- 01
/plugin marketplace add microsoft/skills-for-fabric - 02
/plugin install fabric-skills@fabric-collection
Builds and queries Eventhouse, Fabric's database for large volumes of event and time-series data, which is queried in KQL. Your assistant can create tables, set how long data is kept, load data and add functions or materialized views, or run read-only queries and report what it finds.
WHEN TO USE
USE FOR
- Count the events that arrived each hour over the last day.
- Create a table for a sensor feed that keeps 30 days of data.
- List the tables in a KQL database with their row counts.
- Check whether data is still arriving.
NOT FOR
- Building the event stream that feeds the database: the eventstream-cli skill.
- T-SQL against a warehouse or a lakehouse: the sqldw-cli skill.
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: eventhouse-cli(az rest:--headers "x-ms-fabric-skill=eventhouse-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
eventhouse-clifor anything expressed in KQL or stored in a KQL Database. Use the matchingeventstream-climode for streaming topology, and the matchingsqldw-*skill for T-SQL against a Warehouse or Lakehouse SQL endpoint.
Fabric Eventhouse / KQL Database -- CLI Skill
This one skill owns Fabric Eventhouse and KQL Database: schema and ingestion management plus read-only KQL analytics.
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 | runs KQL management commands (.create, .alter, .ingest, .drop), policies, mappings, functions or materialized views | create kql table, kql ingestion, kql retention policy, kql function, materialized view, kql mapping | references/authoring.md |
consumption | runs read-only KQL (where, summarize, join, render), discovers schema with .show, or monitors ingestion health | kql query, query eventhouse, time-series kql, show tables kql, explore eventhouse | references/consumption.md |
Mode boundary rule
consumption may only issue read-only KQL and .show commands. Any dot-command that changes state (.create, .alter, .ingest, .drop, .set-or-append) requires the authoring mode: say so, read references/authoring.md, then proceed.
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.
Reference index
Read the mode reference first; open a topic file below only when the task needs it. Every reference is listed here, so read it from this table rather than following a link out of another reference.
| Reference | Read it when |
|---|---|
| references/authoring.md | any authoring request -- start here |
| references/authoring-core.md | you need the capability matrix, table/schema, ingestion, policy, external table or permission detail behind an authoring task |
| references/authoring-advanced-operations.md | materialized views, stored functions, update policies, schema evolution, or monitoring authoring operations |
| references/authoring-scripts.md | you want a ready-to-run script for create-and-ingest, schema deployment, export or policies -- run them from scripts/, do not read them |
| references/consumption.md | any consumption request -- start here |
| references/consumption-discovery-queries.md | you need the .show discovery queries for schema, tables or ingestion health |
| EVENTHOUSE-CONSUMPTION-CORE.md | connection fundamentals, schema discovery and security, monitoring, performance best practices, or common KQL query patterns -- read before writing KQL |
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 | POST .../v1/rest/mgmt carrying the literal .create-merge table (or CREATE TABLE-equivalent), .alter or .ingest command. Composing the KQL management command and showing it to the user is not executing it. |
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 |
|---|---|---|
| "How many events arrived per hour in the last day in the Telemetry eventhouse?" | consumption | references/consumption.md |
| "Create a KQL table for the sensor feed and a 30-day retention policy." | authoring | references/authoring.md |
| "Show me the tables in the KQL database and their row counts." | 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. Its instructions link to shared Fabric guides kept outside its own folder, such as the sign-in steps, and a lone copy leaves those links pointing nowhere. The plugin brings those guides and Microsoft's other Fabric skills, which it hands event streams and SQL to.
- 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.
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 →