agentleFS
PatrickGallucciPatrickGallucci/fabric-skills/skills/fabric-data-agent/SKILL.md

fabric-data-agent

Skill17 starsChanged 9 months agoMITView on GitHub

Create, configure, and manage Microsoft Fabric Data Agents that enable natural language Q&A over lakehouses, warehouses, Power BI semantic models, KQL databases, and ontologies. Use when asked to build data agents, configure NL2SQL/NL2DAX/NL2KQL experiences, write agent instructions, create example queries, automate data agent provisioning via REST API or PowerShell, integrate Fabric data agents with Azure AI Foundry, or troubleshoot data agent configuration issues.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

12 rules. About 0 are common, 12 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈12

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Add up to 5 data sources from the OneLake catalog (any mix of Lakehouse, Warehouse, PBI Semantic Model, KQL DB, Ontology)

    line 39
  2. Distinctive:

    Write agent instructions — see instruction-best-practices.md

    line 41
  3. Distinctive:

    Add example queries for each data source — see example-query-guide.md

    line 42
  4. Distinctive:

    Test the agent in the chat pane with representative questions

    line 43
  5. Distinctive:

    Create the agent item using the Fabric Items API — run New-FabricDataAgent.ps1

    line 50
  6. Distinctive:

    Update the item definition using the Update Item Definition API

    line 52
  7. Distinctive:

    Create and publish the Fabric Data Agent in the Fabric portal

    line 57
  8. Distinctive:

    Create a Foundry Agent in the Azure AI Foundry portal

    line 58
  9. Distinctive:

    Add a Microsoft Fabric connection to your Foundry project

    line 59
  10. Distinctive:

    Create the agent with the Fabric tool enabled — see foundry-integration.md

    line 60
  11. Distinctive:

    Create a thread, add a user question, run the thread, and retrieve the response

    line 61
  12. Distinctive:

    Update Foundry agent instructions to describe what data the Fabric tool can access

    line 62

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill 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
SKILL.md

Microsoft Fabric Data Agents

Build conversational AI experiences that let users ask questions in plain English against structured data in Microsoft Fabric. Fabric Data Agents translate natural language into SQL, DAX, or KQL queries, execute them securely under the caller's identity, and return data-driven answers.

When to Use This Skill

  • Creating a new Fabric Data Agent from the portal or via REST API
  • Configuring data sources (Lakehouse, Warehouse, Power BI Semantic Model, KQL Database, Ontology)
  • Writing effective agent-level or data-source-level instructions
  • Authoring example queries (few-shot examples) to improve NL2SQL/NL2DAX/NL2KQL accuracy
  • Automating data agent provisioning with PowerShell and the Fabric REST API
  • Integrating a published Fabric Data Agent with Azure AI Foundry agents
  • Managing the Operations Agent definition (Configurations.json) programmatically
  • Publishing, sharing, and versioning data agents
  • remediate query generation, data source permissions, or tenant settings

Prerequisites

RequirementDetails
Fabric capacityPaid F2+ SKU, or Power BI Premium P1+ with Fabric enabled
Tenant settingsFabric data agent, Cross-geo processing for AI, Cross-geo storing for AI all enabled
XMLA endpointsEnabled if using Power BI Semantic Model data sources
Data source accessAt least Read permission on target lakehouses, warehouses, semantic models, or KQL databases
PowerShell (automation)PowerShell 7.4+, Az.Accounts module
Azure AI Foundry (integration)Foundry Project endpoint, Fabric connection, model deployment

Step-by-Step Workflows

Workflow 1: Create and Configure a Data Agent (Portal)

  1. Navigate to your workspace and select + New Item > Fabric data agent
  2. Provide a descriptive name for the agent
  3. Add up to 5 data sources from the OneLake catalog (any mix of Lakehouse, Warehouse, PBI Semantic Model, KQL DB, Ontology)
  4. Select/deselect tables in the Explorer pane to control what the AI can query
  5. Write agent instructions — see instruction-best-practices.md
  6. Add example queries for each data source — see example-query-guide.md
  7. Test the agent in the chat pane with representative questions
  8. Select Publish and provide a description
  9. Share the published version with colleagues via workspace permissions

Workflow 2: Automate Data Agent via REST API (PowerShell)

  1. Authenticate with Connect-AzAccount and obtain an access token
  2. Create the agent item using the Fabric Items API — run New-FabricDataAgent.ps1
  3. Configure the Operations Agent definition (Configurations.json) — see operations-agent-schema.md
  4. Update the item definition using the Update Item Definition API
  5. Validate deployment by listing items in the workspace

Workflow 3: Integrate with Azure AI Foundry

  1. Create and publish the Fabric Data Agent in the Fabric portal
  2. Create a Foundry Agent in the Azure AI Foundry portal
  3. Add a Microsoft Fabric connection to your Foundry project
  4. Create the agent with the Fabric tool enabled — see foundry-integration.md
  5. Create a thread, add a user question, run the thread, and retrieve the response
  6. Update Foundry agent instructions to describe what data the Fabric tool can access

remediate

SymptomCauseResolution
Data agent option not visible in New ItemTenant setting disabledAdmin enables "Fabric data agent" in Tenant Settings
Agent can't see my tablesTables not selected in ExplorerCheck table checkboxes in the data source Explorer
Queries return permission errorsInsufficient data accessGrant at least Read on the underlying data source
Example queries show validation errorsSQL/KQL syntax invalid or schema mismatchValidate queries against the actual table schema
Agent misinterprets domain termsMissing definitions in instructionsAdd term definitions in Agent Instructions (up to 15,000 chars)
Power BI semantic model won't addXMLA endpoints disabledEnable "Power BI semantic models via XMLA endpoints" tenant switch
Published agent not accessible to colleaguesWorkspace permissions not grantedShare the workspace or agent item with appropriate roles

References

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.