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/design-brief-part-02.md

Design Brief Contract - Part 2

Contents

  • Page layout contract

    • Canvas

    • Grid regions

    • Space allocation and balance

    • Space allocation counterexamples

    • Header and slicer band

    • Placements

    • Date slicer example variants

  • Common region patterns

    • Executive Summary with inline slicers

    • Analytical Canvas with filter rail

    • Operational Monitor

  • Validation checklist

Continuation of design-brief.md. Open this file directly from the skill reference index.

Page layout contract

Each pages[] entry must include a layout_contract. Freeform wireframes or Markdown descriptions may appear as explanation, but they are not authoritative for geometry.

Canvas
FieldTypeDescription
widthintCanvas width in pixels. Greenfield reports default to 1920 (FHD) unless the user asks for another size.
heightintCanvas height in pixels. Greenfield reports default to 1080 (FHD) unless the user asks for another size.
marginintPage edge margin in pixels; usually 32 on FHD (24 on 1280 x 720 brownfield pages).
gutterintMinimum pixels between sibling visuals; usually 24 on FHD (16 on 1280 x 720 brownfield pages).
snapintCoordinate snap grid; use 8.

For brownfield work, preserve the existing canvas size unless the user approved a resize. Tooltip pages may use a smaller canvas such as 320 x 240, but still require the same region and placement checks.

Grid regions

Regions are named rectangular areas on a 12-column x 12-row grid. Coordinates use [col_start, row_start, col_end, row_end], 1-indexed and end-exclusive. For example, [1, 1, 13, 13] covers the full grid.

Rules:

  • Region names must describe page semantics: header, filters, kpis, hero, detail, slicer_rail; never r1 or box2.

  • Regions must not overlap unless the overlap is intentional and non-data bearing, such as a background shape behind a group.

  • Every placement must reference a defined region.

  • Every coordinate must stay within [1, 1, columns + 1, rows + 1].

  • The authoring step converts regions to pixels and snaps all resulting x, y, width, and height values to the snap grid.

Space allocation and balance

The grid must account for the whole page, not just avoid overlaps. Empty regions and oversized heroes are common failure modes: they make reports look unfinished and leave important visuals too small to read.

Required rules:

  • Every region in grid.regions must either have at least one placement or be deliberately named as non-data-bearing structure (spacer_*, bg_*, divider_*) and referenced by a non-data placement. Do not define empty footer, callout, detail, or legend regions as placeholders.

  • Include space_audit under every non-trivial page's layout_contract. The audit forces the design step to count occupied space before handoff.

  • Compute empty space against content cells: all grid cells minus reserved header/slicer band cells and minus justified filter-rail cells. For analytical, operational, and comparative pages, empty_cell_pct should be <= 15. For executive and narrative pages, <= 20 is acceptable. Higher values require an explicit narrative/brand rationale.

  • No contiguous empty band may be taller than one grid row unless it is a named spacer/divider region with a placement and rationale. Prefer pixel gutters for section breaks instead of reserving whole empty grid rows.

  • For pages with 4+ data visuals, no single non-hero data region should exceed 45% of content cells. A dominant hero region may exceed this only when the selected archetype variant explicitly calls for one and balance_rationale says why the supporting visuals remain readable.

  • For pages with 2-3 data visuals, balanced halves/thirds are usually better than one region swallowing the page. A single region over 55% of content cells needs hero rationale tied to the page question.

  • A bare single-value cardVisual must not be the page's largest or dominant hero region. Cards encode one number; oversized cards create low information density and starve richer visuals. Use cards in KPI strips, compact status tiles, or side callouts. A card-like hero is acceptable only as a composite KPI treatment with explicit context (delta/reference label, sparkline, threshold band, annotation, or paired explanatory chart) and a balance_rationale explaining why the tradeoff is worth it.

  • A side callout, context tile, smart narrative, or card-like annotation must add information not already carried by the neighboring chart/table. It needs a derived insight basis such as variance %, delta, rank shift, gap-to-benchmark, threshold exception, or dynamic narrative text. If the only available value is the same absolute measure plotted next to it, remove the callout or repurpose the region for richer evidence. Use Smart Narrative (aiNarratives) only when the callout must be a filter-responsive natural-language summary and the authoring mode has verified the formatting/query mechanics for the target report version; otherwise prefer a textbox bound to an explicit narrative measure or a compact KPI/context tile.

  • Supporting chart regions are a floor of 3 columns x 3 rows; use 4+ columns or 4+ rows for charts with dense labels, legends, or small multiples. Tables should receive at least 4 grid rows unless they are a compact top-N spotlight. KPI/card strips should be 2 grid rows on standard report pages so cards can show value plus context.

space_audit shape:

space_audit:
  content_cell_count: <grid cells after excluding reserved header/slicer/rail>
  placed_cell_count: <cells covered by regions with placements>
  empty_cell_pct: <0-100>
  unplaced_regions: []
  largest_region:
    name: <region name>
    pct_of_content: <0-100>
  balance_rationale: <why region sizes match the page's analytical priorities>
Space allocation counterexamples

Counter-example to fix before handoff:

regions:
  header: [1, 1, 9, 2]
  filters: [9, 1, 13, 2]
  kpis: [1, 2, 13, 4]
  trend: [1, 4, 7, 9]
  ranking: [7, 4, 13, 9]
  footer: [1, 11, 13, 13]   # no placement references this region

Rows 9-11 are a dead band and footer is unplaced. Fix by expanding trend/ranking to row 10 and moving a real detail table, source note, or navigation/footer placement into the remaining row; otherwise remove the footer region and let the occupied regions fill the content area.

Counter-example to fix before handoff:

regions:
  header: [1, 1, 13, 2]
  hero:   [1, 2, 13, 8]   # largest region
  detail: [1, 8, 13, 13]
placements:
  - id: total_revenue
    region: hero
    kind: cardVisual       # one measure, no delta/sparkline/threshold context
    field_bindings: Sales[Revenue]
space_audit:
  largest_region: { name: hero, pct_of_content: 50 }
  balance_rationale: "Revenue is important."

The card wastes half the content area to show one number. Fix by moving total_revenue into a 2-row KPI strip or side callout and assigning the hero region to the explanatory trend, ranked driver chart, variance chart, map, decomposition visual, or detail table that proves the headline. If the page truly needs a KPI hero, make it a composite KPI treatment and say so in balance_rationale.

Header and slicer band

Every standard report page must reserve a title/header band before content regions begin.

Required rules:

  • Include exactly one placement with id: page_title, kind: textbox, and non-empty text.

  • The page title must be a descriptive insight title, not a generic label such as "Overview" or "Dashboard".

  • For 1-3 slicers, place slicers inline in a right-aligned filters region that shares the reserved header band with the title. The title remains the left anchor.

  • For more slicers, or for archetype variants that intentionally expose a larger filter set, use a side slicer_rail/rail region and start content to the right of that rail.

  • No chart, card, table, map, or data visual may start under a slicer region. Raising z-order is not a fix for overlap.

Placements

Each placement assigns one authorable object to one region.

FieldRequiredDescription
idyesStable unique identifier for the object.
regionyesRegion name from layout_contract.grid.regions.
kindyesPBIR visual type or object kind (textbox, slicer, cardVisual, barChart, lineChart, tableEx, azureMap, aiNarratives, etc.).
textfor textbox titlesRequired for page_title; recommended for annotations.
slot / ofwhen sharing1-indexed subdivision within a shared region.
purposedata visualsOne analytical question the visual answers.
field_bindingsdata visuals and slicersTable[Column], Table[Measure], or role map.
slicer_typeslicersbetween, dropdown, list, or another authorable slicer style.
sort_policybar/column/table visualsvalue_desc, value_asc, category_asc, natural_order, or none.
color_strategycolor-bearing visualsmeasure_match, gradient, unique, semantic, or none.
insight_basiscallouts, annotations, Smart Narrative, KPI contextThe derived comparison, threshold, rank, anomaly, or dynamic text that makes the element worth its space.
comparison_basiscomparative visuals and calloutsBaseline being compared: prior period, plan, target, peer median, selected entity, etc.
callout_value_basisside callouts / context tilesSpecific evidence that prevents a callout from duplicating an adjacent chart's absolute measure.

When multiple visuals share a region, slot and of divide the region along its longer axis. A placement with no slot fills its region.

Date slicer example variants

Executive and annual-grain pages should usually use a compact Year dropdown or tile slicer:

- id: year_slicer
  region: filters
  kind: slicer
  field_bindings: Date[CalendarYear]
  slicer_type: dropdown

Use a full-date between slicer only when the page needs day/month range exploration and the bound field is a renderable Date/DateTime column:

- id: date_range_slicer
  region: filters
  kind: slicer
  field_bindings: Date[FullDate]
  slicer_type: between
  insight_basis: "Users compare arbitrary date ranges, not just years."

Common region patterns

Executive Summary with inline slicers
regions:
  header:  [1,  1,  9,  2]
  filters: [9,  1, 13,  2]
  kpis:    [1,  2, 13,  4]
  trend:   [1,  4,  7,  9]
  hero:    [7,  4, 13,  9]
  detail:  [1,  9, 13, 13]
space_audit:
  content_cell_count: 132
  placed_cell_count: 132
  empty_cell_pct: 0
  unplaced_regions: []
  largest_region: { name: detail, pct_of_content: 36 }
  balance_rationale: "KPI strip, two balanced analysis panels, and detail row fill the content area without an unused footer."
Analytical Canvas with filter rail
regions:
  header: [1,  1, 13,  2]
  rail:   [1,  2,  3, 13]
  hero:   [3,  2, 13,  7]
  charts: [3,  7, 13, 10]
  detail: [3, 10, 13, 13]
Operational Monitor
regions:
  header: [1,  1, 13,  2]
  kpis:   [1,  2, 13,  4]
  tl:     [1,  4,  7,  8]
  tr:     [7,  4, 13,  8]
  bl:     [1,  8,  7, 13]
  br:     [7,  8, 13, 13]

Validation checklist

Before handoff, fix any failure:

  • [ ] generated_by: powerbi-report-cli and contract_version are present.

  • [ ] Every non-trivial page has layout_contract.canvas, layout_contract.grid.regions, and layout_contract.placements.

  • [ ] Every page has a page_title placement with non-empty title text.

  • [ ] Every placement references a defined region.

  • [ ] Regions do not overlap unintentionally.

  • [ ] Every non-spacer region has at least one placement.

  • [ ] Slicers are in filters, rail, or slicer_rail regions, never in the top-left title anchor.

  • [ ] Data visuals do not start under header-band slicer regions.

  • [ ] space_audit is present and reports no unplaced regions.

  • [ ] empty_cell_pct is within budget (<= 15 for analytical/operational/ comparative, <= 20 for executive/narrative unless justified).

  • [ ] Largest-region balance is justified: no non-hero data region starves supporting visuals; dominant heroes cite the archetype variant and keep supporting charts/tables readable.

  • [ ] A bare single-value cardVisual is not the largest/dominant region. If a card-like KPI hero is used, it is composite and the rationale names its context elements.

  • [ ] Every side callout, context tile, Smart Narrative, or card-like annotation has insight_basis or callout_value_basis tied to derived insight; no callout duplicates the same absolute measure plotted in an adjacent visual.

  • [ ] Date slicer type matches data grain and audience: executive/annual pages use Year dropdown/tile by default; full-date between is reserved for renderable Date/DateTime fields where arbitrary date-range exploration is part of the page question.

  • [ ] Every chart/map/table placement has purpose and field_bindings.

  • [ ] Bar/column placements specify sort_policy.

  • [ ] A report-wide navigation_model is set for multi-page reports; each drillthrough-role page pairs with a Back button, and nav/button labels are destination-scented (not "Page 2").

  • [ ] Every color-bearing measure visual has a color_strategy that can be resolved against color_map.

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