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/design/layout.md

Layout Composition

Contents

  • Core Principles

  • Reading Patterns

  • Grid System

    • 8-Point Base Grid

    • 12-Column Grid

    • Concrete Arithmetic (FHD 1920 x 1080 canvas)

  • Slicer Placement Rules

    • 1–3 slicers — inline with title

    • 4+ slicers — vertical filter rail

    • Bounds and overlap

  • Visual Hierarchy Levers

  • Whitespace Tiers

  • Space Allocation Rules

    • Composition Templates

  • Power BI Grounding

Core Principles

  1. Top-left carries the heaviest message — Readers start there; place the descriptive title, primary KPI callout, or hero chart there.

  2. Align to a grid — Every edge snaps to an 8px grid; misalignment signals carelessness.

  3. Whitespace is structure — Gaps separate groups more effectively than borders or boxes.

  4. Size + contrast + position = hierarchy — Largest, highest-contrast element in the best position gets attention first.

  5. Group by proximity, not by boxes — Elements 8–16px apart read as related; ≥32px apart read as distinct (Gestalt).

  6. 7 ± 2 visual groups per page — More overwhelms working memory; fewer may under-inform.

  7. Repetition creates rhythm — Consistent sizing, spacing, and placement across pages builds trust and scannability.


Reading Patterns

PatternShapeWhen to UseArchetype Fit
F-patternLeft-anchored, top-heavy scanningDense analytical pages, tables, filter railsAnalytical, Operational
Z-patternTop-left → top-right → bottom-left → bottom-rightSparse executive summaries, narrative pagesExecutive, Narrative

F-pattern works when the left column holds navigation (slicers, filter rail) and the eye scans rightward into content. Z-pattern works when the page has a clear headline, a hero visual, and a small number of supporting elements.


Grid System

8-Point Base Grid

All spacing, sizing, and positioning use multiples of 8px.

ValuePixelsUse
1 unit8Minimum internal padding
2 units16Tight spacing between visuals in a group
3 units24Standard spacing between groups, page margins
4 units32Section breaks, major separations
6 units48Banner height, header strip
12-Column Grid

Greenfield reports default to FHD (1920 x 1080) unless the user asks for a different size. Brownfield redesigns preserve the existing canvas size unless a resize is approved.

Use a 12-track grid inside the page margins. On FHD, subtract 32px margins on each side (1856px usable), then use 24px gutters between tracks. This leaves 1592px for 12 equal tracks, or ~132.7px per track. A visual spanning N tracks is (N * 132.7) + ((N - 1) * 24), then rounded to the 8px grid during placement. On existing 1280px canvases, use 24px side margins and compact gutters (usually 16px), or express placements as ratios instead of copying FHD pixel widths. For multi-span rows, add one gutter between adjacent visuals; for example, an 8 + 4 split is ~1229px + 24px gutter + ~603px.

LayoutColumnsSpan Width (before final 8px rounding)Use
Full width12~1856 FHD / ~1232 720pHero chart, full-width table
Two-thirds + one-third8 + 4~1229 + ~603 FHDPrimary chart + slicer panel
Half + half6 + 6~916 + ~916 FHDSide-by-side comparison
Asymmetric 7-57 + 5~1072 + ~760 FHDNarrative: hero chart + annotation
Asymmetric 8-48 + 4~1229 + ~603 FHDAnalytical: chart + detail panel
Thirds4 + 4 + 4~603 each FHDKPI cards row, small multiples
Quarters3 + 3 + 3 + 3~446 each FHD4-up status tiles
Concrete Arithmetic (FHD 1920 x 1080 canvas)
Canvas:       1920 x 1080
Margins:      32px each side -> usable 1856 x 1016
Header:       72px tall -> content area 1856 x 944
Footer:       optional; do not reserve a footer band unless it has content

Slicer Placement Rules

Choose slicer placement by count — fewer slicers go inline with the title to preserve full chart width.

Slicer countPlacementWidth impact
1–3Inline with title rowZero — cards and charts span full content width
4+Vertical filter rail, usually 2 grid columnsF-pattern; slicers fill the column

Key rule: a vertical rail is only justified when slicers fill ≥50% of the column height. A short list of three dropdown slicers usually leaves too much dead space in a full-height rail, so keep them inline with the title.

1–3 slicers — inline with title

Place slicers at the right end of the title row. Each slicer gets about 12% of page width (about 230px on FHD, 160px on 1280px pages; use about 10% for short labels like "Year"), h=64 on FHD or h=56 on 1280px pages, spaced 16-24px apart. The title textbox fills the remaining width on the left. Reserve the entire title/slicer band before placing any chart/card/table below it; the reserved band still belongs to the title first, with slicers aligned to the right. If a slicer must be taller than the standard header-band height, increase the reserved band; do not let the next row start under the slicer. Z-order cannot fix a bad layout — it only decides which overlapping visual hides the other.

┌──────────────────────────────┬──────────┬──────────┬──────────┐
│  TITLE                       │ Slicer 1 │ Slicer 2 │ Slicer 3 │
├──────────┬──────────┬────────┴──┬───────┴──────────┴──────────┤
│ Card 1   │ Card 2   │ Card 3   │ Card 4                      │  full width
└──────────┴──────────┴──────────┴──────────────────────────────┘
4+ slicers — vertical filter rail

The canonical F-pattern layout. Rail is usually 2 grid columns wide: about 310px on FHD and about 206px on 1280px brownfield pages. Content area occupies the remaining width. See archetypes/analytical-canvas.md for the full template.

Bounds and overlap
  • No visual bounding boxes may overlap unless the overlap is deliberate and non-data-bearing (for example, a background shape behind a group).

  • Slicers are interactive controls, so they must be fully visible in screenshots; their lower portions must not sit behind charts/tables.

  • Compute each visual's right = x + width and bottom = y + height; sibling visuals in the same layer must have either a horizontal or vertical gap.

  • Keep at least 16px between grouped visuals and 24px between major sections.


Visual Hierarchy Levers

LeverHow to ApplyRule
SizeHero visual is largest only when the page has a true hero question; otherwise balance halves/thirdsSize should reflect analytical priority, not default habit
ContrastDark/saturated on light canvasHigh contrast = primary; low contrast = context
PositionTop-left = #1 priority; center = hero; bottom-right = least priorityFollows natural reading order
Rule of thirdsPlace focal point at intersection of thirds grid linesCreates dynamic, non-centered compositions
Gestalt proximity8–16px gap = "these belong together"32px+ gap = "these are separate groups"
EnclosureLight background fill to group (use sparingly)Only when proximity alone is ambiguous

Whitespace Tiers

TierPixelsUse
Tight16Between visuals within the same logical group
Normal24Between groups, page edge margins
Section32Between major page sections (header/body, body/footer)

Rule: pick one tier for intra-group and one for inter-group. Never mix three spacing values within a single row of visuals.


Space Allocation Rules

Use the layout_contract.space_audit from design-brief.md before handoff. The goal is not to pack every pixel, but to prevent dead bands and unreadable supporting visuals.

  • Do not define a region unless a placement uses it, except named structural regions such as spacer_*, divider_*, or bg_* with a non-data placement.

  • Analytical, operational, and comparative pages should leave no more than 15% of content cells empty. Executive and narrative pages may leave up to 20% when the whitespace supports the story.

  • Supporting chart regions are a floor of 3 columns x 3 rows; dense labels, legends, and small multiples need 4+ columns or 4+ rows.

  • Tables need at least 4 grid rows unless they are compact top-N spotlights.

  • KPI/card strips should use 2 grid rows on standard report pages so values can show context labels or reference labels.

  • A single non-hero region should not swallow the page. If one region exceeds 45% of content cells on a page with 4+ data visuals, the brief must explain why it is the hero and how the remaining visuals stay readable.

  • Do not let a bare single-value cardVisual become the hero/largest region. Its visual footprint should match its information density: compact KPI strip, status tile, or side callout. Reserve large hero regions for charts/tables/maps that explain change, ranking, distribution, exceptions, or drivers. A KPI hero must be a composite treatment with context (delta/reference label, sparkline, threshold band, annotation, or nearby explanatory chart).


Composition Templates

Each archetype file ships 2–3 layout variants (A / B / C) with a selection table keyed on data signals. Read the archetype reference for your page type, walk the selection table, and pick the variant the data calls for — do NOT default to variant A out of habit:

  • archetypes/executive-summary.md — A. Hero-Right · B. KPI-Strip · C. Headline-Hero

  • archetypes/analytical-canvas.md — A. Filter-Rail · B. Inline-Slicers · C. Small-Multiples-Grid

  • archetypes/operational-monitor.md — A. 4-Up Status · B. Wallboard · C. Incident-First

  • archetypes/narrative-story.md — A. 7/5 Split · B. Single-Column-Scroll · C. Annotated-Hero

  • archetypes/comparative-benchmark.md — A. Side-by-Side · B. Stacked-Pairs · C. Slope-Graph-First


Power BI Grounding

PropertyKey / LocationNotes
Page sizepage.width, page.heightGreenfield default 1920×1080; preserve existing size for brownfield unless resize is approved
Visual positionposition.x, position.ySnap to multiples of 8
Visual sizeposition.width, position.heightSnap to multiples of 8
Z-orderposition.zIncrement by 1000 for layering headroom
Tab ordertabOrderMust match visual reading order for accessibility
Bounds constraint—No visual may extend beyond page width/height
Page backgroundwallpaper / backgroundKeep white or near-white

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

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