agentleFS
alifadl009alifadl009/microsoft-fabric-claude-skill/CLAUDE.md

microsoft-fabric-claude-skill

CLAUDE.md3 starsChanged 4 months agoMITView on GitHub

Update Check: At session start, check for skills-for-fabric updates by reading the remote package.json version from https://github.com/microsoft/skills-for-fabric (via git fetch origin main --quiet && git show origin/main:package.json or GitHub API with authentication) and comparing with the local package.json version. Show changelog if update available. This project uses Microsoft Fabric for data engineering, warehousing, and analytics. All Fabric operations require Azure AD authentication. For development: All Fabric operations use the REST APIs documented at: https://learn.microsoft.com/en-us/rest/api/fabric/articles/

The file

We split this CLAUDE.md into the rules it gives an agent

11 rules. About 0 are common, 9 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈9

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use the hybrid layering model: Agents → Skills → Common.

    line 9
  2. Distinctive:

    All Fabric operations require Azure AD authentication.

    line 15
  3. Distinctive:

    All Fabric operations use the REST APIs documented at: https://learn.microsoft.com/en-us/rest/api/fabric/articles/

    line 30
  4. Distinctive:

    Use REST APIs to create/manage artifacts (workspaces, warehouses, lakehouses)

    line 36
  5. Distinctive:

    Use protocol-specific connections to access data:

    line 37
  6. Distinctive:

    Use MCP servers for natural language queries

    line 44
  7. Distinctive:

    No ODBC/JDBC setup needed - MCP handles connections

    line 46
  8. Distinctive:

    Use Delta Lake format for Lakehouse tables

    line 139
  9. Very specific:

    Use has over contains for indexed string search in KQL

    line 141
  10. Very specific:

    Use idempotent KQL commands (.create-merge table, .create-or-alter function)

    line 142
  11. Distinctive:

    Use parameterized notebooks and pipelines

    line 144

≈ “Common” is an estimate: at least 1 in 5 of the 27,641 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
CLAUDE.md

Microsoft Fabric Development Instructions

Update Check: At session start, check for skills-for-fabric updates by reading the remote package.json version from https://github.com/microsoft/skills-for-fabric (via git fetch origin main --quiet && git show origin/main:package.json or GitHub API with authentication) and comparing with the local package.json version. Show changelog if update available.

This project uses Microsoft Fabric for data engineering, warehousing, and analytics.

Architecture Mode

  • Use the hybrid layering model: Agents → Skills → Common.
  • For cross-workload orchestration, start with agents/FabricDataEngineer.agent.md.
  • Delegate deep endpoint implementation to relevant skills under skills/.

Authentication

All Fabric operations require Azure AD authentication. For development:

# Login to Azure
az login

# Get token for Fabric REST API
az account get-access-token --resource https://api.fabric.microsoft.com

# Get token for SQL connections (Warehouse, Lakehouse SQL Endpoint)
az account get-access-token --resource https://database.windows.net

Fabric REST APIs

All Fabric operations use the REST APIs documented at: https://learn.microsoft.com/en-us/rest/api/fabric/articles/

Developer vs Consumer Patterns

Developers

  • Use REST APIs to create/manage artifacts (workspaces, warehouses, lakehouses)
  • Use protocol-specific connections to access data:
    • ODBC/JDBC for Warehouse queries
    • Spark/PySpark for Lakehouse data
    • XMLA/DAX for Semantic Models
    • KQL for Real-Time Intelligence

Consumers

  • Use MCP servers for natural language queries
  • Limited to: Semantic Models, Warehouses, Lakehouse SQL Endpoints
  • No ODBC/JDBC setup needed - MCP handles connections

Workloads

Data Engineering

Data Warehouse

  • Warehouse: T-SQL data warehouse
    • Docs: https://learn.microsoft.com/en-us/fabric/data-warehouse/data-warehousing
    • Note: Limited T-SQL surface area - check supported features
    • Authoring skill: skills/sqldw-authoring-cli/SKILL.md — DDL, DML, ingestion, schema changes
    • Consumption skill: skills/sqldw-consumption-cli/SKILL.md — read-only T-SQL queries
    • Operations skill: skills/sqldw-operations-cli/SKILL.md — performance diagnostics, slow queries, query insights

SQL Database (in Fabric)

  • SQL database: OLTP database with an enforced T-SQL surface, Query Store, and DMVs (distinct from the Warehouse)
    • Docs: https://learn.microsoft.com/en-us/fabric/database/sql/overview
    • Authoring skill: skills/sqldb-authoring-cli/SKILL.md — DDL/DML, constraints, indexes, source control, SqlPackage deploy, GraphQL
    • Consumption skill: skills/sqldb-consumption-cli/SKILL.md — read-only T-SQL exploration, vector similarity, JSON, temporal queries
    • Operations skill: skills/sqldb-operations-cli/SKILL.md — performance diagnostics via Query Store, DMVs, Extended Events

Data Integration

Real-Time Intelligence

  • Eventstreams: Real-time data ingestion
  • Activator: Alerts, notifications, and automated actions over Fabric data/events
  • Fabric IQ / Ontology (preview): Semantic model of entity types, properties, and relationships over Fabric data
    • Docs: https://learn.microsoft.com/en-us/rest/api/fabric/articles/
    • Authoring skill: skills/fabriciq-ontology-authoring-cli/SKILL.md — define entity types, properties (incl. timeseries), relationship types, and bind them to lakehouse/Eventhouse tables via the item-definition REST API
    • Consumption skill: skills/fabriciq-ontology-consumption-cli/SKILL.md — read ontology items for agent grounding context and route ontology-backed queries to the matching per-datasource consumption skill
    • Primary CLI tool: az rest via Fabric REST API
  • KQL Database / Eventhouse: Time-series queries with Kusto
    • Docs: https://learn.microsoft.com/en-us/fabric/real-time-intelligence/create-database
    • Authoring skill: skills/eventhouse-authoring-cli/SKILL.md — table management, ingestion, policies, materialized views
    • Consumption skill: skills/eventhouse-consumption-cli/SKILL.md — read-only KQL queries, schema discovery
    • Primary CLI tool: az rest via Kusto REST API (/v1/rest/query and /v1/rest/mgmt)
    • Token audience: https://kusto.kusto.windows.net/.default

OneLake Catalog Search

  • Catalog Search API: Cross-workspace item discovery

Business Intelligence

  • Semantic Models: DAX, XMLA, Power BI integration, TMDL
    • Docs: https://learn.microsoft.com/en-us/power-bi/connect-data/service-datasets-understand
    • Authoring skill: skills/semantic-model-authoring/SKILL.md — semantic model authoring
    • Consumption skill: skills/semantic-model-consumption/SKILL.md — raw DAX queries against semantic models via MCP ExecuteQuery tool
    • FabricIQ skill: skills/fabriciq/SKILL.md — multi-step Power BI data analysis (discover, inspect, resolve, generate, execute)
    • ⚠️ MANDATORY: Before calling any FabricIQ MCP tool, read skills/fabriciq/SKILL.md in full (see agents/FabricIQ.agent.md § Pre-Flight).
  • Power BI Reports: PBIR/PBIP report projects, visual design, Desktop validation, and Fabric report item management

Data Science

Best Practices

Must

  • Use Delta Lake format for Lakehouse tables
  • Include time filters in KQL queries (where Timestamp > ago(...))
  • Use has over contains for indexed string search in KQL
  • Use idempotent KQL commands (.create-merge table, .create-or-alter function)
  • Handle credentials via environment variables or Key Vault
  • Use parameterized notebooks and pipelines

Prefer

  • Medallion architecture (Bronze/Silver/Gold) for data organization
  • REST APIs for programmatic management
  • Incremental processing over full refreshes
  • mssparkutils for Fabric-specific notebook operations

Avoid

  • Hardcoded workspace/item IDs
  • SELECT * without LIMIT on large tables
  • Long-running transactions in Warehouse
  • Unbounded streaming queries

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.