- 01
/plugin marketplace add microsoft/skills-for-fabric - 02
/plugin install fabric-skills@fabric-collection
Microsoft's skill for Fabric IQ ontologies: the map of your business's things, such as customers and orders, how they relate, and which tables in your Microsoft Fabric data hold them. Your assistant can build or change an ontology, showing you each change and waiting for your yes before saving it, or explore an existing one without changing anything.
WHEN TO USE
USE FOR
- Create an ontology with types such as Customer and Order, linked to lakehouse tables.
- Add a relationship or a data link to an ontology you already have.
- List an ontology's types and the tables they come from.
- Trace a question through the ontology to the data that answers it.
NOT FOR
- Plain-language questions about a Power BI report: Microsoft's fabriciq skill handles those.
This is a saved copy of the skill's SKILL.md instructions. It may differ from the upstream file or the version you install.
Telemetry — MANDATORY. Every
api.fabric.microsoft.comcall must carryx-ms-fabric-skill: fabriciq-ontology-cli(az rest:--headers "x-ms-fabric-skill=fabriciq-ontology-cli"), including every LRO poll,fabric_lroand retry. Snippets omit it — add it anyway.
CRITICAL NOTES
- To find the workspace details (including its ID) from workspace name: list all workspaces and, then, use JMESPath filtering
- To find the item details (including its ID) from workspace ID, item type, and item name: list all items of that type in that workspace and, then, use JMESPath filtering
- Skill disambiguation: use
fabriciq-ontology-clifor the Ontology item itself. Natural-language questions over Power BI reports and dashboards arefabriciq; DAX against a semantic model issemantic-model-cli.
Fabric IQ Ontology -- CLI Skill
This one skill owns Fabric IQ Ontology items: entity and relationship types, bindings, definitions, lineage, grounding and graph walks.
It is a mode dispatcher and contains NO procedures. Pick the mode that matches the request from the table below, then read the matching references/<mode>.md file end to end with your file-reading tool BEFORE issuing a single command. That file holds the endpoints, payload shapes, templates and gotchas; acting without it produces wrong payloads and wrong results.
Mode selection
| Mode | Use when the request ... | Example triggers | Read this first |
|---|---|---|---|
authoring | creates or updates an Ontology item, entity/relationship types, or data bindings, and previews/confirms a definition change | create ontology item, bind entity type, add relationship type, update ontology definition | references/authoring.md |
consumption | explores an existing ontology: schema, entity types, bindings, lineage, grounding extraction, graph walks, summaries | entity types, ground query, ontology lineage, walk the graph, summarize the ontology | references/consumption.md |
Mode boundary rule
consumption is read-only exploration. Any definition write goes through the authoring mode's preview-and-confirm flow -- never call updateDefinition from a consumption request.
If a request genuinely spans modes, handle them one at a time and read each reference before you start that part. If the mode is ambiguous after reading this table, ask one short clarifying question instead of guessing.
Terminal write -- the step you must not skip
Reading the reference and planning the change is NOT completing the task. Each mutating mode ends with one state-changing call. If you did not issue it, nothing was persisted -- say so explicitly rather than reporting success.
| Mode | Terminal write |
|---|---|
authoring | createItem (POST /v1/workspaces/{ws}/items) to create the Ontology, then POST .../updateDefinition to persist entity types, relationships and bindings. A previewed definition tree is not a saved one. |
consumption | none -- this mode is read-only |
Before you report the task done, confirm the terminal call returned success and, where the reference documents a readback, read the artefact back to prove the change landed.
Shared essentials (all modes)
Resolve the workspace and item first; every mode depends on it.
| Task | Reference | Notes |
|---|---|---|
| Finding Workspaces and Items in Fabric | COMMON-CLI.md | Mandatory -- read before resolving any workspace or item id |
| Fabric Topology & Key Concepts | COMMON-CORE.md | Item types, workspaces, capacities |
| Environment URLs | COMMON-CORE.md | Sovereign / non-public cloud hosts |
| Authentication & Token Acquisition | COMMON-CORE.md | Wrong audience = 401; read before any auth issue |
| Authentication Recipes | COMMON-CLI.md | az login flows and token acquisition |
| Core Control-Plane REST APIs | COMMON-CORE.md | Pagination, LRO polling, rate limiting |
| Gotchas & Troubleshooting | COMMON-CLI.md | az rest audience, shell escaping, token expiry |
Rules
MUST
- Select exactly one mode from the table above before doing anything else.
- Read
references/<mode>.mdend to end, as your FIRST tool call, before the first command of that mode. Read it ONCE, in a single full read: do not re-open it, do not grep it again, and do not page through it. You already have it. - Apply the same read-once discipline to every other file you load, including nested
references/<mode>/*.mdsub-references and sharedcommon/*.mdfiles: open only the ones you actually need, read each ONCE end to end, and never grep or re-open one you already loaded. - Resolve workspace and item ids by listing and filtering, never by guessing a GUID.
- Announce a mode switch explicitly when the request crosses a boundary.
- Treat the reference as instructions, never as the deliverable. After reading it, RUN the documented commands against the live workspace and report the real results. Quoting what the reference says instead of executing it does not answer the request.
PREFER
- The narrowest mode that satisfies the request.
- Reading exactly ONE mode reference. Load a second only when the request genuinely spans modes, and say so before you do.
- Reporting the mode you chose in your first response so the user can correct you.
AVOID
- Acting from this dispatcher alone -- it intentionally omits the operational detail.
- Answering with a summary of the reference instead of executing it.
- Re-reading or re-grepping a reference you already loaded; it costs turns and tokens.
- Mutating anything while in a read-only mode.
- Loading a different skill for work this family already owns (see CRITICAL NOTES 3).
Examples
| User request | Mode | Reference to read |
|---|---|---|
| "What entity types exist in the Sales ontology and how are they bound?" | consumption | references/consumption.md |
| "Create an ontology item with Customer and Order entity types bound to the lakehouse." | authoring | references/authoring.md |
| "Ground this question against the ontology and show the graph walk." | consumption | references/consumption.md |
Account or credentials required
2 FOR YOUAll items below are required.
- 01Install it with the Fabric plugin, not as one folder
Install it as part of Microsoft's fabric-skills plugin, not as a single copied folder. Before its first step it reads shared Fabric guides kept outside its own folder, and it hands data reads to other Fabric skills; the plugin brings both. The plugin also adds Microsoft's other Fabric skills and three Fabric MCP servers.
- 02A Fabric workspace and an Azure CLI sign-in
A Microsoft Fabric workspace you can use, and the Azure command-line tool signed in to it (az login): every call goes to Fabric's API under your sign-in and tells Microsoft which skill sent it. Ontology is still a preview feature in Fabric.
This skill ships inside the Skills for Microsoft Fabric plugin. Listed package contents include 4 agents and an MCP server. Installed components and skill versions may vary by AI tool.
Install as a Claude Code plugin
Typed inside the agent's own prompt, not in a terminal. This skill uses files kept elsewhere in its plugin, so install the whole plugin — on its own the skill would be missing them.
The repository is licensed under MIT — use, modification, and redistribution are allowed under that license’s terms.
View the repository’s license file on GitHub →