semantic-model-consumption
Skill3 starsChanged 4 months agoMITView on GitHub
Execute raw DAX queries and inspect metadata of Microsoft Fabric Power BI semantic models via the MCP server ExecuteQuery tool. Use when the user already knows the DAX to write, wants to run EVALUATE statements, or needs to inspect model metadata (tables, columns, measures, relationships, hierarchies) using INFO functions. For natural-language business questions (where you generate the DAX), use `fabriciq`. For creating, deploying, or managing semantic model definitions, use `semantic-model-authoring`. Triggers: "run DAX query", "execute EVALUATE", "semantic model metadata", "list semantic model tables", "INFO.VIEW.TABLES", "get measure expression", "DAX against", "query the model".
In this repository36 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- activator-authoring-cliSkill
- activator-consumption-cliSkill
- check-updatesSkill
- databricks-migrationSkill
- dataflows-authoring-cliSkill
- dataflows-consumption-cliSkill
- dataflows-save-as-authoring-cliSkill
- e2e-medallion-architectureSkill
- eventhouse-authoring-cliSkill
- eventhouse-consumption-cliSkill
- eventstream-authoring-cliSkill
- eventstream-consumption-cliSkill
- fabriciq-ontology-authoring-cliSkill
- fabriciq-ontology-consumption-cliSkill
- fabriciqSkill
- hdinsight-migrationSkill
- mlv-operations-cliSkill
- pipeline-migrationSkill
- powerbi-report-authoringSkill
- powerbi-report-designSkill
- powerbi-report-managementSkill
- powerbi-report-planningSkill
- search-consumption-cliSkill
- semantic-model-authoringSkill
- spark-authoring-cliSkill
- spark-consumption-cliSkill
- spark-operations-cliSkill
- sqldb-authoring-cliSkill
- sqldb-consumption-cliSkill
- sqldb-operations-cliSkill
- sqldw-authoring-cliSkill
- sqldw-consumption-cliSkill
- sqldw-operations-cliSkill
- synapse-migrationSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
15 rules. About 0 are common, 6 are distinctive, and 9 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
9
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 75
Keep this skill read-only: metadata discovery and analytical DAX queries only.
- Very specific: line 76
Treat DAX data queries and INFO.VIEW.* as available to any user with read access to the semantic model.
- Very specific: line 78
Use DAX INFO.VIEW.* / INFO.* for metadata discovery before writing data queries.
- Distinctive: line 84
Keep guidance provider-agnostic so tool endpoint migration is low risk.
- Distinctive: line 92
Run the discovery-queries.md § Scope Estimation Queries to estimate metadata scope (table, column, measure, and relationship counts) before …
- Very specific: line 93
Start with INFO.VIEW.TABLES() for a fast table inventory.
- Very specific: line 95
Use INFO.VIEW.RELATIONSHIPS() to validate joins and filter behavior.
- Distinctive: line 96
Use the full query catalog in discovery-queries.md for deeper patterns.
- Distinctive: line 158
Use the FabricIQ MCP server tools directly — call them as MCP tool invocations:
- Very specific: line 168
Preferred: Call DiscoverArtifacts (MCP tool) with searchQuery set to the model name and artifactTypes: ["SemanticModel"].
- Very specific: line 173
Call the ExecuteQuery MCP tool directly:
- Very specific: line 184
Call GetSemanticModelSchema(artifactId = "<SEMANTIC_MODEL_GUID>") to retrieve table/column/measure definitions before writing DAX.
- Very specific: line 191
Fix: Verify the active MCP server/tool inventory and confirm ExecuteQuery is exposed.
- Very specific: line 195
Fix: Start with INFO.VIEW.* functions for read-oriented discovery.
- Distinctive: line 199
Fix: Use the scope estimation queries in discovery-queries.md § Scope Estimation Queries to estimate scope and inspect output schemas, then …
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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.
Files
Update Check — ONCE PER SESSION (mandatory) The first time this skill is used in a session, run the check-updates skill before proceeding.
- GitHub Copilot CLI / VS Code: invoke the
check-updatesskill.- Claude Code / Cowork / Cursor / Windsurf / Codex: compare local vs remote package.json version.
- Skip if the check was already performed earlier in this session.
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
Power BI Semantic Model Consumption
Table of Contents
| Task | Reference | Notes |
| Finding Workspaces and Items in Fabric | COMMON-CLI.md § Finding Workspaces and Items in Fabric | Mandatory — READ link first [needed for finding workspace id by its name or item id by its name, item type, and workspace id] |
| Fabric Topology & Key Concepts | COMMON-CORE.md § Fabric Topology & Key Concepts | Hierarchy; Finding Things in Fabric |
| Environment URLs | COMMON-CORE.md § Environment URLs | Production (Public Cloud) |
| Authentication & Token Acquisition | COMMON-CORE.md § Authentication & Token Acquisition | Wrong audience = 401; covers token audiences, delegated vs app permissions, OAuth flows, identity types, and Entra app registration |
| Core Control-Plane REST APIs | COMMON-CORE.md § Core Control-Plane REST APIs | Includes workspace/item CRUD, resolve-by-name, pagination, LRO polling, and rate-limiting patterns |
| OneLake Data Access | COMMON-CORE.md § OneLake Data Access | Requires storage.azure.com token, not Fabric token; covers URL structure, ADLS Gen2 parity, and shortcuts |
| Job Execution | COMMON-CORE.md § Job Execution | Run On-Demand Job; Get / Cancel Job |
| Capacity Management | COMMON-CORE.md § Capacity Management | List Capacities; Assign Workspace to Capacity |
| Gotchas, Best Practices & Troubleshooting | COMMON-CORE.md § Gotchas, Best Practices & Troubleshooting | Common Errors; Best Practices |
| Tool Selection Rationale | COMMON-CLI.md § Tool Selection Rationale | |
| Authentication Recipes | COMMON-CLI.md § Authentication Recipes | az login flows, environment detection, token acquisition, and debugging |
Fabric Control-Plane API via az rest | COMMON-CLI.md § Fabric Control-Plane API via az rest | Always pass --resource; includes workspace/item operations, pagination, and LRO patterns |
OneLake Data Access via curl | COMMON-CLI.md § OneLake Data Access via curl | Use curl not az rest (different token audience); file list/read/upload/delete and directory creation |
| SQL / TDS Data-Plane Access | COMMON-CLI.md § SQL / TDS Data-Plane Access | sqlcmd (Go) connect, query, CSV export, service principal auth, and connection parameter discovery |
| Job Execution (CLI) | COMMON-CLI.md § Job Execution | Run notebooks/pipelines, refresh semantic models, check/cancel jobs |
| OneLake Shortcuts | COMMON-CLI.md § OneLake Shortcuts | Create a Shortcut; List Shortcuts; Delete a Shortcut |
| Capacity Management (CLI) | COMMON-CLI.md § Capacity Management | List Capacities; Assign Workspace to Capacity |
| Composite Recipes | COMMON-CLI.md § Composite Recipes | End-to-end workspace→lakehouse→file, SQL endpoint→query, and notebook execution recipes |
| Gotchas & Troubleshooting (CLI-Specific) | COMMON-CLI.md § Gotchas & Troubleshooting (CLI-Specific) | |
| Quick Reference | COMMON-CLI.md § Quick Reference | az rest Template; Token Audience ↔ CLI Tool Matrix |
| Prerequisites | SKILL.md § Prerequisites | |
| Must/Prefer/Avoid | SKILL.md § Must/Prefer/Avoid | Guardrails for read-only semantic model usage. MUST DO; PREFER; AVOID |
| Metadata Discovery | SKILL.md § Metadata Discovery | INFO.VIEW.* and INFO.* functions. |
| Recommended Discovery Order | SKILL.md § Recommended Discovery Order | Preferred order for metadata exploration |
| Frequently Used INFO Functions | SKILL.md § Frequently Used INFO Functions | High-usage function list for first-pass discovery |
| Complete INFO Function Catalog (Dynamic) | discovery-queries.md § Complete INFO Function Catalog (Dynamic) | |
| Metadata Object → INFO Function Map | SKILL.md § Metadata Object → INFO Function Map | Inlined mapping for object-focused discovery |
| Query Execution | SKILL.md § Query Execution | ExecuteQuery usage shape |
| Troubleshooting | SKILL.md § Troubleshooting | Resolve common execution and metadata issues |
| Examples | SKILL.md § Examples | Sample Metadata Query; Sample Data Query |
| Scope Estimation Queries | discovery-queries.md § Scope Estimation Queries | |
| INFO Output Columns | discovery-queries.md § INFO Output Columns | INFO.VIEW.* (preferred first-pass metadata); Critical INFO.* (deep metadata / diagnostics) |
| Narrowing Results (Projection + Filtering) | discovery-queries.md § Narrowing Results (Projection + Filtering) | |
| Deep Metadata Queries | discovery-queries.md § Deep Metadata Queries | |
| Dependency Discovery | discovery-queries.md § Dependency Discovery | Dependency rowset for a DAX query; Dependency rows scoped to a measure; Reverse dependencies (what references a measure) |
Prerequisites
- COMMON-CORE.md — Fabric concepts, authentication, and control-plane API context.
- COMMON-CLI.md — CLI-oriented discovery and token/audience patterns.
Must/Prefer/Avoid
MUST DO
- Call MCP tools for discovery and execution — use
DiscoverArtifactsto find the semantic model GUID andExecuteQueryto run DAX queries. These are MCP tool invocations, not shell commands. Do NOT useaz rest,Get-Command, or PowerShell scripts to discover or invoke them. - Keep this skill read-only: metadata discovery and analytical DAX queries only.
- Treat DAX data queries and
INFO.VIEW.*as available to any user with read access to the semantic model; assume otherINFO.*functions may require elevated permissions. - Resolve workspace and semantic model item identity dynamically; do not hardcode IDs.
- Use DAX
INFO.VIEW.*/INFO.*for metadata discovery before writing data queries.
PREFER
- Validate semantic model scope early (
artifactId) before iterative query refinement. - Discover semantic model schema progressively: use filtered and projected
INFO.VIEW.*/INFO.*calls (e.g.,SELECTCOLUMNS+FILTER) to fetch only the information directly relevant to the current task instead of retrieving the full schema up front. See discovery-queries.md § Narrowing Results (Projection + Filtering). - Keep guidance provider-agnostic so tool endpoint migration is low risk.
AVOID
- Model-change operations in this skill.
Recommended Discovery Order
- Run the discovery-queries.md § Scope Estimation Queries to estimate metadata scope (table, column, measure, and relationship counts) before deep discovery.
- Start with
INFO.VIEW.TABLES()for a fast table inventory. - Expand to
INFO.VIEW.COLUMNS()andINFO.VIEW.MEASURES()for semantic details. - Use
INFO.VIEW.RELATIONSHIPS()to validate joins and filter behavior. - Use the full query catalog in discovery-queries.md for deeper patterns.
Frequently Used INFO Functions
INFO.VIEW.TABLESINFO.VIEW.MEASURESINFO.VIEW.COLUMNSINFO.VIEW.RELATIONSHIPSINFO.PARTITIONSINFO.MODELINFO.STORAGETABLECOLUMNSEGMENTSINFO.DEPENDENCIESINFO.EXPRESSIONSINFO.ROLESINFO.STORAGETABLECOLUMNSINFO.CALCULATIONGROUPSINFO.CALCULATIONITEMSINFO.CULTURESINFO.OBJECTTRANSLATIONSINFO.USERDEFINEDFUNCTIONSINFO.REFRESHPOLICIESINFO.ATTRIBUTEHIERARCHYSTORAGESINFO.COLUMNPARTITIONSTORAGESINFO.COLUMNSTORAGESINFO.DICTIONARYSTORAGESINFO.HIERARCHYSTORAGESINFO.PARTITIONSTORAGESINFO.RELATIONSHIPINDEXSTORAGESINFO.RELATIONSHIPSTORAGESINFO.SEGMENTMAPSTORAGESINFO.SEGMENTSTORAGESINFO.STORAGEFOLDERSINFO.STORAGEFILESINFO.TABLESTORAGESINFO.GENERALSEGMENTMAPSEGMENTMETADATASTORAGESINFO.DELTATABLEMETADATASTORAGESINFO.PARQUETFILESTORAGESINFO.STORAGETABLES
Metadata Object → INFO Function Map
| Metadata Object | Primary INFO functions |
| Model | INFO.MODEL |
| Tables | INFO.VIEW.TABLES |
| Columns | INFO.VIEW.COLUMNS, INFO.GROUPBYCOLUMNS, INFO.RELATEDCOLUMNDETAILS |
| Measures | INFO.VIEW.MEASURES, INFO.FORMATSTRINGDEFINITIONS, INFO.DETAILROWSDEFINITIONS |
| Relationships | INFO.VIEW.RELATIONSHIPS |
| Partitions | INFO.PARTITIONS, INFO.EXPRESSIONS, INFO.QUERYGROUPS, INFO.REFRESHPOLICIES, INFO.DATACOVERAGEDEFINITIONS |
| Security roles & permissions | INFO.ROLES, INFO.TABLEPERMISSIONS, INFO.COLUMNPERMISSIONS |
| Hierarchies | INFO.HIERARCHIES, INFO.LEVELS, INFO.ATTRIBUTEHIERARCHIES, INFO.VARIATIONS |
| Calculation groups/items | INFO.CALCULATIONGROUPS, INFO.CALCULATIONITEMS, INFO.CALCULATIONEXPRESSIONS |
| Perspectives | INFO.PERSPECTIVES, INFO.PERSPECTIVETABLES, INFO.PERSPECTIVECOLUMNS, INFO.PERSPECTIVEHIERARCHIES, INFO.PERSPECTIVEMEASURES |
| Calendars | INFO.CALENDARS, INFO.CALENDARCOLUMNGROUPS, INFO.CALENDARCOLUMNREFERENCES |
| Cultures | INFO.CULTURES |
| Object translations | INFO.OBJECTTRANSLATIONS |
| Functions | INFO.USERDEFINEDFUNCTIONS |
| Dependencies / lineage | INFO.DEPENDENCIES, INFO.CHANGEDPROPERTIES, INFO.EXCLUDEDARTIFACTS |
| Storage internals / size | INFO.STORAGEFOLDERS, INFO.STORAGEFILES, INFO.TABLESTORAGES, INFO.COLUMNSTORAGES, INFO.PARTITIONSTORAGES, INFO.SEGMENTMAPSTORAGES, INFO.DICTIONARYSTORAGES, INFO.COLUMNPARTITIONSTORAGES, INFO.SEGMENTSTORAGES, INFO.RELATIONSHIPSTORAGES, INFO.RELATIONSHIPINDEXSTORAGES, INFO.ATTRIBUTEHIERARCHYSTORAGES, INFO.HIERARCHYSTORAGES, INFO.GENERALSEGMENTMAPSEGMENTMETADATASTORAGES, INFO.DELTATABLEMETADATASTORAGES, INFO.PARQUETFILESTORAGES, INFO.STORAGETABLES, INFO.STORAGETABLECOLUMNS, INFO.STORAGETABLECOLUMNSEGMENTS |
Query Execution
Use the FabricIQ MCP server tools directly — call them as MCP tool invocations:
| Parameter | Description |
artifactId | GUID of the target semantic model |
daxQueries | Array of 1–4 DAX queries (each must contain a single EVALUATE statement) |
maxRows | Optional. Default 250, max 1,000 rows per query |
How to find the artifact ID
- Preferred: Call
DiscoverArtifacts(MCP tool) withsearchQueryset to the model name andartifactTypes: ["SemanticModel"]. - Fallback only if MCP discovery is unavailable: Resolve via Fabric REST (
az rest) — list items of typeSemanticModelin the workspace and filter bydisplayName.
Executing a query
Call the ExecuteQuery MCP tool directly:
ExecuteQuery(
artifactId = "<SEMANTIC_MODEL_GUID>",
daxQueries = ["EVALUATE SUMMARIZECOLUMNS(...)"]
)Getting the schema first
Call GetSemanticModelSchema(artifactId = "<SEMANTIC_MODEL_GUID>") to retrieve table/column/measure definitions before writing DAX.
Troubleshooting
- ExecuteQuery capability is unavailable in the MCP server
- Issue: Query execution cannot start because
ExecuteQueryis not available in the active tool list. - Cause: The FabricIQ MCP server is not registered, not loaded, or the current client session has stale tool metadata.
- Fix: Verify the active MCP server/tool inventory and confirm
ExecuteQueryis exposed.
- Issue: Query execution cannot start because
- Advanced INFO functions return permission errors
- Issue: Queries against
INFO.*fail with authorization or privilege-related errors. - Cause: Many
INFO.*functions require elevated semantic model permissions beyond standard read access. - Fix: Start with
INFO.VIEW.*functions for read-oriented discovery.
- Issue: Queries against
- Metadata output volume is too large for focused analysis
- Issue: Returning full metadata rowsets introduces too many properties and crowds the working context.
- Cause: Unbounded
INFO.VIEW.*andINFO.*queries return broad object/property surfaces that are often unnecessary for the current task. - Fix: Use the scope estimation queries in discovery-queries.md § Scope Estimation Queries to estimate scope and inspect output schemas, then narrow results with projection and filtering as shown in discovery-queries.md § Narrowing Results (Projection + Filtering).
- Do not use
INFODAX functions to retrieve role memberships- Issue:
INFO.ROLEMEMBERSHIPS()returns empty or incomplete results. - Cause: Role members are assigned at the service level (Entra ID) after deployment, not in the model definition — so DAX
INFOfunctions cannot reliably surface them. - Fix: Redirect to Manage role membership documentation for current guidance on role membership management.
- Issue:
Examples
For the full query catalog (including dependency patterns), see discovery-queries.md.
Sample Metadata Query
EVALUATE
INFO.VIEW.TABLES()
ORDER BY [Name]Sample Data Query
DEFINE
MEASURE 'Sales'[Total Sales] = SUM('Sales'[Amount])
EVALUATE
SUMMARIZECOLUMNS(
'Customer'[Customer Name],
"Total Sales", [Total Sales]
)
ORDER BY [Total Sales] DESCDoes 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
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.

