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/design/archetypes/narrative-story.md

Narrative / Data Story

Contents

  • Job To Be Done

  • Core Principles

  • Structural Patterns (Segel & Heer)

    • Decision Table: Which Pattern?

  • Layout Variants

    • Variant A — 7/5 Split (default, balanced argument)

    • Variant B — Single-Column-Scroll

    • Variant C — Annotated-Hero

  • Chart Selection

    • Choosing the Anchor Chart

    • Do NOT Use

  • Annotation Techniques

    • Annotation Z-Order

  • Color & Typography

    • Highlight + Grey Context Palette

    • Typography

  • Interaction Design

    • Do NOT Use on Narrative Pages

  • PBI Formatting Reference

    • Text & Annotation Visuals

    • Navigation

    • Narrative Intelligence

    • Page-Level

  • Decision Checklist

Archetype: Narrative / Data Story Theme: for generated reports, preserve references/design/assets/base.json safeguards while adapting dataColors to domain; for brownfield, preserve the existing theme unless a theme swap is requested Canvas: greenfield default FHD 1920 x 1080; preserve existing size for brownfield unless resize is approved · 7/5 asymmetric layout Success metric: Reader can restate the argument in one sentence


Job To Be Done

DimensionValue
Primary userBoard member, senior stakeholder, external audience
Session triggerCFO presents: "Revenue missed $42M. Here are three drivers. Here's the plan."
ModeAuthor-driven argument; reader is convinced, not exploring
StructureMulti-page, paced, annotation-rich
Success metricReader restates the argument in one sentence
Failure signalReader asks "so what?" after viewing the page
Design implicationMinimal interactivity; content is curated, not generated on the fly

Core Principles

#PrincipleRationale
1Thesis in the title"Q3 revenue missed $42M, driven by EMEA enterprise" — not "Revenue Overview"
2Annotations carry the argumentArrows, callouts, reference lines, shaded periods do the explaining
3One anchor chart per pageSingle visual that proves the page's thesis
4Reveal pacingBookmarks or page sequence control what reader sees when
5Highlight + grey contextHero data in brand color, everything else grey
6Reader interactivity minimalNo slicers on main narrative path
7Chart chosen for the pointSlope for rank change, waterfall for bridge, dumbbell for before/after

Structural Patterns (Segel & Heer)

PatternFlowPBI implementation
Martini glassLinear narrative → open exploration at endPages 1–N guided; final page has slicers + filters
Interactive slideshowLinear steps with optional side tripspageNavigator + drill-through from each step
Drill-down storyHub page with spoke detail pagesHub has actionButton links to each spoke
Decision Table: Which Pattern?
If the story…UseBecause
Has a single linear argumentMartini glassReader follows one path to conclusion + can explore
Has parallel threads (3 drivers)Interactive slideshowReader can branch to any driver
Centers on one entity with many facetsDrill-down storyHub gives overview; spokes give depth

Layout Variants

Pick ONE variant based on the story's structure from Step 0. Do NOT mix. Default to A only when signals genuinely tie — record the signal that drove your pick in variant_rationale.

Signal (from story structure + brief)Variant
Single anchor chart with a side annotation panel; balanced "show + tell"A. 7/5 Split
Multiple short narrative beats stacked vertically; reader scrolls/pagesB. Single-Column-Scroll
One dominant chart that argues the whole point; annotations on the chart itselfC. Annotated-Hero

Variant A — 7/5 Split (default, balanced argument)

Anchor chart on the left (7/12 width), annotation panel on the right (5/12 width), body text below. Classic "show on the left, tell on the right".

┌──────────────────────────────────────────────────────────┐
│  PAGE TITLE: thesis sentence (28-32pt)                   │  h=56
│  subtitle: context / date range (14pt)                   │
├──────────────────────────────┬───────────────────────────┤
│                              │                           │
│  ANCHOR CHART                │  ANNOTATION PANEL         │
│  (7/12 width)                │  (5/12 width)             │  h=340
│                              │  • callout boxes          │
│  Hero in brand color         │  • arrows to chart        │
│  Rest in grey                │  • key numbers            │
│                              │                           │
├──────────────────────────────┴───────────────────────────┤
│  BODY TEXT                                               │
│  What the chart shows → Why it matters → So what / action│  h=160
│  (11-12pt, ~1.4 line height)                             │
├──────────────────────────────────────────────────────────┤
│  [← Prev]                                    [Next →]    │  h=48
└──────────────────────────────────────────────────────────┘
ZoneHeightContent
Title block56 pxThesis sentence + subtitle
Chart + annotations340 px7/12 anchor chart + 5/12 annotation panel
Body text160 pxNarrative: shows → matters → so-what
Navigation48 pxPrev / Next buttons (or page navigator)

Variant B — Single-Column-Scroll

Vertical narrative beats stacked top to bottom, each one a small chart + paragraph. Use when the story has 3–5 sequential points that each deserve their own frame.

┌──────────────────────────────────────────────────────────┐
│  PAGE TITLE: thesis sentence (28-32pt)                   │  h=56
├──────────────────────────────────────────────────────────┤
│  BEAT 1 — sub-thesis (16pt SemiBold)                     │
│  ┌──────────────────────┐  Body: ~3 sentences explaining │  h=160
│  │  small chart 480w    │  what the chart shows and why  │
│  └──────────────────────┘  it advances the argument.     │
├──────────────────────────────────────────────────────────┤
│  BEAT 2 — sub-thesis                                     │
│  ┌──────────────────────┐  Body text continuing the      │  h=160
│  │  small chart 480w    │  narrative.                    │
│  └──────────────────────┘                                │
├──────────────────────────────────────────────────────────┤
│  BEAT 3 — sub-thesis                                     │
│  ┌──────────────────────┐  Body text — closing argument  │  h=160
│  │  small chart 480w    │  or call to action.            │
│  └──────────────────────┘                                │
├──────────────────────────────────────────────────────────┤
│  [← Prev]                                    [Next →]    │  h=48
└──────────────────────────────────────────────────────────┘
ZoneHeightContent
Title block56 pxThesis sentence
Beat 1–3160 px eachSub-thesis + small chart (left ~480px) + body text (right)
Navigation48 pxPrev / Next buttons

Each beat is self-contained — the reader can stop after any beat with a complete thought. Maximum 3 beats per page; beyond that, split to a new page in the sequence.


Variant C — Annotated-Hero

A single dominant chart fills most of the canvas. All explanation lives on the chart itself: arrows, callout boxes, shaded regions, reference lines. Use when the chart's shape IS the argument.

┌──────────────────────────────────────────────────────────┐
│  PAGE TITLE: thesis sentence (28-32pt)                   │  h=56
├──────────────────────────────────────────────────────────┤
│                                                          │
│   HERO CHART — full width                                │
│                                                          │
│   ┌─ shaded period: "promotion" ─┐                       │  h=480
│   │  ~∿~∿~∿~∿~ ↗ "+18% lift"    │                       │
│   │  ~∿~∿~/                     │  ← arrow + callout    │
│   │     ↑ inflection             │                       │
│   │     "Aug launch"             │                       │
│   └──────────────────────────────┘  ── reference line ── │
│                                                          │
├──────────────────────────────────────────────────────────┤
│  CALLOUT — one-sentence interpretation                   │  h=80
├──────────────────────────────────────────────────────────┤
│  [← Prev]                                    [Next →]    │  h=48
└──────────────────────────────────────────────────────────┘
ZoneHeightContent
Title block56 pxThesis sentence
Hero chart480 pxSingle chart with on-chart annotations: arrows, callouts, shaded periods, reference lines
Callout80 pxTextbox: one-sentence interpretation reinforcing the title
Navigation48 pxPrev / Next buttons

Annotation z-order: shaded regions back, chart middle, arrows + callouts front. Use the brand color for the data being argued and grey for everything else — preattentive highlight does the lifting.

Callouts must interpret the chart shape, threshold, anomaly, or period change. Do not use callout boxes for a bare metric that simply repeats the adjacent visual's measure.


Chart Selection

Choosing the Anchor Chart
If the point is…UseWhy
Trend over timelineChartPosition along common scale
Rank change between periodsSlope chart (simulated lineChart)Crossing lines show overtakes
Additive decompositionwaterfallChartBridge from start to end
Before / after comparisonDumbbell (simulated barChart)Gap = change magnitude
Part-to-whole at one momentStacked bar (single bar)Length encoding
Distribution of a metricHistogram (binned columnChart)Shape of distribution
Do NOT Use
Visual typeReason
Dense dashboards (> 3 visuals)Narrative has ONE anchor per page
Unannotated chartsWithout annotations, chart doesn't argue
Matrix with > 2 measuresToo analytical; belongs in canvas archetype
Slicer-heavy layoutsReader doesn't explore; author curates

Annotation Techniques

TechniquePBI implementationUse case
Arrow pointing to datashape with arrowhead property"This is the inflection point"
Callout text boxtextbox with filled backgroundKey number or quote
Reference lineaxis > referenceLineTarget, SLA, benchmark
Shaded regionbasicShape (low-opacity rectangle) behind chart via z-order"This period was promotional"
Preattentive highlightdataColors override: one series brand, rest greyFocus on the subject of the sentence
Direct data labelLabels on hero data point onlyCall out the exact value
Annotation Z-Order
LayerContent
BackShaded regions (basicShape, 10–20% opacity)
MiddleChart visual
FrontArrows, callout textboxes, direct labels

Color & Typography

Highlight + Grey Context Palette
RoleColorHex
Hero / subjectBrand primarydataColors[0] from theme
Context / other seriesGrey#9E9E9E to #BDBDBD
Annotation text backgroundLight fill#F5F5F5 at 90% opacity
Negative calloutSemantic red#D13438

Rule: Maximum two non-grey colors on any page. If three things need highlighting, the page has too many points.

Typography
ElementSizeWeightNotes
Page title (thesis)28–32 ptBoldMust be a complete sentence
Subtitle14 ptRegularDate range, context
Body prose11–12 ptRegular~1.4 line height; narrative is read
Annotation callout10 ptSemiBoldInside callout box
Axis labels9 ptRegularMinimal, unobtrusive
Footer / source9 ptLightBottom of page

Interaction Design

Interactivity is minimal and guided — the author controls pacing.

PatternPBI mechanismNotes
Page sequencepageNavigator or Prev/Next actionButtonLinear story flow
Staged revealsBookmarks triggered by actionButtonShow data progressively
"Next" affordanceButton always visible, labeled with next page's thesisReader knows what comes next
Page tooltipsSupporting detail on hoverDon't clutter the page
Smart NarrativeaiNarratives visualDrafts "what changed"; agent usually rewrites
Martini-glass bowlSlicers on final exploration page ONLYNot on narrative path
Do NOT Use on Narrative Pages
PatternWhy
SlicersAuthor controls the story, not the reader
Cross-filter websUnpredictable state changes break pacing
Drill-downReader might lose their place in the argument

Anti-patterns: see references/design/anti-patterns.md


PBI Formatting Reference

Text & Annotation Visuals
VisualKey propertiesPurpose
textboxFont, background fill, paddingThesis titles, body prose, callouts
shape / basicShapeFill, opacity, arrowhead, z-orderArrows, shaded regions, annotation backing
imageURL or embedded, alt textSupporting imagery (use sparingly)
Navigation
VisualKey propertiesPurpose
actionButtonAction: PageNavigation / Bookmark / DrillthroughPrev / Next / reveal
pageNavigatorStyle, positionLinear page flow
bookmarkNavigatorBookmark groupStaged reveal sequence
Narrative Intelligence
VisualKey propertiesPurpose
aiNarrativesSummarize key changesAuto-generated insight (agent rewrites)
Page-Level
Property pathValuePurpose
page > displayNameThesis sentence (abbreviated)Reads as TOC in page tabs
page > tooltip > tooltipTypeReportPageEnable custom tooltip pages
dataColors overrideBrand + greyHighlight + context palette
referenceLineTarget / benchmark valueDraw comparison baseline

Decision Checklist

#CheckPass?
1Every page title is a thesis sentence☐
2One anchor chart per page, annotated☐
3Body text explains: shows → matters → so-what☐
4Palette is highlight + grey (max 2 non-grey colors)☐
5Navigation (Prev/Next) always visible☐
6No slicers on narrative pages☐
7Annotations use arrows, callouts, or reference lines☐
8Page displayName reads as table of contents☐
9Story structure follows Segel & Heer pattern☐
10Reader can restate argument after viewing☐

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