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/pre-flight-checklist.md

Pre-Flight Checklist

Contents

  • Identity (Step 1)

  • Routing (Steps 2–3)

  • Theme & propagation (Step 1 → Step 5)

  • Page-level layout (Step 6)

  • Accessibility (Step 7)

  • Final visual audit (after build)

Walk through this before handing off the report spec/design contract to the authoring mode. Fix any failures first — the authoring skill will faithfully implement what you give it, including its flaws.

For brownfield mode, also walk brownfield.md (see brownfield.md) § Brownfield-specific Pre-Flight items.

Identity (Step 1)

  • [ ] [ ] Single source of truth — if writing files, _brief/report-spec.md contains the user-readable report spec and exactly one fenced yaml block beginning with Design Brief:.

  • [ ] [ ] Markdown/YAML alignment — every page, core visual, design identity, model requirement, and delivery boundary promised in Markdown is present in the embedded YAML. If they conflict, fix the spec before authoring.

  • [ ] [ ] Implementation authority clear — prose provides context; the embedded Design Brief: YAML is the canonical implementation contract.

  • [ ] [ ] Tone committed — the brief's design_identity.tone is a named catalog entry from tone-catalog.md (see tone-catalog.md), OR a short elaboration that pins down the feel. One-word tones like "modern" or "professional" are not enough; replace.

  • [ ] [ ] Signature committed — the brief's design_identity.signature names a single concrete move from signatures.md (see signatures.md) or an authored equivalent. The signature recurs on every page (or every relevant page).

  • [ ] [ ] Tone and signature are coherent — the signature pick fits the tone (see signatures.md § Composing tone + signature). If the feel and visual move point in different directions, re-pick.

  • [ ] [ ] Brownfield two-value form — if mode: brownfield, both current_tone and current_signature are filled in (or explicitly "indistinct" / "none"). The redesign delta is reasoned about in the brief.

Routing (Steps 2–3)

  • [ ] Vague prompt handled — if the original request was missing audience, purpose, page count, or filtering depth, the design brief shows that 2–3 named options were offered to the user and one was confirmed (or, after two rounds, an assumption was documented in variant_rationale). Do NOT silently guess on a vague prompt and ship a brief.

  • [ ] Per-page archetype routing — every page's archetype was chosen from its own audience/purpose/cadence — not inherited from page 1. Multi-page reports covering distinct subject areas should mix archetypes. 3+ pages all sharing one archetype is a smell — re-route each page independently.

  • [ ] Layout variant per page — every page declares layout_variant (A/B/C) AND a one-sentence variant_rationale citing the data signal that drove the pick. Same-archetype pages should rotate variants where data signals support it (see archetype-composition.md (see archetype-composition.md) § Cross-page variant rotation).

Theme & propagation (Step 1 → Step 5)

  • [ ] Theme handoff is explicit — if a custom theme is needed, the brief states the intended theme name, palette/text changes, and asks the authoring mode to handle registration mechanics.

  • [ ] Theme/per-visual boundary captured — properties that may need per-visual treatment (border radius, padding, page background transparency, gradient stops, card accent bar) are called out in the brief for the authoring mode.

  • [ ] Generated-report theme safeguards preserved — if creating/adapting a custom theme, preserve references/design/assets/base.json per-type safeguards: textbox zero padding/background/border, cardVisual zero padding/card spacing, table grow-to-fit styling, hidden visual headers, and chart defaults.

  • [ ] Tone propagated to typography — if the tone called for a display serif (Editorial), the brief's theme has serif textClasses.title.fontFace set. Tone declared without typography change reads as accidental.

  • [ ] Tone propagated to color — the dataColors palette reflects the tone-catalog row's accent guidance, not the base Okabe-Ito as-is.

  • [ ] Measure color map complete — every measure used in a color-bearing card/chart/map/table has a color_map entry or a documented reason to use category/semantic colors instead.

  • [ ] Tone propagated to iconography — if iconography is part of the signature, the icon style (filled/outline/duotone) matches the tone and stays consistent across the report.

Page-level layout (Step 6)

  • [ ] Page background set (#F3F2F1 or similar off-white, OR the tone-aligned tinted surface from the tone-catalog) on every page with explicit transparency: 0D.

  • [ ] Descriptive insight titles on every page — not "Overview" or "Dashboard" but "Language Courses Drive 45% of All Enrollment".

  • [ ] Every chart has explicit VCO title.text and intentional subtitle behavior — use a subtitle for time window, active filter, units, comparison baseline, or caveat; omit/disable it when it repeats the title, obvious measure, or raw field name.

  • [ ] KPI cards show context (referenceLabel or subtitle) — no bare numbers.

  • [ ] Callouts earn their space — every side callout/context tile or Smart Narrative has insight_basis or callout_value_basis tied to delta, variance %, rank shift, threshold, benchmark gap, anomaly, or dynamic narrative text. No callout repeats the same absolute measure already shown in an adjacent chart/table.

  • [ ] Bar/column charts sorted by value descending.

  • [ ] No unintended monochrome bars — if category contrast matters, specify value-gradient or per-category color intent.

  • [ ] Clean display names everywhere — no raw field names (subject_name, Count of fight_key), no default aggregation labels (Sum of X).

  • [ ] Slicers on pages with 3+ data visuals — right field, right type (dropdown/list/between), right position (top-bar/left-rail).

  • [ ] Date slicer matches grain — executive/annual-grain pages use Year or Period dropdown/tile by default; full-date between is used only for renderable Date/DateTime fields when arbitrary date-range exploration is part of the page question.

  • [ ] Slicer/header band reserved — top-bar slicers sit fully inside a reserved title/slicer band, with the page title as the left anchor and slicers aligned to the right. No chart/card/table starts under the slicer rectangle. Taller slicers increase the band height.

  • [ ] Geography routed by question — if location/spatial distribution carries the message, consider azureMap first; if geography is only a ranked category, a sorted bar chart is acceptable and the rationale should say so.

  • [ ] No pie/donut with >5 slices — use sorted horizontal bar.

  • [ ] No text month/quarter names on time-series axes — use Date column.

  • [ ] Every coordinate on 8-px grid (x, y, width, height all multiples of 8).

  • [ ] Greenfield canvas defaults to FHD — new reports use 1920 x 1080 unless the user requested or approved a different size. Brownfield keeps the existing canvas unless resize is approved.

  • [ ] No unintended overlaps — sibling visual bounding boxes do not overlap unless the overlap is intentional and non-data-bearing.

  • [ ] No unplaced regions — every non-spacer region in layout_contract has at least one placement. Remove empty footer/callout/detail regions or put real content in them.

  • [ ] Space audit passes — space_audit exists, unplaced_regions is empty, and empty_cell_pct stays within budget (<=15 for analytical/ operational/comparative, <=20 for executive/narrative unless justified).

  • [ ] Visual balance intentional — no single non-hero data region starves supporting visuals; supporting charts have at least 3x3 grid cells, tables at least 4 rows, and KPI/card strips 2 rows on standard pages.

  • [ ] No oversized bare card hero — a single-value cardVisual is not the largest/dominant page region. If a KPI hero is intentional, it is a composite treatment with delta/reference label, sparkline/threshold context, annotation, or adjacent explanatory chart, and balance_rationale says why it deserves the space.

  • [ ] Textbox heights sufficient — no scrollbars (height formula: max(18, ⌈fontSize × 25/16⌉) + padding_top + padding_bottom).

  • [ ] Per-visual formatting needs are explicit — background, border/radius, padding, visualHeader, or card accent-bar requirements are stated in the brief when the design depends on them.

  • [ ] Card padding/gutters intentional — card visuals use card-specific padding/background/spacing, not accidental wildcard theme padding that creates white gutters or clipped content.

  • [ ] Canvas filled — no dead footer band or >20% whitespace gap; expand bottom-row visuals, add a real detail/footer placement, or rebalance rows if the canvas looks empty.

Accessibility (Step 7)

  • [ ] WCAG contrast verified on every text/background pair (page background ↔ axis labels; card background ↔ card values; chart plot ↔ legend; tooltips; CF cell colors).

  • [ ] Tab order matches reading order — Selection pane reordered on every page.

  • [ ] Alt text per visual — content-specific, not "Bar chart".

  • [ ] Color encoding has redundant cue when color carries meaning (data labels, shape, or pattern).

Final visual audit (after build)

  • [ ] Squint test — a screenshot of each page makes one element jump out (the hero / signature). If nothing jumps, hierarchy is flat.

  • [ ] Sibling test — pages laid out side-by-side read as part of the same family (border radius, type, accent usage all consistent).

  • [ ] Identity propagation visible — a stranger looking at the report could describe the tone in a sentence (the test for whether tone is doing real work).

  • [ ] No clipped controls or scrollbars — slicers, textboxes, cards, legends, and tables are fully visible in screenshots.

  • [ ] Color-map audit passes — every visual using the same measure reuses that measure's color, and gradients use that measure's tint/base pair.

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