Generated banner for Powerbi Report CLI
Generated logo for Powerbi Report CLI

Powerbi Report CLI

MicrosoftOfficialPublished by Microsoft

  • Skill
  • Tool integration
  • Data and AI
  • MIT
  • Low risk

From the author

Plan, design, author, preview, publish, and manage Power BI reports across requirements, page design, local PBIR/PBIP edits, validation, screenshots, Fabric upload/download, and rebinding. Use for report lifecycle work; use semantic-model-authoring for model or DAX changes and fabriciq for data questions. Triggers: plan Power BI report, design report page, edit PBIR, preview PBIP, publish report, rebind report
— the description by Microsoft

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

The powerbi-report-cli skill provides a structured, mode-based framework for managing the entire Power BI report lifecycle. It acts as a dispatcher across four distinct phases: planning (requirements and scope), design (visual and layout strategy), authoring (local PBIR/PBIP file manipulation and validation), and management (Fabric item transport and rebinding). The skill enforces strict boundaries between these modes to ensure quality, requiring explicit approval for new reports and utilizing a dedicated CLI for metadata-driven validation and authoring tasks.

What it does

  • Guides users through report requirements, scope, and page planning.
  • Provides design contracts for visual archetypes, layouts, and branding.
  • Enables local editing, validation, and previewing of PBIR and PBIP files.
  • Handles report item transport to and from Microsoft Fabric.
  • Supports re-theming, conditional formatting, and visual configuration.
  • Enforces a mandatory approval gate for greenfield report development.

When to use it

  • When planning a new Power BI report from a semantic model.
  • When you need to define a professional design brief or layout strategy.
  • When editing local PBIR/PBIP files, including visuals, filters, and themes.
  • When validating report structure and formatting before deployment.
  • When publishing or managing report items within a Fabric workspace.

Advantages

  • Ensures consistent report quality through a structured, multi-mode workflow.
  • Prevents premature publishing by enforcing a mandatory approval barrier.
  • Uses a dedicated CLI to eliminate guesswork in PBIR schema and property editing.
  • Maintains clear separation between design intent and technical implementation.
  • Provides robust validation tools to catch errors before Fabric deployment.

Usage examples

“Create a new executive report from this semantic model.”
The agent enters planning mode, inspects the model, generates a report spec, and requests user approval before proceeding.
“Design an operational page and choose the right charts.”
The agent enters design mode, produces a design brief with page archetypes and chart recommendations.
“Add a KPI page to this PBIP, validate it, and take screenshots.”
The agent enters authoring mode, modifies the local PBIP files, runs validation, and captures screenshots for review.
“Publish this local PBIP to my Fabric workspace and rebind it.”
The agent enters management mode, performs the upload to Fabric, and completes the rebind operation.

Install

  1. Download the skill as a ZIP:

    https://mp-staging.autogineer.com/agent-skills/microsoft/powerbi-report-cli/download
  2. Unzip it into the cross-client skills folder of your project:

    mkdir -p .agents/skills && unzip powerbi-report-cli.zip -d .agents/skills

Documentation by Microsoft

Telemetry — MANDATORY. Every api.fabric.microsoft.com call must carry x-ms-fabric-skill: powerbi-report-cli (az rest: --headers "x-ms-fabric-skill=powerbi-report-cli"), including every LRO poll, fabric_lro and retry. Snippets omit it — add it anyway.

CRITICAL NOTES

  1. To find workspace details, including its ID, from a workspace name: list all workspaces, then use JMESPath filtering.

  2. To find item details, including its ID, from a workspace ID, item type, and item name: list all items of that type in that workspace, then use JMESPath filtering.

  3. Use powerbi-report-cli for the report artifact: requirements, design, PBIR/PBIP page and visual edits, preview, and publishing. Semantic model, measure, and DAX work belongs to a semantic-model skill. Natural-language questions about report data belong to fabriciq.

Power BI Reports - CLI Skill

This skill owns the Power BI report lifecycle end to end: requirements and scope, visual design, local PBIR/PBIP authoring and preview, and report-item transport to and from Microsoft Fabric.

It is a mode dispatcher and intentionally contains no detailed procedures. Select the mode that matches the request, then read the matching mode reference end to end before acting. The mode file holds the required workflow, commands, payloads, templates, and failure rules.

Mode Selection

ModeUse when the request...Existing route examplesRead first
planningcreates a new report/dashboard and needs requirements, model/dependency inspection, scope, a page plan, and approval before implementationcreate a report, build a dashboard, create from a semantic model, plan then implement, walk me through creating a reportreferences/planning.md, then references/planning-part-02.md
designdecides what a report should look like: tone, signature, page archetype, chart type, layout, color, typography, theme direction, accessibility, brand application, redesign, or critiquedesign a Power BI report, make the dashboard professional, choose a chart, apply a brand, redesign the report, create a design briefreferences/design.md
authoringreads or edits local PBIR/PBIP files, validates them, previews the report, or captures screenshotsedit PBIR, create/add a report page or visual, format a visual, add filters/slicers/bookmarks/themes, validate PBIR, preview/reload/screenshot in Desktop or servicereferences/authoring.md
managementmoves a report definition to or from Fabric or manages the workspace report itempublish/upload/download PBIR or PBIP, list reports, get/update/delete a report, rebind a reportreferences/management.md

Mode Boundary Rules

  • Classify by intent, not by which file or tool is already open.

  • design decides what the report should look like; authoring writes the PBIR that realizes it. Choosing a chart type is design; encoding it into visual.json is authoring.

  • Restyling or reformatting an existing local report is authoring, even when the request uses design language. Use design when the user wants advice or a design contract rather than a file change.

  • authoring changes local files and performs preview/validation. It does not publish to Fabric.

  • management transports definitions and manages Fabric report items. It does not invent or directly author PBIR content.

  • planning owns the guided requirements-to-approval flow for a new report. A focused edit to an existing report goes directly to authoring.

A greenfield request can span modes in this order:

planning -> design -> authoring -> management

Handle one mode at a time. Announce each switch and read the new mode reference before starting that part. The planning approval gate is a turn boundary: never build or publish until the user explicitly approves the locked spec in a later reply.

GREENFIELD APPROVAL BARRIER — MANDATORY. When a new-report request asks to plan, build, and/or publish but the user has not approved a locked spec in a prior reply, set the current phase to approval_pending and keep planning as the only active mode. In this phase, do not load authoring or management, edit/scaffold PBIR or semantic-model files, generate synthetic data, call Fabric write APIs, or publish. Persist _brief/report-spec.md, ask for explicit approval, and end the turn. The build/publish wording in the original request is desired future scope, not approval to cross this barrier.

Required Deliverable by Mode

ModeCompletion requirement
planningPersist _brief/report-spec.md or the user-named equivalent, ask for explicit approval, and stop before implementation.
designProduce the complete Design Brief: contract, including design_identity and a page archetype/layout contract for every page. Do not edit PBIR or call Fabric APIs.
authoringPersist the requested PBIR/PBIP changes, validate each logical batch, then complete the selected preview and screenshot-review workflow required by the authoring reference. Do not publish.
managementComplete the requested Fabric report operation, including LRO polling and documented readback verification.

Rules

MUST
  • Select the narrowest mode that fully covers the current request.

  • Read references/<mode>.md end to end before the first command or file edit in that mode. When an already-loaded mode explicitly routes one narrow cross-mode operation to a named topic reference, treat that topic reference as the complete handoff; do not load the target mode's umbrella file unless the work expands beyond that operation.

  • In planning mode, also read references/planning-part-02.md before producing _brief/report-spec.md; it contains the required canonical design contract and approval checks.

  • Across a multi-turn task, retain a compact working state containing resolved workspace/item/model IDs, local and downloaded paths, and references already read. Reuse it in later turns unless the user explicitly requests a fresh query or the preceding operation invalidated a value.

  • Preserve every argument and safety boundary documented by the selected mode.

  • Announce and perform an explicit mode switch when the request crosses a boundary.

  • Use the powerbi-report-author CLI metadata and validation surfaces instead of guessing PBIR schemas, roles, formatting properties, selectors, or enum values.

  • Keep local edits local unless the user explicitly requests publishing.

  • Resolve Fabric workspace and item IDs by listing and filtering rather than guessing identifiers.

  • Produce the artifact the user requested; reading or summarizing a reference is not task completion.

PREFER
  • Infer facts already present in the prompt, semantic model, existing PBIP, or prior approved spec instead of asking again.

  • Load only the selected mode and its directly relevant topic references.

  • Reuse reference guidance already loaded in the current task. Open a new reference only when the requested operation or an observed mismatch requires it.

  • Preserve the user's existing project structure, schemas, host, operation, binding, and delivery target unless the selected mode explicitly requires a change.

AVOID
  • Acting from this dispatcher without reading the selected mode reference.

  • Reloading this dispatcher, a mode file, or a topic reference already read in the current task solely because the conversation advanced to a later turn.

  • Loading a retired sibling skill name; planning, design, authoring, and management are modes of this skill.

  • Editing PBIR or calling Fabric APIs in planning or design.

  • Publishing from authoring, or authoring PBIR content from management.

  • Bypassing the planning approval gate because the original request also asked to build or publish.

<!-- BEGIN GENERATED REFERENCE INDEX -->

Complete Reference Index

Open every relevant reference directly from this index. Files named part-XX continue the named topic.

Authoring
Design
Mode Guides

<!-- END GENERATED REFERENCE INDEX -->

Examples

User requestMode
"Create a new executive report from this semantic model."planning
"Design an operational page and choose the right charts."design
"Add a KPI page to this PBIP, validate it, and take screenshots."authoring
"Publish this local PBIP to my Fabric workspace and rebind it."management

Route Compatibility

The merged skill preserves the four previous route surfaces. Treat the following phrases as explicit aliases for the corresponding mode:

ModePreserved route phrases
planningcreate a report; build a report; create a dashboard; create a new report from scratch; create a report from a semantic model or dataset link; build a report for this model; make me a dashboard; plan then implement; walk me through creating a report
designdesign Power BI report; make dashboard look professional; choose chart type; apply brand to report; redesign report; create design brief; Power BI report design archetype
authoringedit PBIR; create Power BI report page; add visual to PBIP; format report visual; validate Power BI report; preview Power BI report; Power BI Desktop preview status; preview report in service; preview report in browser; screenshot report page; screenshot all report pages; list preview hosts; implement dashboard in PBIP; add dashboard visuals to report; implement an approved PBIP report spec; edit PBIR pages/visuals; edit a Power BI report
managementupload PBIR report definition; upload Power BI report; download PBIR definition; publish PBIR definition; publish Power BI report to Fabric; manage Power BI reports; list workspace reports

Files

references/management-part-04.md

powerbi-report-cli management mode -- Power BI Report Items in Fabric - Part 4

Contents

  • Agentic Workflow

    • Publishing a local .pbip

    • Modifying an existing report in Fabric

    • Creating a new report in Fabric

  • Troubleshooting

Continuation of management.md. Open this file directly from the skill reference index.

Agentic Workflow

Keep one compact run-state record for this workflow: workspace name/ID, model name/ID, report name/ID, local .pbip/.Report/.SemanticModel paths, downloaded-definition path, the complete .../getDefinition?format=PBIR URL, and the active LRO endpoint for the current operation. Populate stable IDs, paths, and URLs once and reuse them across later turns. The LRO endpoint is operation-scoped: replace it with the Location or operation ID returned by each new create, getDefinition, or updateDefinition request, poll only that endpoint, and clear it after terminal success or failure. Never reuse a terminal endpoint for a later operation. A user request to query Fabric again is an explicit exception for stable values; refresh only the requested value and update the record. Re-downloading after updateDefinition reuses the stored complete URL; do not reconstruct it without the format query.

Publishing a local .pbip

This is the primary entry point when a user has a local .pbip (report plus sibling .SemanticModel) on disk and asks to publish, upload, push, or deploy the report to a Fabric workspace.

Do not enter this workflow merely because local authoring and screenshot review finished successfully. Never publish or overwrite the remote report with local changes until the user explicitly gives permission. If the user has not explicitly requested this remote write in the current request, or you are unsure, keep the changes local and do not publish. A request to publish does not by itself authorize replacing an existing report; step 8 requires the user to confirm they agree to overwrite the existing remote report.

1. Detect that the source is a local .pbip. Any of these signals:

  • A <Name>.pbip file in or above the working directory.

  • A <Name>.Report folder with a sibling <Name>.SemanticModel folder.

  • The report's definition.pbir uses byPath (local/Git form) rather than byConnection (API form).

  • Presence of a .pbi/ cache folder.

If the source is not a local .pbip (e.g., the report was already downloaded from Fabric and only the .Report folder is present with a byConnection definition.pbir), use the Modifying an existing report in Fabric workflow instead.

2. Confirm the target workspace once. Resolve and store the workspace ID by name (per COMMON-CLI.md (see ../../../common/COMMON-CLI.md, section finding-workspaces-and-items-in-fabric)). This single workspace is reused for both the model deploy (if applicable) and the report publish — never split them. A workspace name supplied in the request is a lookup key, not confirmation that the workspace exists. List and resolve it before step 3. If it is missing or ambiguous, report that and stop; never defer workspace resolution until after the user answers the semantic-model question.

3. Prompt the user about the semantic model. Ask explicitly — do not silently choose. This question happens only after step 2 has resolved the exact workspace ID:

"Do you want me to publish the local semantic model to this workspace too, or connect this report to an existing semantic model already in the workspace?"

4a. Branch: "Publish the local model".

  • Check whether a semantic-model authoring skill is available in the current session.

    • Available → hand off to that skill to create or update the semantic model. Pass: target workspace ID, the local .SemanticModel folder path (TMDL source), and the desired model display name. Wait for that skill's workflow to reach terminal success before proceeding.

    • Not available → tell the user a semantic-model authoring skill is not loaded in this session and that publishing the local model is not possible without it. Then degrade to branch 4b (connect-to-existing) and re-prompt for which workspace model to bind the report to.

4b. Branch: "Connect to an existing model in the workspace".

  • List semantic models in the target workspace and confirm the target model with the user. Resolve semanticModelId by name.

5. Resolve semanticModelId. Regardless of branch, the report needs a concrete model ID to bind to:

  • After 4a: list semantic models in the target workspace and find the model just deployed by name (the model skill verifies by listing workspace items but does not return an ID).

  • After 4b: this was already done.

6. Verify bindings against the resolved model (universal, both branches). Download the model TMDL and run the bindings diff per Verify semantic-model bindings after the target model is resolved in the MUST section of management-part-03.md. Even on the publish-the-local-model branch, the model skill may rename tables or apply transforms during deploy, so this diff is not optional. Treat the downloaded deployed TMDL as the canonical schema source for the first comparison. Do not also connect to the model and issue separate table, column, and measure listings when that TMDL is complete and parseable. Escalate to targeted live-model inspection only for names the first diff cannot resolve. Remap any drift via the authoring mode or, if structurally divergent, prompt the user before re-authoring.

7. Rebind definition.pbir from byPath → byConnection. Use the authoring mode to set:

"datasetReference": {
  "byConnection": {
    "connectionString": "semanticmodelid=<resolved-id>"
  }
}

The Fabric API rejects byPath; this swap is mandatory on every local-source publish. For this narrow mechanical conversion, use the API-publish form shown above. If more binding detail is needed, read authoring/model-binding.md directly; do not load the full authoring.md umbrella or unrelated visual-authoring references. If the binding diff in step 6 requires broader PBIR repairs, switch to the full authoring workflow at that point. The conversion MUST execute before any powerbi-report-author pack command; pack is byte-verbatim and does not repair dataset references.

8. Decide create-new vs. update-existing for the report. Default the report displayName to the .pbip filename without extension (e.g. SalesDashboard.pbip → "SalesDashboard"). Surface the default to the user so they can override.

  • List reports in the target workspace and look up the chosen displayName.

    • Not found → create. Follow Create Report (with Definition) in management-part-02.md.

    • Found → confirm with the user: overwrite the existing report (updateDefinition), publish under a different name, or cancel. Follow Update Report Definition in management-part-02.md on overwrite.

9. Pack and upload. Pick the branch that matches the create-new versus overwrite-existing decision from step 8. Use the create branch for a new report and the overwrite branch for an existing one. Run the Modern-PBIR preflight before pack in management.md first, then run powerbi-report-author pack for the base64+walk transport step and use az rest for the Fabric call. Pack emits all qualifying PBIR parts with forward-slash paths; az rest still owns POST, x-ms-operation-id capture (with --verbose written to a file), and LRO polling to terminal success.

  • Create branch from step 8:

    set -euo pipefail
    
    REPORT_DISPLAY_NAME="SalesDashboard"   # Non-empty name confirmed in step 8.
    REPORT_DESCRIPTION="Published from local PBIP"   # Optional; leave unset to omit.
    PACK_CREATE_ARGS=(--raw --mode create --display-name "$REPORT_DISPLAY_NAME")
    if [ -n "${REPORT_DESCRIPTION:-}" ]; then
      PACK_CREATE_ARGS+=(--description "$REPORT_DESCRIPTION")
    fi
    
    powerbi-report-author pack ./MyReport.Report "${PACK_CREATE_ARGS[@]}" --out create-report.json
    az rest --method post \
      --resource "https://api.fabric.microsoft.com" \
      --url "https://api.fabric.microsoft.com/v1/workspaces/$WS_ID/reports" \
      --headers "Content-Type=application/json" \
      --body @create-report.json \
      --verbose 2>&1 | tee publish-create-start.log

    Do not pass --description ""; omit the flag when no description is intended.

  • Overwrite branch from step 8:

    set -euo pipefail
    
    powerbi-report-author pack ./MyReport.Report --raw --out update-definition.json
    az rest --method post \
      --resource "https://api.fabric.microsoft.com" \
      --url "https://api.fabric.microsoft.com/v1/workspaces/$WS_ID/reports/$REPORT_ID/updateDefinition" \
      --headers "Content-Type=application/json" \
      --body @update-definition.json \
      --verbose 2>&1 | tee publish-update-start.log

10. Clean up any temporary files created during the flow.

Note on report-side verification: there is no reliable programmatic way to confirm a report renders correctly post-publish — the report lives at a Fabric Service URL and visual rendering requires a browser session. Surface the workspace/report URL so the user can verify in the browser.

Modifying an existing report in Fabric
  1. Authenticate → see COMMON-CLI.md § Authentication Recipes (see ../../../common/COMMON-CLI.md, section authentication-recipes)

  2. Find workspace → Resolve workspace ID by name

  3. List/find report → Resolve report ID by name

  4. Download definition → getDefinition?format=PBIR → capture/poll any LRO → save the final PBIR JSON to payload.json, then powerbi-report-author unpack ./MyReport.Report --input payload.json. Use a fresh or explicitly emptied directory for every download, including reruns. unpack only overwrites files present in the payload and leaves other local files untouched, so --force into a reused directory keeps parts that were deleted on the server and the next pack re-uploads them. Do not rerun with --force into a directory that already holds a previous download.

  5. Author PBIR content → Use the authoring mode for ALL changes. This covers every file: definition.pbir, report.json, version.json, pages.json, page configs, visuals, filters, formatting, themes, and expressions. Follow its guidance for correct structure, schemas, and field values. Use its CLI tools to validate. Never construct any PBIR JSON from memory or guesswork.

  6. Upload changes → run Modern-PBIR preflight before pack in management.md, then powerbi-report-author pack ./MyReport.Report --raw --out update-definition.json → POST /reports/{id}/updateDefinition with --body @update-definition.json → persist verbose headers to a named log, capture x-ms-operation-id, and poll the LRO; pack emits ALL parts (modified + unmodified)

  7. Clean up → Delete all temporary local files and directories created during the workflow

Creating a new report in Fabric
  1. Authenticate → see COMMON-CLI.md § Authentication Recipes (see ../../../common/COMMON-CLI.md, section authentication-recipes)

  2. Find workspace → Resolve workspace ID by name

  3. Resolve semantic model → Find the semantic model ID and workspace name for the definition.pbir connection string

  4. Verify semantic-model bindings → Download the target semantic model definition (TMDL) and compare all PBIR Entity, queryRef, nativeQueryRef, and filter references against the target table/column names. If names differ but structure matches, remap all table-qualified bindings. If models are structurally different, prompt the user before proceeding — explain what doesn't match and ask whether to re-author the affected bindings

  5. Author PBIR content → Use the authoring mode to generate the complete PBIR definition from scratch — definition.pbir, report.json, version.json, pages.json, page configs, and all visuals. Never construct any PBIR JSON from memory or guesswork.

  6. Upload → choose a concrete non-empty display name first (for example REPORT_DISPLAY_NAME="My New Report"). Build create arguments with --display-name "$REPORT_DISPLAY_NAME" and add --description "$REPORT_DESCRIPTION" only when a non-empty description is intended; otherwise omit --description. Run Modern-PBIR preflight before pack in management.md, then powerbi-report-author pack ./MyReport.Report --raw --mode create --display-name "$REPORT_DISPLAY_NAME" [--description "$REPORT_DESCRIPTION"] --out create-report.json → POST /reports with --body @create-report.json → persist verbose headers to a named log, capture x-ms-operation-id, and poll the LRO; pack emits displayName and all definition parts

  7. Clean up → Delete temporary local files

Troubleshooting

ErrorCauseFix
401 UnauthorizedWrong or missing --resource audienceAlways pass --resource "https://api.fabric.microsoft.com"
403 ForbiddenInsufficient permissionsCheck workspace role (Contributor+ for write ops)
404 Not FoundWrong workspace or report IDRe-resolve IDs via List APIs
CorruptedPayloadMalformed base64 or invalid PBIR JSON, usually from unsupported manual hand-walkingInstall/upgrade powerbi-report-author >= 0.3.0 and use pack/unpack, which avoid manual base64 and path mistakes. Do not continue with fallback recipes from this skill.
202 with no resultLRO not polled to completionImplement LRO polling pattern
OperationNotSupportedForItemReport has encrypted sensitivity labelCannot get definition for encrypted reports
ItemDisplayNameAlreadyInUseDuplicate name in workspaceUse a unique display name
format: "PBIR-Legacy"Report was created before PBIR was defaultPBIR-Legacy is not supported by this skill
UNPACK_FORMAT_UNSUPPORTEDpowerbi-report-author unpack received PBIR-Legacy or another non-PBIR formatRe-run getDefinition?format=PBIR; if Fabric still returns PBIR-Legacy, stop — this skill only supports modern PBIR
Visuals empty / no data after publishPBIR entity names don't match workspace semantic model table names (e.g., local CSV table name vs workspace table name)Download target semantic model TMDL, compare table names, update all Entity, queryRef, nativeQueryRef, and filter references to match
MissingDefinitionParts on create/update even though all files are includedUnsupported manual hand-walking can emit backslashes in definition part paths (definition\report.json), but the Fabric API requires forward slashes. powerbi-report-author pack normalizes to forward slashes for you.Install/upgrade powerbi-report-author >= 0.3.0 and use pack; do not continue with manual fallback path walkers.
Duplicate reports appear in workspace after createCreate POST was retried after a 202 Accepted response. Each retry risks creating a new report.Never retry a create POST after 202. See Long-Running Operations (LRO) in management-part-02.md for reliable operation ID capture and recovery steps. Delete any duplicates with the Delete Report API.
Visuals empty after publishing a local .pbip via the model hand-offThe semantic-model authoring skill may rename or transform tables/columns during deploy, so the freshly deployed model's TMDL no longer matches the report's PBIR bindings.Re-run the TMDL-diff verification against the deployed model (per Verify semantic-model bindings after the target model is resolved in the MUST section of management-part-03.md) and remap drifted bindings via the authoring mode.
Visuals empty after publish, despite TMDL diff being cleandefinition.pbir byConnection still points at a stale model ID (e.g., from .pbi/ cache or an earlier publish), not the freshly resolved one.Re-run step 7 of Publishing a local .pbip to set byConnection to the actually resolved semanticModelId, then re-publish.
Semantic-model authoring skill not available when user wants to publish the local modelNo semantic-model authoring skill is loaded in the current session.Inform the user and degrade to the connect-to-existing branch — re-prompt for which workspace model to bind the report to. Do not silently fall through.
Model published to one workspace, report POSTed to anotherWorkspace was not confirmed up front, or two different workspaces were used for the model deploy and the report publish.Enforce the single-workspace rule (step 2 of Publishing a local .pbip). Recovery: either re-publish the report into the model's workspace, or move the model.

Requirements and compatibility

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Security

What our scanner noticed· Low risk

  • Phrasing that asks for actions without confirmation
  • Instructions that use the network

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Attribution and licence

Published by
Microsoft
Publisher
Microsoft (Official)
Source
microsoft/skills-for-fabric · skills/powerbi-report-cli · commit f8fac11
Licence
MIT License (redistribution allowed)
  • LICENSE (added by AutoGineer from LICENSE)
  • ATTRIBUTION.md (written by AutoGineer)
Synced
Also distributed in
microsoft/skills-for-fabric

AutoGineer is not affiliated with or endorsed by Microsoft.

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download powerbi-report-cli.zip