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://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/authoring/authoring-workflows.md

Authoring Workflows & Examples

Read this for concrete PBIR authoring workflows: pages, visuals, layout templates, themes, drillthrough, interactions, and visual-type routing.

Related references:

  • formatting.md (see formatting.md) — value encoding, colors, selectors, VCOs, and formatting properties.

  • expressions.md (see expressions.md) — field expressions, filters, and sort definitions.

Mandatory completion gate: Every workflow in this file that creates or changes rendered report content must end with validation, loading the latest PBIR into a preview host, screenshot capture of every affected page, and review using screenshot-review.md (see screenshot-review.md). Use --all-pages for report-wide changes such as themes or global formatting. Load/reload and screenshot are separate commands; never combine --reload and --screenshot. A successful powerbi-report-author validate result must be followed by loading the validated PBIR, capturing screenshots of every affected page, and reviewing those screenshots; schema validation alone never completes a workflow. If any of those steps cannot be completed using the latest PBIR, report screenshot validation as blocked and do not claim the authoring task is complete.

Before editing existing reports: inventory the report with powerbi-report-author preview-pages <path-to-.Report-dir> and powerbi-report-author preview-visuals <path-to-.Report-dir>. Add --with-derived when you need counts or cheap computed flags.

Examples are structural patterns. Property names may vary by visual type. Always confirm exact properties with powerbi-report-author formatting describe-object <type> <object> before applying formatting.

Contents

  • Names & Format Versions

  • Add a New Page

  • Add a Visual to a Page

  • Common Layout Templates

  • Change Theme

  • Visual Type References

  • Drillthrough Page

  • Same-Report Drillthrough Workflow

  • Visual Interactions

Names & Format Versions

ID Generation
ElementFormatScope
Visual name20 lowercase hex chars (e.g. f4214b297bb2c1e49dfe)Unique within a page
Page nameModern: bare 20 hex chars. Traditional: ReportSection + 24 hex chars. The first page may be just ReportSection (no suffix).Unique across the report
Filter nameFilter + 24 lowercase hex chars (e.g. Filter1a2b3c4d5e6f7890a1b2c3d4)Unique across the entire report definition — powerbi-report-author validate flags duplicates with PBIR_FILTER_NAME_DUPLICATE_*
// Node.js
const crypto = require('crypto');
const visualId = crypto.randomBytes(10).toString('hex');                  // 20 hex chars
const pageId   = 'ReportSection' + crypto.randomBytes(12).toString('hex'); // ReportSection + 24 hex
const filterId = 'Filter'        + crypto.randomBytes(12).toString('hex'); // Filter + 24 hex
Format Versions

These are file-content versions (not $schema URLs) and are constants for the current PBIR format:

  • version.json → "version": "2.0.0"

  • definition.pbir → "version": "4.0"

For $schema URL versioning rules and the file layout, see SKILL.md § PBIR File Layout (see ../authoring-part-02.md, section pbir-file-layout). When creating a new file of any type, copy the $schema URL from an existing file of the same type in the same report.

Add a New Page

  1. Generate a unique page name (e.g. ReportSection + 24 hex chars)

  2. Create the directory: definition/pages/<pageName>/

  3. Create page.json:

    {
      "$schema": "https://developer.microsoft.com/json-schemas/fabric/item/report/definition/page/2.1.0/schema.json",
      "name": "<pageName>",
      "displayName": "My New Page",
      "displayOption": "FitToPage",
      "height": 720,
      "width": 1280
    }
  4. Create visuals/ subdirectory (can be empty initially)

  5. Add the page name to pages.json → pageOrder array at the desired position

Note: For the $schema URL, copy from an existing page.json in the same report.

Add a Visual to a Page

  1. Generate a unique visual name (20 hex chars)

  2. Create definition/pages/<pageName>/visuals/<visualName>/visual.json

  3. Populate with the visual definition:

    {
      "$schema": "https://developer.microsoft.com/json-schemas/fabric/item/report/definition/visualContainer/2.9.0/schema.json",
      "name": "<visualName>",
      "position": {
        "x": 0, "y": 0, "z": 1000,
        "height": 300, "width": 400,
        "tabOrder": 1000
      },
      "visual": {
        "visualType": "<type>",
        "query": {
          "queryState": {
            "<RoleName>": {
              "projections": [
                {
                  "field": { /* expression — see references/authoring/expressions.md */ },
                  "queryRef": "<Entity>.<Property>",
                  "nativeQueryRef": "<Property>"
                }
              ]
            }
          }
        }
      }
    }

⚠️ All role projections (Rows, Columns, Values, etc.) must be inside queryState, not directly under query. Placing them under query causes a schema validation error.

Position guidelines (1280×720 canvas):

  • z: Stacking order. Higher = on top. Increment by 1000 for each visual.

  • tabOrder: Keyboard navigation order. Usually matches z.

  • Keep visuals within canvas bounds: x + width ≤ 1280, y + height ≤ 720.

Common Layout Templates

Full-width KPI row + detail chart (720px canvas example):

KPI Card 1:  x=20,  y=20,  w=290, h=82
KPI Card 2:  x=330, y=20,  w=290, h=82
KPI Card 3:  x=640, y=20,  w=290, h=82
KPI Card 4:  x=950, y=20,  w=290, h=82
Main Chart:  x=20,  y=118, w=1240, h=582

Card heights follow the card sizing formula (see card-part-02.md, section card-sizing-required) — derive per canvas, don't hardcode.

2×2 Grid:

Top-Left:     x=20,  y=20,  w=610, h=340
Top-Right:    x=650, y=20,  w=610, h=340
Bottom-Left:  x=20,  y=380, w=610, h=320
Bottom-Right: x=650, y=380, w=610, h=320

Header + sidebar + main:

Header:   x=0,   y=0,   w=1280, h=80
Sidebar:  x=0,   y=80,  w=280,  h=640
Main:     x=300, y=80,  w=960,  h=640

Change Theme

In report.json, update the themeCollection.customTheme:

{
  "customTheme": {
    "name": "<CustomThemeName>-<guid>.json",
    "reportVersionAtImport": {
      "visual": "2.6.0",
      "report": "3.1.0",
      "page": "2.3.0"
    },
    "type": "RegisteredResources"
  }
}

Also ensure the theme file exists in StaticResources/RegisteredResources/ and is listed in the resourcePackages array with matching name and path.

On every theme edit, follow the GUID cache-busting procedure in theming.md (see theming.md, section theme-name-guid-convention-cache-busting) — rotate the GUID suffix (keep <CustomThemeName> stable), update all report.json references, and rerun the host-specific workflow in preview.md (see preview.md). Only change <CustomThemeName> if the user explicitly requests a rename.

⚠️ type must be "RegisteredResources" — not "SharedResources". Using the wrong type causes the theme to silently fail.

Inside report.json, both customTheme.name and the matching resourcePackages[].items[].name MUST include the .json extension and equal the item's path (e.g., all three are "<ThemeName>.json"). Using the bare theme name causes the published report to incorrectly apply the theme on Power BI service. The name field inside the theme JSON file itself stays as the bare theme name (no .json suffix). See theming.md for details.

Visual Type References

Use these focused references for visual-specific templates, formatting rules, and known rendering pitfalls.

IntentRead
Bar, column, and line chartscartesian.md (see cartesian.md)
Cards (cardVisual)card.md (see card.md)
KPI visual (kpi)kpi.md (see kpi.md)
Tables and matricestable.md (see table.md)
Slicers and slicer selectionsslicers.md (see slicers.md)
Image visualsimage.md (see image.md)
Shapes, dividers, and containersshape.md (see shape.md)
Mapsmap.md (see map.md)
Static or dynamic textboxestextbox.md (see textbox.md)

Drillthrough Page

A drillthrough page adds pageBinding and drillthrough filters to page.json:

{
  "$schema": "https://developer.microsoft.com/json-schemas/fabric/item/report/definition/page/2.1.0/schema.json",
  "name": "<pageName>",
  "displayName": "Detail Drillthrough",
  "displayOption": "FitToPage",
  "height": 720,
  "width": 1280,
  "filterConfig": {
    "filters": [
      {
        "name": "Filter<24hex>",
        "field": {
          "Column": {
            "Expression": { "SourceRef": { "Entity": "<Table>" } },
            "Property": "<DrillthroughColumn>"
          }
        },
        "type": "Categorical",
        "howCreated": "Drillthrough"
      }
    ]
  },
  "pageBinding": {
    "name": "Pod",
    "type": "Drillthrough",
    "parameters": [
      {
        "name": "Param_Filter<24hex>",
        "boundFilter": "Filter<24hex>",
        "fieldExpr": {
          "Column": {
            "Expression": { "SourceRef": { "Entity": "<Table>" } },
            "Property": "<DrillthroughColumn>"
          }
        }
      }
    ]
  }
}

Key points:

  • Each drillthrough field needs both a filter entry (with "howCreated": "Drillthrough") and a matching pageBinding.parameters entry with boundFilter referencing the filter name.

  • The pageBinding.name is typically "Pod".

  • pageBinding.type is "Drillthrough" (or "Tooltip" for tooltip pages).

  • To trigger a drillthrough (or any page navigation, bookmark, or slicer action) from a button, see the Drillthrough button pattern (see button-part-03.md, section drillthrough-button). The button enables only when a selected data point carries the drillthrough field; a slicer selection alone does not enable it.

  • For bookmark files, saved page/visual/filter state, groups, show/hide patterns, and bookmark verification, see bookmark.md (see bookmark.md).

Same-Report Drillthrough Workflow

A same-report drillthrough opens the target page with filter context from a selected data point in a source visual:

  1. Choose the drillthrough field and ensure the source visual projects it.

  2. Create the target page and add a page filter marked "howCreated": "Drillthrough".

  3. Add pageBinding.type: "Drillthrough" with a parameter whose boundFilter references that filter and whose fieldExpr matches it.

  4. Add the target visuals and the required Back button (see button-part-03.md, section back-button).

  5. Use the source visual's drillthrough menu, or add a Drillthrough button (see button-part-03.md, section drillthrough-button) when the report needs an explicit action.

  6. Validate and reload the report, select a source data point carrying the field, navigate to the target, and confirm the filter context and Back action.

Visual Interactions

Control how visuals cross-filter/highlight each other on a page. Add visualInteractions array to page.json:

{
  "visualInteractions": [
    {
      "source": "<sourceVisualName>",
      "target": "<targetVisualName>",
      "type": "NoFilter"
    }
  ]
}
TypeEffect
"NoFilter"Source visual does NOT filter target
"DataFilter"Source cross-filters target (shows subset)
"HighlightFilter"Source highlights matching data in target

By default (no entry), visuals cross-filter each other. Only add entries to override the default behavior.

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 or Microsoft.

Download ZIP

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