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/visual-cookbook-part-02.md

Visual Design Cookbook - Part 2

Contents

  • Slicers

  • Temporal slicer decision matrix

  • Textbox (page titles, annotations)

  • Shape (shape)

  • Scatter (scatterChart)

  • Waterfall (waterfallChart)

  • Treemap (treemap)

  • Conditional Formatting — MANDATORY

Continuation of visual-cookbook.md. Open this file directly from the skill reference index.

Slicers

2-3 slicers per page maximum. Pick dimensions that control the most visuals on the page — if 3 charts use Weight Class and 2 use Year, those are your slicers. Avoid slicing by the same field on a chart's category axis.

Type selection:

DataTypevisualType
Categorical ≤10 valuesButton/tileadvancedSlicerVisual
Categorical 10-50ListlistSlicer
Categorical >50Dropdownslicer (mode: Dropdown)
Annual or period selectorDropdown or tileslicer (mode: Dropdown) or advancedSlicerVisual
True date rangeDate pickerslicer (mode: Between)
HierarchyTreelistSlicer
Temporal slicer decision matrix

Choose the slicer from the page question and data grain, not from the mere presence of a full-date column.

SignalRecommended slicerRationale
Executive page, annual grain, ≤10 yearsYear dropdown or year tileCompact, reliable, and matches scan-first behavior
User needs to compare discrete periods (e.g., 2020 vs 2023)Year/month dropdown with multi-selectBetween implies continuous ranges, not discrete comparisons
Month/quarter reporting with 12-36 periodsPeriod dropdown or relative dateKeeps the header compact while exposing current period
Analyst needs arbitrary day/month range explorationFull-date BetweenRange selection is the task
Date column is an integer key/text key or did not render as a date pickerDropdown on Year/PeriodBetween requires a renderable Date/DateTime field
Many dates but no need for arbitrary rangesRelative date or period dropdownAvoids oversized controls for low-value precision

Placement (choose by slicer count — see references/design/layout.md):

CountPositionLayout impact
1–3Inline with title row (right side)No width penalty — full chart width preserved
4+Vertical filter rail (200–240px left)F-pattern, justified when slicers fill the column

Never use a vertical rail for ≤3 slicers — it wastes 70%+ of the column height as dead space and unnecessarily narrows all content. Never place slicers in the top-left corner — that's for the page title.

Dropdown Slicer (slicer, mode: Dropdown)

The default choice — compact, searchable, handles any cardinality.

Sizing (proportional to canvas):

  • Height: follow the slicer sizing guidance in the authoring mode exactly; default dropdown is 60 + top_padding + bottom_padding, snapped to the 8px grid. Do not shrink to 48px or 8pt to make a tight layout work.

  • Width: ~12% of page width (about 230px on FHD, 160px on 1280×720). Use ~10% for short labels like "Year" or "Stance".

Two styling variants:

Standard (fill)Light (no fill)
BackgroundWhite #FFFFFFNone
Border#E8E8E8, radius=8#E8E8E8, radius=8
Use forTop strip, inline with cardsSidebar rail

Both share border radius=8 and color=#E8E8E8, matching card visuals.

Theme handles (via visualStyles.slicer in base.json):

  • header: body-lg font (10pt Semibold), outlineStyle=0 (no header border)

  • items: body font (9pt Regular), outlineStyle=0, padding=2

Per-visual must set:

  • header.text — display name ("Weight Class" not "weight_class_name")

  • data.mode — "Dropdown" (or Basic, Between, etc.)

  • VCO background, border, padding — for fill vs light variant

Date Between Slicer (slicer, mode: Between)

Use for temporal filtering only when arbitrary date-range exploration is part of the page question and the bound field is a renderable Date/DateTime column. For executive dashboards with yearly or quarterly grain, prefer a compact Year/Period dropdown or tile.

Sizing:

  • Inline with title: w=216; height is 60 + top_padding + bottom_padding, snapped to the 8px grid. Dates render side-by-side at this width.

  • Vertical rail: w=200; height is 84 + top_padding + bottom_padding because dates stack vertically at this width.

  • Authoring must use the exact slicer sizing formula from the authoring mode after theme/VCO padding is known.

Styling variants: same Fill and Light as Dropdown Slicer (see table above).

Theme handles (via visualStyles.slicer in base.json — shared with dropdown):

  • header: 10pt Semibold, outlineStyle=0

  • date: 9pt font for date picker text

Per-visual must set:

  • data.mode — "Between"

  • header.text — "Date Range" or similar

  • VCO background, border, padding — for fill vs light variant

When to prefer Dropdown/Tile over Between:

  • Executive or scan-first page with annual/quarterly grain

  • Integer/text year-month key or date picker did not render

  • User expects multi-select (e.g., compare 2020 vs 2023)

  • ≤30 distinct values where a list is scannable

Textbox (page titles, annotations)

When to use: Descriptive titles, section labels, body prose in narrative, footnotes.

Design rules:

  • Page title (H1): 20pt SemiBold, dark navy (#252423), top-left, width ≥600px

  • Section dividers: use shape (rectangle) not textbox — textbox has a ~24px minimum height

  • Annotations: 10-11pt Regular, positioned near the chart element they reference

  • Rich text: use paragraphs[].textRuns[] for inline bold, color, sizing

  • Dynamic text: bind to a measure for data-driven titles ("Revenue is {[Revenue]} this quarter")

  • Footer text: 8-9pt, muted grey (#605E5C), bottom of page, source + refresh timestamp

⚠️ Textbox height — avoid scrollbar: A scrollbar appears when the textbox height is too small for the font size. Use this formula:

h_min = max(18, ⌈fontSize_pt × 25/16⌉) + padding_top + padding_bottom
Font SizeMin Height (no padding)With 8+8 padding
10pt18px34px
14pt22px38px
20pt32px48px
24pt38px54px
28pt44px60px
  • Floor of 18px regardless of font size

  • VCO border adds ZERO pixels (rendered outside bounds)

  • Font family and bold/regular do NOT change the threshold

  • Set VCO padding to 0 if you want the tightest possible fit

PBIR note: paragraphs is a native JSON array — never stringify it

Shape (shape)

When to use: Decorative dividers, section backgrounds, annotation arrows, call-out boxes.

Design rules:

  • Divider line: rectangle, h=2, w=full page width, fill=#E0E0E0 — separates page sections

  • Section background: rounded rectangle, low opacity fill (#F5F5F5), z-ordered BEHIND the visuals it groups

  • Annotation arrow: use arrowhead geometry, point at the chart element being called out

  • Decorative shapes are acceptable when they support the report's tone; keep data-bearing areas legible

  • Shapes don't have a 24px minimum like textboxes — use them for thin dividers

Formatting notes: Shape visual uses id selectors (not metadata/scope). fill, outline, text, shadow, glow MUST have "selector": { "id": "default" }. The shape object (tileShape/geometry) needs NO selector.

Scatter (scatterChart)

When to use: Relationship between two continuous variables. Correlation, clusters, outliers.

Design rules:

  • X and Y axes: always labeled with measure name and unit

  • Bubble size role: use sparingly (3rd variable) — area encodes poorly (Stevens' law)

  • Data labels: show on outlier points only, not all (visual clutter)

  • Quadrant reference lines: add horizontal + vertical referenceLine to divide into performance quadrants

  • Color by category: use legend for identity, not for magnitude

  • Play axis: enable for time-lapse animation when a date dimension exists

Waterfall (waterfallChart)

When to use: Sequential additive contribution — how does a total build up from components? Variance bridges (start → adjustments → end).

Design rules:

  • Use the theme's sentiment colors for increase (good=#1AAB40) and decrease (bad=#D64554)

  • Total bar: distinct color (neutral blue #0072B2 or grey)

  • Data labels: always on — the reader needs the exact numbers

  • Category labels: name each step clearly

  • Connector lines: show to maintain the visual bridge

Treemap (treemap)

When to use: Part-to-whole when there are >10 categories. NOT for comparison (use bar chart).

Design rules:

  • Limit to 1 grouping level unless the hierarchy is the point

  • Color: use the categorical palette so each rectangle is distinct

  • Data labels: show category name + value/percentage inside each rectangle

  • Size encodes magnitude — the biggest rectangle is the dominant category

Conditional Formatting — MANDATORY

Use conditional formatting when it reinforces the page's main comparison, threshold, or exception pattern.

TechniqueUse onEffect
Per-series colorBar/column chartsEach category bar gets a distinct color when category identity matters
Threshold colorKPI cardsBackground or font color changes based on good/neutral/bad thresholds
Data barsTable numeric columnsIn-cell horizontal bars show magnitude at a glance
Icon setsTable status columnsPass/fail or good/warn/bad status becomes scannable
Color gradientMatrix cells, heatmapsMin→mid→max color scale reveals patterns
Highlight + greyAny chartOne series in accent color, rest in #BDBDBD — draws the eye to the insight

The "all bars same color" problem: single-series bar charts can render every bar with the same default color. If category contrast matters, specify per-category colors or a sequential gradient in the design brief and let authoring handle the mechanics.

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