quality. Use before submitting a PR to catch issues early. Triggers: "check my skills", "run quality check", "validate skills", "pre-commit check", "lint skills".

End-to-end public-release workflow for skills-for-fabric: stamp version, open the microsoft/skills-for-fabric PR, run the release-artifact smoke (structural + install + behavioral Copilot probes), then tag and publish. Captures the exact verification harness used for 0.3.2. Use when the user wants to: (1) cut a new public release, (2) smoke-test a release branch before merging the public PR, (3) verify a release artifact behaves correctly in a clean Copilot CLI install. Triggers: "cut a release", "public release", "release smoke", "verify release", "stamp version", "publish to public", "0.x.y release", "release workflow", "release runbook".

Generate a Fabric Skills weekly status PowerPoint deck from ADO work items, git history, and open PRs in the gim-home/skills-for-fabric and microsoft/skills-for-fabric repos, then upload it to the team's SharePoint folder. Use this skill whenever the user asks for a "weekly summary", "status slides", "status deck", "weekly pptx", "weekly report pptx", or mentions creating presentation slides for Fabric Skills status. Also trigger when the user says "generate slides", "status PowerPoint", or "upload status to SharePoint".

Create alerts, notifications, and automated actions on Fabric data and events via Fabric REST API and `az rest` CLI. **Invoke this skill** whenever the user wants to: (1) create, update, or delete an alert or notification flow, (2) send a Teams message, email, or run a Fabric item when something happens, (3) connect alert logic to Eventhouse, Eventstream, Real-time Hub, or DTB / Ontology data, (4) adjust thresholds, filters, event triggers, or actions, (5) troubleshoot or change an existing Activator/Reflex definition. Invoke this skill **before** asking clarifying questions — clarification is part of this skill, not a preamble to it. Triggers: "create an alert", "create an activator", "create a reflex", "create an activator item", "create an alert item", "notify me when", "let me know when", "take action when", "send me an email when", "send a teams message when", "run a pipeline when", "update an alert", "delete an alert", "activator rule"

Inspect existing alerts, notifications, and automated actions in Fabric via read-only REST API calls using `az rest` CLI. **Invoke this skill** whenever the user wants to: (1) list existing alerts in a workspace, (2) inspect how an alert or notification is configured, (3) read and decode an Activator/Reflex definition (ReflexEntities.json), (4) list rules, sources, and actions behind an alert, (5) understand why an alert fires or what action it takes. **Invoke this skill before answering questions** about an Activator/Reflex item in a Fabric workspace — the listing, lookup, and decoding workflows are part of this skill, not preamble to it. Triggers: "show my alerts", "what alerts do I have", "inspect this alert", "show me the rule", "show me the action", "show me the source", "get reflex definition", "list activators", "list alerts", "list reflex items", "show activator items", "activator details", "find activator named"

Check for skills-for-fabric marketplace updates at session start. Compares local version against GitHub releases and shows changelog if updates are available. Use when the user wants to: (1) check for skill updates, (2) see what's new in skills-for-fabric, (3) verify current version. Triggers: "check for updates", "am I up to date", "what version", "update skills", "show changelog".

Port Databricks notebooks and jobs to Microsoft Fabric. Provides an exhaustive dbutils to notebookutils substitution table: fs operations (mount removal via OneLake Shortcuts), secret scope to Key Vault URL conversion, notebook run and exit, widget replacement with parameter-tagged cells, and library install replacement with Fabric Environments. Covers Unity Catalog three-level namespace reduction to Lakehouse two-level schemas, DBFS path conversion to OneLake, Databricks Jobs to Spark Job Definitions, MLflow tracking URI removal, and Photon to Native Execution Engine substitution. Use when the user wants to: (1) replace dbutils with notebookutils, (2) collapse Unity Catalog namespaces to Lakehouse schemas, (3) convert Databricks Jobs or Delta Live Tables. Triggers: "migrate from databricks", "databricks to fabric", "dbutils to notebookutils", "dbutils fabric", "unity catalog migration", "dbfs to onelake", "databricks notebook migration", "delta live tables fabric", "photon native execution".

Create, update, delete, and refresh Fabric Dataflows Gen2 via write-side CLI against Fabric Items and Connections APIs. Builds mashup.pq + queryMetadata definitions, triggers parameterized refreshes, manages connections, and configures output destinations (Lakehouse, Warehouse, ADX, Azure SQL). Includes preview-driven authoring loop (executeQuery + customMashupDocument). Lists `supportedConnectionTypes`/`credentialType` per connector. For executing saved queries or reading refresh status, use `dataflows-consumption-cli`. Triggers: "create dataflow", "update dataflow", "delete dataflow", "trigger dataflow refresh", "refresh dataflow", "preview Power Query M", "preview mashup", "preview before save", "iterate dataflow M", "create Fabric data source connection", "create dataflow connection", "bind connection", "list supportedConnectionTypes", "dataflow output destination", "dataflow write to lakehouse", "dataflow write to warehouse", "dataflow write to ADX", "DataDestinations annotation".

Monitor, inspect, and query saved Fabric Dataflows Gen2 via read-only CLI. List dataflows, decode base64 definitions (mashup.pq, queryMetadata.json, .platform), discover parameters, retrieve refresh status and job history, classify queries by staging, and execute queries against saved dataflows via the read-side `executeQuery` mashup engine (Arrow IPC response). Runs persisted or ad-hoc read-only executeQuery requests; parses/renders Arrow results. For previewing candidate M before persisting, or for `supportedConnectionTypes`/`credentialType` discovery and connection configuration, use `dataflows-authoring-cli` (not this skill). Triggers: "list dataflows", "inspect dataflow", "decode dataflow definition", "dataflow parameters", "dataflow refresh status", "refresh history", "last refresh status", "dataflow job history", "execute dataflow query", "executeQuery saved query", "executeQuery fetch rows", "ad-hoc dataflow query", "parse Arrow response", "Arrow IPC", "dataflow staging analysis".

Assess, plan, and execute dataflow Gen1 → Gen2.1 CI/CD save-as operations via CLI (az rest / curl) against Power BI REST and Fabric REST APIs. Scan workspaces or entire tenants for Gen1 dataflows, evaluate save-as readiness with seven risk signals (incremental refresh, BYOSA storage, Power Automate triggers, pipeline dependencies, linked entities, DirectQuery, caller-not-owner), produce a Save-As Readiness Snapshot (markdown + JSON), and invoke the SaveAsNativeArtifact API to create upgraded Gen2.1 copies of Gen1 dataflows. **Invoke this skill** whenever the user wants to: (1) discover Gen1 dataflows in a workspace or tenant, (2) assess save-as readiness and risk signals, (3) upgrade or migrate Gen1 into a Gen2.1 copy, (4) validate post-save-as data integrity, (5) detect residual Gen1 references. Triggers: "save Gen1 dataflow", "convert dataflow Gen1", "upgrade dataflow", "migrate dataflow", "dataflow readiness", "Gen1 to Gen2", "dataflow save-as assessment", "saveAsNativeArtifact", "dataflow save-as scan".

Implement end-to-end Medallion Architecture (Bronze/Silver/Gold) lakehouse patterns in Microsoft Fabric using PySpark, Delta Lake, and Fabric Pipelines. Use when the user wants to: (1) design a Bronze/Silver/Gold data lakehouse, (2) set up multi-layer workspace with lakehouses for each tier, (3) build ingestion-to-analytics pipelines with data quality enforcement, (4) optimize Spark configurations per medallion layer, (5) orchestrate Bronze-to-Silver-to-Gold flows via notebooks. Triggers: "medallion architecture", "bronze silver gold", "lakehouse layers", "e2e data pipeline", "end-to-end lakehouse", "data lakehouse pattern", "multi-layer lakehouse", "build medallion", "setup medallion".

Create, wire, and publish Microsoft Fabric Eventstream real-time event streaming topologies via the Fabric Items REST API. Build graph-based definitions with 25 source types (Event Hubs, IoT Hub, CDC connectors, Kafka, SampleData), 8 transformation operators (Filter, Aggregate, GroupBy, Join, ManageFields, Union, Expand, SQL), 4 destination types (Lakehouse Delta, Eventhouse, Activator, Custom Endpoint), and DefaultStream/DerivedStream routing. Use when the user wants to: (1) author or publish an Eventstream topology, (2) add CDC sources with SQL-based Debezium payload flattening, (3) assemble multi-table fan-out routing, (4) modify or delete Eventstream definitions. Triggers: "create eventstream", "deploy eventstream", "design eventstream topology", "CDC source", "eventstream operator", "real-time ingestion pipeline", "eventstream definition", "update eventstream".

List, inspect, and monitor Microsoft Fabric Eventstream real-time event ingestion pipelines via the Fabric Items REST API. Discover Eventstreams across workspaces, decode base64-encoded graph topologies to trace event flow from source through operators to destination nodes. Validate source connection IDs, destination wiring, retention policies (1-90 days), and throughput levels. Use when the user wants to: (1) list or search Eventstreams in a workspace, (2) decode and trace graph topology from source to destination, (3) validate source and destination configurations, (4) check retention and throughput settings. Triggers: "list eventstreams", "show eventstream", "inspect eventstream", "explain eventstream", "eventstream health", "monitor eventstream", "describe eventstream", "check eventstream configuration", "eventstream retention".

Answer business questions by querying Power BI reports and dashboards through the FabricIQ MCP endpoint. Orchestrates: discover Power BI artifacts, inspect report/model schemas, resolve entity values, generate DAX, execute queries. Returns plain-language answers from Power BI semantic models. Use when the user asks a natural-language question about Power BI report or dashboard content (not raw DAX). Triggers: "ask power bi", "PBI question", "discover report", "report data", "dashboard data", "what are the top", "show me the power bi data", "which products sold", "compare sales in report".

Create and modify Power BI report files in PBIR/PBIP format using the `powerbi-report-author` and `powerbi-desktop` CLIs. Use when the user wants to: (1) implement an approved report spec or design brief, (2) add or edit pages, visuals, filters, slicers, bookmarks, themes, or formatting, (3) validate PBIR and verify rendering in Power BI Desktop. For open-ended visual design, use `powerbi-report-design` first. For end-to-end requirements and approval workflow, use `powerbi-report-planning` first. Triggers: "edit PBIR", "create Power BI report page", "add visual to PBIP", "format report visual", "validate Power BI report", "reload Desktop screenshot", "implement an approved PBIP report spec", "edit PBIR pages/visuals".

Generate Power BI report visual design guidance before PBIR files are written. Use when the user wants to: (1) choose tone, signature, page archetypes, chart types, layout, color, typography, theme direction, or accessibility approach, (2) redesign/restyle an existing report, apply a brand, or critique chart/layout choices, (3) produce a design contract for `powerbi-report-authoring`. For end-to-end requirements, approval, and build sequencing, use `powerbi-report-planning`. Triggers: "design Power BI report", "make dashboard look professional", "choose chart type", "apply brand to report", "redesign report", "create design brief".

Manage Power BI report workspace items in Microsoft Fabric via `az rest` CLI against the Fabric REST API. Use when the user wants to: (1) create reports from PBIR definitions, (2) get or download report definitions, (3) update report definitions or properties, (4) list workspace reports, (5) delete reports. For report layout authoring (pages, visuals, filters, formatting), use `powerbi-report-authoring`. Triggers: upload Power BI report, download PBIR definition, publish Power BI report to Fabric, manage Power BI reports.

Find and discover Microsoft Fabric items across workspaces when the workspace is unknown. Use when the user wants to: (1) find an item by name across workspaces, (2) list items of specific type across workspaces, (3) identify which workspace contains an item, (4) return item/workspace IDs for downstream API calls. Triggers: "which workspace has", "where is", "what items do I have", "do I have", "find item", "find all items", "search for item", "discover items", "find across workspaces".

Develops and manages Power BI semantic models across Desktop, PBIP projects, and Fabric Service. Handles: (1) creating new models (Import, DirectQuery, Direct Lake), (2) editing existing models (e.g. measures, tables, columns, relationships), (3) deploying models to Fabric workspaces, (4) working with PBIP project files, (5) refreshing semantic models, (6) configuring data sources and permissions, (7) DAX performance optimization. Supports both Power BI Desktop and Fabric Service development workflows. For read-only DAX queries, use `semantic-model-consumption`. Does NOT handle report layout/visual authoring, workspace administration, or RLS/OLS role membership management. Triggers: "create semantic model", "edit semantic model", "add a DAX measure to semantic model", "refresh semantic model", "set semantic model permissions", "Prepare semantic model for AI/Copilot".

Develop Microsoft Fabric Spark/data engineering workflows and write code in Fabric Notebook cells with intelligent routing to specialized resources. Provides workspace/lakehouse management, notebook code authoring (PySpark, Scala, SparkR, SQL), and Materialized Lake View (MLV) authoring (Spark SQL MLVs support incremental refresh; PySpark is full-refresh only). Routes to data engineering patterns, development workflow, or infrastructure orchestration. Triggers: "develop notebook", "data engineering", "workspace setup", "pipeline design", "Delta Lake patterns", "Spark development", "lakehouse configuration", "write notebook code", "notebookutils", "notebook cell", "PySpark notebook", "%%sql cell", "%%configure", "fabric notebook", "run notebook", "notebook deployment", "materialized lake view", "MLV", "CREATE MATERIALIZED LAKE VIEW", "MLV incremental refresh", "review MLV for incremental refresh", "MLV refresh policy", "schedule MLV refresh", "infrastructure provisioning"

Analyze lakehouse data interactively using Fabric Lakehouse Livy API sessions and PySpark/Spark SQL for advanced analytics, DataFrames, cross-lakehouse joins, Delta time-travel, and unstructured/JSON data. Use when the user explicitly asks for PySpark, Spark DataFrames, Livy sessions, or Python-based analysis — NOT for simple SQL queries. Triggers: "PySpark", "Spark SQL", "analyze with PySpark", "Spark DataFrame", "Livy session", "lakehouse with Python", "PySpark analysis", "PySpark data quality", "Delta time-travel with Spark".

Diagnose failed Spark jobs, unhealthy Livy sessions, and performance bottlenecks in Microsoft Fabric via read-only CLI triage. Use when the user wants to: (1) diagnose why a Spark job, notebook run, or Lakehouse job failed, (2) triage stuck or dead Livy sessions, (3) identify OOM, shuffle spill, or data skew, (4) retrieve driver and executor logs or Spark Advisor findings, (5) copy event logs and start a local Spark History Server, (6) diagnose all Spark activities within a failed pipeline run. Triggers: "diagnose my failed notebook", "why did my spark job fail", "triage spark failure", "diagnose pipeline run failure", "why did my pipeline fail", "livy session stuck in starting", "spark executor OOM", "check spark advisor findings", "shuffle spill diagnosis", "why did my lakehouse job fail", "diagnose lakehouse table load", "data skew diagnosis", "open spark history server locally", "analyze spark failure logs", "spark job triage".

Create, manage, and deploy Power BI semantic models inside Microsoft Fabric workspaces via `az rest` CLI against Fabric and Power BI REST APIs. Use when the user wants to: (1) create a semantic model from TMDL definition files, (2) retrieve or download semantic model definitions, (3) update a semantic model definition with modified TMDL, (4) trigger or manage dataset refresh operations, (5) configure data sources, parameters, or permissions, (6) deploy semantic models between pipeline stages. Covers Fabric Items API (CRUD) and Power BI Datasets API (refresh, data sources, permissions). For read-only DAX queries, use `powerbi-consumption-cli`. For fine-grained modeling changes, route to `powerbi-modeling-mcp`. Triggers: "create semantic model", "upload TMDL", "download semantic model TMDL", "refresh dataset", "semantic model deployment pipeline", "dataset permissions", "list dataset users", "semantic model authoring".

Author Fabric Paginated Reports (.rdl) from scratch, connecting to semantic models via PBIDATASET. Covers RDL XML structure, namespace requirements, data source configuration, DAX dataset queries, Tablix layout, conditional formatting, page setup, and known schema validation pitfalls. Use when the user wants to: (1) create a new paginated report from scratch, (2) add datasets or tables to an existing .rdl, (3) connect an .rdl to a Fabric semantic model, (4) fix RDL validation or schema errors, (5) design report layout with headers, sections, and page footers. Triggers: "create paginated report", "new rdl", "author rdl", "build paginated", "add tablix", "add dataset", "rdl from scratch", "rdl layout", "paginated report design", "fix rdl error", "rdl schema error", "connect rdl to semantic model".

Export, modify, and re-import Fabric Paginated Reports (.rdl) via REST APIs. Covers data source rebinding, renaming, folder placement, and known platform limitations. Use when the user wants to: (1) export a paginated report .rdl from Fabric, (2) change the data source / semantic model of a paginated report, (3) import a modified .rdl back into a Fabric workspace, (4) move paginated reports between workspace folders. Triggers: "paginated report", "rdl file", "change data source", "rebind paginated", "export report", "import rdl", "move report to folder".

Guide to develop Power BI Reports using IBCS (International Business Communication Standards) and ZebraBI visuals for professional financial dashboards. Use this skill for creating Hichert diagrams, variance charts, IBCS-compliant tables, and KPI cards in PBIR format. Covers ZebraBI Cards, ZebraBI Charts (waterfall/variance), and ZebraBI Tables for financial and business reporting.

The ONLY supported path for read-only Microsoft Fabric Power BI semantic model (formerly "Power BI dataset") query interactions. Execute DAX queries via the MCP server ExecuteQuery tool to: (1) discover semantic model metadata (tables, columns, measures, relationships, hierarchies, etc.) and their properties, (2) retrieve data from a semantic model. Triggers: "DAX query", "semantic model metadata", "list semantic model tables", "run EVALUATE", "get measure expression".

Execute read-only T-SQL queries against Fabric Data Warehouse, Lakehouse SQL Endpoints, and Mirrored Databases via CLI. Default skill for any lakehouse data query (row counts, SELECT, filtering, aggregation) unless the user explicitly requests PySpark or Spark DataFrames. Use when the user wants to: (1) query warehouse/lakehouse data, (2) count rows or explore lakehouse tables, (3) discover schemas/columns, (4) generate T-SQL scripts, (5) monitor SQL performance, (6) export results to CSV/JSON. Triggers: "warehouse", "SQL query", "T-SQL", "query warehouse", "show warehouse tables", "show lakehouse tables", "query lakehouse", "lakehouse table", "how many rows", "count rows", "SQL endpoint", "describe warehouse schema", "generate T-SQL script", "warehouse performance", "export SQL data", "connect to warehouse", "lakehouse data", "explore lakehouse".