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

Download the skill as a ZIP:
https://autogineer.com/agent-skills/microsoft/powerbi-report-cli/download

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
To find workspace details, including its ID, from a workspace name: list all workspaces, then use JMESPath filtering.
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.
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

Mode	Use when the request...	Existing route examples	Read first
`planning`	creates a new report/dashboard and needs requirements, model/dependency inspection, scope, a page plan, and approval before implementation	create a report, build a dashboard, create from a semantic model, plan then implement, walk me through creating a report	references/planning.md, then references/planning-part-02.md
`design`	decides what a report should look like: tone, signature, page archetype, chart type, layout, color, typography, theme direction, accessibility, brand application, redesign, or critique	design a Power BI report, make the dashboard professional, choose a chart, apply a brand, redesign the report, create a design brief	references/design.md
`authoring`	reads or edits local PBIR/PBIP files, validates them, previews the report, or captures screenshots	edit PBIR, create/add a report page or visual, format a visual, add filters/slicers/bookmarks/themes, validate PBIR, preview/reload/screenshot in Desktop or service	references/authoring.md
`management`	moves a report definition to or from Fabric or manages the workspace report item	publish/upload/download PBIR or PBIP, list reports, get/update/delete a report, rebind a report	references/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

Mode	Completion requirement
`planning`	Persist `_brief/report-spec.md` or the user-named equivalent, ask for explicit approval, and stop before implementation.
`design`	Produce 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.
`authoring`	Persist 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.
`management`	Complete 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.

Complete Reference Index

Open every relevant reference directly from this index. Files named part-XX continue the named topic.

Authoring

Design

Mode Guides

Examples

User request	Mode
"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:

Mode	Preserved route phrases
`planning`	create 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
`design`	design Power BI report; make dashboard look professional; choose chart type; apply brand to report; redesign report; create design brief; Power BI report design archetype
`authoring`	edit 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
`management`	upload 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

ATTRIBUTION.mdAdded by AutoGineer881 B
LICENSELicence file added by AutoGineer1.1 KiB
SKILL.md16.1 KiB
apm.yml642 B
references/authoring-part-02.md14.6 KiB
references/authoring-part-03.md16.0 KiB
references/authoring-part-04.md15.9 KiB
references/authoring.md16.8 KiB
references/authoring/authoring-workflows.md11.7 KiB
references/authoring/bookmark.md14.3 KiB
references/authoring/button-part-02.md16.1 KiB
references/authoring/button-part-03.md7.7 KiB
references/authoring/button.md15.7 KiB
references/authoring/card-part-02.md16.1 KiB
references/authoring/card-part-03.md8.6 KiB
references/authoring/card.md6.4 KiB
references/authoring/cartesian-part-02.md17.7 KiB
references/authoring/cartesian-part-03.md12.3 KiB
references/authoring/cartesian-part-04.md15.8 KiB
references/authoring/cartesian.md18.0 KiB
references/authoring/color-strategy.md8.4 KiB
references/authoring/conditional-formatting-part-02.md13.5 KiB
references/authoring/conditional-formatting-part-03.md16.0 KiB
references/authoring/conditional-formatting-part-04.md14.0 KiB
references/authoring/conditional-formatting-part-05.md16.9 KiB
references/authoring/conditional-formatting-part-06.md14.7 KiB
references/authoring/conditional-formatting-part-07.md14.5 KiB
references/authoring/conditional-formatting.md18.2 KiB
references/authoring/custom-visuals.md13.9 KiB
references/authoring/expressions.md11.9 KiB
references/authoring/field-parameters.md5.1 KiB
references/authoring/filter-pane.md5.0 KiB
references/authoring/filters.md9.3 KiB
references/authoring/formatting-overview.md4.8 KiB
references/authoring/formatting-part-02.md3.3 KiB
references/authoring/formatting.md17.0 KiB
references/authoring/image.md12.6 KiB
references/authoring/kpi.md2.5 KiB
references/authoring/map.md13.4 KiB
references/authoring/model-binding.md7.7 KiB
references/authoring/page-formatting.md4.5 KiB
references/authoring/powerbi-desktop.md2.4 KiB
references/authoring/powerbi-report-author-cli-part-02.md3.2 KiB
references/authoring/powerbi-report-author-cli.md17.7 KiB
references/authoring/preview-part-02.md16.9 KiB
references/authoring/preview-part-03.md4.0 KiB
references/authoring/preview-part-04.md2.5 KiB
references/authoring/preview.md16.1 KiB
references/authoring/re-theming-part-02.md16.8 KiB
references/authoring/re-theming-part-03.md4.9 KiB
references/authoring/re-theming.md1.5 KiB
references/authoring/screenshot-review.md5.0 KiB
references/authoring/shape.md13.6 KiB
references/authoring/slicers-part-02.md16.3 KiB
references/authoring/slicers.md15.6 KiB
references/authoring/table.md17.5 KiB
references/authoring/textbox.md5.6 KiB
references/authoring/theming-part-02.md6.7 KiB
references/authoring/theming.md16.4 KiB
references/authoring/version-control.md6.6 KiB
references/design.md17.3 KiB
references/design/accessibility.md11.4 KiB
references/design/anti-patterns.md18.5 KiB
references/design/archetype-composition.md3.4 KiB
references/design/archetypes/analytical-canvas.md17.7 KiB
references/design/archetypes/comparative-benchmark-part-02.md5.7 KiB
references/design/archetypes/comparative-benchmark.md15.8 KiB
references/design/archetypes/executive-summary.md14.7 KiB
references/design/archetypes/narrative-story.md18.1 KiB
references/design/archetypes/operational-monitor.md17.0 KiB
references/design/assets/base.json7.5 KiB
references/design/brownfield.md5.7 KiB
references/design/chart-selection.md9.8 KiB
references/design/color.md10.5 KiB
references/design/design-brief-part-02.md13.7 KiB
references/design/design-brief.md8.8 KiB
references/design/interactivity.md9.2 KiB
references/design/layout.md11.3 KiB
references/design/pre-flight-checklist.md10.8 KiB
references/design/signatures.md12.3 KiB
references/design/tone-catalog.md14.4 KiB
references/design/typography.md9.2 KiB
references/design/visual-cookbook-part-02.md11.0 KiB
references/design/visual-cookbook.md16.7 KiB
references/management-part-02.md17.2 KiB
references/management-part-03.md7.5 KiB
references/management-part-04.md16.7 KiB
references/management.md10.1 KiB
references/planning-part-02.md11.2 KiB
references/planning.md19.5 KiB

references/design/anti-patterns.md

Anti-Patterns — The Dashboard Slop Catalog

Why This Catalog Exists
Cluster 1 — Visual Noise (Chartjunk)
Cluster 2 — Misleading Encoding
Cluster 3 — Cognitive Overload
Cluster 4 — Color Misuse
Cluster 5 — Interactivity Theater
Cluster 6 — Archetype Mismatch
LLM-Specific Failure Modes
Detection Heuristics
Severity Model
Remediation Quick-Reference
Pre-Publish Review Workflow
Cross-Reference to Other Documents

Why This Catalog Exists

LLMs producing dashboard layouts gravitate toward a set of attractor states — generic, cluttered, misleading designs that look complete but fail users. This is the refusal list: when the agent detects these patterns in its own output, it must stop and fix before emitting.

This catalog is advisory. It assigns severity levels but never blocks output. Strong warnings surface to the user for explicit confirmation.

Cluster 1 — Visual Noise (Chartjunk)

Anti-Pattern	Why It Fails	Do Instead	PBI Tell
3D effects	Perspective distortion destroys precision; occludes data	Flat 2D equivalent	Any `3D` visual type selected
Drop shadows on visuals	Pure decoration; adds visual weight without information	Remove all shadows; rely on whitespace for separation	`shadow` enabled in visual formatting
Saturated background fills	Competes with data ink; reduces text contrast	White or near-white canvas (`#FFFFFF`, `#F9F9F9`)	`background.color` is a saturated hue

Cluster 2 — Misleading Encoding

Anti-Pattern	Why It Fails	Do Instead	PBI Tell
Truncated bar baseline	Bars starting at non-zero exaggerate differences by 2-10×	Always start bars at zero; use dot plot if range is narrow	`valueAxis.start` ≠ 0 on bar chart
Dual y-axis chart	Implies correlation by scale manipulation; easy to lie with	Two separate charts, shared x-axis, stacked vertically	`secondaryYAxis` enabled
Pie chart >5 slices	Angle encoding is imprecise; small slices become invisible	Sorted horizontal bar chart	Pie/donut with >5 data points
Stacked bar for mid-stack comparison	Only bottom and top segments have a common baseline	Grouped bar or small multiples	Stacked bar with >2 segments compared across categories
Unshared small-multiple axes	Different scales make comparison impossible — defeats the purpose	Force identical axis range on all multiples	Auto-scale per tile
Gauge / speedometer	Uses large area for one number; no trend; arbitrary dial range	Card + sparkline or bullet graph	Gauge visual type
Radar / spider chart	Area distortion; axis order changes shape; unreadable	Grouped bar or parallel coordinates	Radar visual type
Area chart for non-stacked data	Fill implies volume/accumulation that may not exist	Line chart for trends; area only for stacked composition	`areaChart` for single series

Cluster 3 — Cognitive Overload

Anti-Pattern	Why It Fails	Do Instead	PBI Tell
KPI carpet-bombing	8+ cards in a row; nothing stands out; reader skips all	3–4 KPIs max; pick the ones that drive decisions	>6 card visuals on one page
12+ visuals on a page	Exceeds working memory; user scans nothing carefully	5–7 visual groups; use drill-through for depth	Visual count >12 on single page
Alert fatigue	Everything highlighted = nothing highlighted	Reserve red/amber for actionable exceptions only	>3 conditional-format rules using red
Embedded detail matrix on exec page	Executives scan, not read; a 50-row matrix wastes their time	Summary KPIs on exec page; matrix on drill-through detail page	Matrix with >10 rows on a page with cards
Wall of slicers	5+ slicers consume space and paralyze with choice	2–3 key slicers visible; rest in filter pane or collapsible panel	>4 slicer visuals on one page
Wrong date slicer grain	Full-date `Between` picker used for yearly executive filtering; control may not render and adds precision users do not need	Match slicer to grain: Year/Period dropdown or tile for annual/quarterly executive pages; full-date `Between` only for renderable Date/DateTime range exploration	Executive page with yearly data but `slicer_type: between` on full-date key
Slicer sizing shortcut	Shrinking slicer height/font hides clipping instead of solving layout; dropdown/date chrome still needs space	Follow the slicer sizing formula from the `authoring` mode and enlarge the reserved band/rail	Slicer height near 48px, 8pt text, or clipped lower row
Multi-page report without navigation	Users don't discover pages beyond the first	Add page navigator or button-based navigation	>3 pages with no navigator or nav buttons
Variant default-bias / uniform-variant pages	Picking layout variant A on every page — or any single variant uniformly across same-archetype pages — without consulting the selection table. Produces interchangeable, templatized reports that ignore each page's data shape	Walk the `Layout Variants` selection table in the archetype file per page, using each page's own data signals (KPI count, slicer count, viewing distance, comparison shape, narrative structure). Record `variant_rationale` per page. Same-archetype reports should rotate variants where data supports it; use `references/design/archetype-composition.md` for cross-page rotation guidance	Every page in a multi-page report has the same `layout_variant`; or `variant_rationale` is missing / generic across pages
Mono-archetype report	Copy-pasting page 1's archetype to pages 2-N instead of routing each page independently. A 4-page report covering distinct subject areas gets shipped with all 4 pages using the same archetype because the agent never re-walked the router after page 1. Pages all look the same regardless of audience/purpose differences	Re-walk the archetype decision for every page using that page's audience, purpose, and cadence. Multi-domain "cover everything" requests almost always decompose into 3-4 different archetypes (Executive landing + Comparative ranking + Analytical exploration + Narrative timeline). Use `references/design/archetype-composition.md` for common multi-archetype compositions	3+ pages all share one archetype; or every page's `archetype` field equals page 1's
Silent-guess on a vague prompt	Receiving a prompt that's missing audience, purpose, page count, or filtering depth — and producing a design brief anyway based on a default assumption. The user gets a templatized "make a report about X" output that doesn't match their actual need	Treat missing audience, purpose, page count, or filtering depth as vagueness. Stop and offer 2–3 named, concrete options (each referencing a specific archetype + variant combination, in user-facing language). Only after the user picks, or after two clarification rounds with a documented assumption, proceed to design	Brief has no record of clarification; prompt was 1-line broad ("build a dashboard for X") and brief jumps straight to layout
Mandatory archetype component fill	Treating every box in an archetype wireframe as required creates redundant cards/callouts that do not answer a new question	Treat variant zones as advisory; drop or repurpose any component without `insight_basis` / `callout_value_basis`	Callout repeats the same absolute measure as the adjacent chart

Cluster 4 — Color Misuse

Anti-Pattern	Why It Fails	Do Instead	PBI Tell
Rainbow categorical on ordered data	No perceptual order; readers can't decode high vs low	Sequential single-hue ramp (Blues, viridis)	`dataColors` with rainbow hues on a sorted dimension
Categorical palette on ordinal data	Distinct hues imply no order; misleads on ranked data	Sequential or diverging palette	Categorical colors assigned to ordered field
Red/green as sole signal	8% of males are red-green CVD; information invisible	Add icon + text label alongside color	Red and green used without secondary channel
Low-contrast labels	<4.5:1 body-text ratio; unreadable on projectors and low-quality screens	Minimum `#767676` on white for body text	Text color with contrast ratio <4.5:1
Semantic color flip	Green=bad violates universal convention; confuses everyone	Respect standard semantics; never invert	`good` theme color mapped to a negative outcome
Pastel for critical status	Light pink doesn't signal urgency; fails to grab attention	Saturated red for critical; pastel only for context/background	Conditional format using pastel for "critical" threshold
>8 categorical hues	Colors become indistinguishable; cognitive overload	Group tail categories into "Other"; limit to 7–8	`dataColors` with >8 entries actively used

Cluster 5 — Interactivity Theater

Anti-Pattern	Why It Fails	Do Instead	PBI Tell
Headline behind a click	Primary insight invisible until interaction	Show insight on page load; interactions reveal depth	Key metric visible only via drill-through or bookmark
Invisible slicer state	User can't tell what's filtered; data appears wrong/incomplete	Show active filter indicators; use slicer headers	Slicers with hidden headers or no default label
Drill without breadcrumb	User gets lost; can't return to overview	Always add back button; show drill path in page subtitle	Drill-through page without back button
Bookmark overload	>10 bookmarks become unmanageable; states conflict	5–8 bookmarks max; clear, descriptive names	>10 bookmarks defined
Slicer in prime real estate	Top-left position wasted on controls, not insight	Slicers in filter strip, right rail, or collapsible panel	Slicer visual at position x<200, y<100
Auto-cycling carousel	Users can't control pace; miss data; a11y violation	Static views with manual next/prev buttons	Timer-driven bookmark cycling

Cluster 6 — Archetype Mismatch

Anti-Pattern	Why It Fails	Do Instead	PBI Tell
Executive page with 30 visuals	Executives scan for 15 seconds; 30 visuals need 15 minutes	4–6 visual groups; cards + 1 hero chart	Archetype=exec + visual count >10
Operational without timestamp	Users can't assess data freshness; stale data = wrong decisions	Show "Last refreshed: {time}" in footer on every ops page	No timestamp or refresh indicator on operational page
Analytical without export/drill	Analysts need to dig; no drill-through = dead end	Enable drill-through, export, personalize visuals	Archetype=analytical + no drill-through pages
Narrative without thesis	Story pages without a headline are just data dumps	Every narrative page leads with a finding statement	Narrative page without text visual stating insight
Default "All" on large model	Loads millions of rows on first view; slow, meaningless overview	Pre-filter to recent period or top-N by default	No default slicer selection + large dataset
Comparative with unsynchronized slicers	Comparing A vs B but slicers don't apply equally	Use sync slicers across all compared pages/visuals	Comparative layout with independent slicer states

LLM-Specific Failure Modes

Common mistakes LLMs make when generating PBI report definitions:

Failure Mode	Description	Fix
Clustered bar for everything	Default chart choice regardless of question type	Consult the chart selection decision matrix
Ignoring small multiples	Uses multi-series line or stacked bar instead of small multiples for comparison	Use small multiples when comparing >3 categories
One line chart per measure	Every KPI gets its own line chart; no hierarchy or grouping	Combine related measures; use cards for single values
Missing sortBy	Bar charts left in alphabetical order	Apply descending sort on the value measure
Ignoring numeric alignment	Proportional-looking figures or left-aligned numbers in comparison tables/matrices	Use tabular-looking fonts where available, right-align numeric columns, and apply consistent number formatting
Skipping alt text	Alt text field left empty on every visual	Write insight-driven alt text for every visual
Hardcoding hex colors	Inline `#FF0000` instead of theme reference	Use theme `dataColors` and sentiment keys
Six font sizes	Each visual gets a different type size	Follow the 4-tier type ramp
Pixel drift	Positions not on 8px grid; edges misaligned	Snap all x, y, width, height to multiples of 8
Title as chart type	"Bar Chart" or "Line Chart" as visual title	Title states the insight: "Sales declined 8% in Q4"

Detection Heuristics

Automated and semi-automated checks to catch anti-patterns:

#	Check	What to Look For	Severity
1	Hue count	>8 distinct hues in `dataColors` actively rendered	warn
2	Dual axis	`secondaryYAxis` enabled on any visual	strong-warn
3	Card count	>6 card visuals on a single page	warn
4	Bar baseline	`valueAxis.start` ≠ 0 on bar or column chart	strong-warn
5	Pie slice count	Pie or donut with >5 data points in field	warn
6	Visual density	>12 visuals on a single page	warn
7	Pixel grid	Any `position.x`, `y`, `width`, `height` not divisible by 8	info
8	Contrast ratio	Any text/background pair below 4.5:1	strong-warn
9	Alt text	Alt text field empty on any non-decorative visual	warn
10	Inline hex	Hardcoded hex color not referencing theme	info
11	Freshness indicator	Operational page missing refresh timestamp	warn
12	Ramp bloat	>4 distinct `fontSize` values across visual titles/labels	info

Severity Model

Level	Label	Meaning	Agent Behavior
`info`	Informational	Stylistic concern; may be intentional	Log internally; do not surface unless asked
`warn`	Warning	Likely unintentional; surface to user	Surface in review summary; suggest fix
`strong-warn`	Strong Warning	High risk of misleading or inaccessible output	Recommend explicit user confirmation before proceeding

Important: This system is advisory only. It never blocks output or refuses to generate. The agent surfaces findings and recommendations; the user decides.

Remediation Quick-Reference

For each detected anti-pattern, the recommended fix action:

Anti-Pattern Detected	Immediate Fix	Time to Fix
3D visual	Replace with flat 2D equivalent	1 min
Truncated baseline	Set `valueAxis.start: 0`	30 sec
Dual axis	Split into two visuals, stack vertically	5 min
Pie >5 slices	Replace with sorted horizontal bar	3 min
>12 visuals	Move detail to drill-through page	10 min
>8 colors	Group tail categories into "Other"	5 min
Missing alt text	Write insight-driven text per template	2 min/visual
Pixel drift	Snap x/y/w/h to multiples of 8	1 min/visual
Rainbow on sequential	Replace with single-hue sequential ramp	3 min
Missing timestamp	Add "Last refreshed" text box in footer	2 min
Hardcoded hex	Move colors to theme JSON	5 min
Ramp bloat (>4 sizes)	Standardize to 4-tier type ramp	5 min
Unsorted bars	Apply descending sort by value measure	30 sec
Gauge	Replace with card + sparkline	3 min
Slicer in top-left	Move to filter strip or right rail	2 min
Bookmark overload	Consolidate to ≤8; delete redundant states	10 min
No navigation	Add page navigator or button navigation	5 min
Semantic color flip	Correct to standard green=good/red=bad	2 min

Pre-Publish Review Workflow

Run these checks in order before delivering any report:

1. LAYOUT CHECK
   □ Visual count ≤ 7 groups per page
   □ All positions on 8px grid
   □ Consistent gutters (16px or 24px)
   □ Page margins ≥ 24px all sides
   □ Title/header/breadcrumb height matches layout contract (~72px FHD / ~48px 1280x720)

2. COLOR CHECK
   □ ≤ 8 categorical hues
   □ No rainbow on ordered data
   □ All text passes WCAG contrast (4.5:1 body, 3:1 large)
   □ No red/green as sole signal
   □ CVD simulation passes
   □ All colors from theme (no inline hex)

3. TYPOGRAPHY CHECK
   □ ≤ 4 distinct font sizes
   □ Right-align numeric columns; use tabular-looking digits where comparison matters
   □ Consistent number formatting across pages
   □ No text below 8pt

4. CHART CHECK
   □ Every chart answers a stated question
   □ Bars start at 0
   □ No dual axes
   □ No pie with >5 slices
   □ All bar charts sorted by value (unless meaningful order)

5. INTERACTIVITY CHECK
   □ Primary insight visible on page load
   □ Slicer state visible
   □ Drill-through has back button
   □ ≤ 8 bookmarks
   □ All cross-filter interactions deliberately configured

6. ACCESSIBILITY CHECK
   □ Alt text on every non-decorative visual
   □ Tab order matches reading order
   □ Keyboard navigation works end-to-end
   □ Touch targets ≥ 24×24px
   □ High-contrast mode tested

7. ARCHETYPE CHECK
   □ Visual density matches archetype
   □ Interaction budget matches archetype
   □ Typography tier matches archetype
   □ Color palette matches archetype

Cross-Reference to Other Documents

Anti-Pattern Cluster	Primary Reference	Secondary Reference
Visual noise	`chart-selection.md` — Anti-patterns section	`layout.md` — Whitespace tiers
Misleading encoding	`chart-selection.md` — Decision matrix	`chart-selection.md` — Encoding accuracy
Cognitive overload	`layout.md` — Visual hierarchy, Templates	`interactivity.md` — Interaction budgets
Color misuse	`color.md` — Palette tables, CVD	`accessibility.md` — Contrast workflow
Interactivity theater	`interactivity.md` — Taxonomy, titles	`interactivity.md` — Bookmark rules
Archetype mismatch	`layout.md` — Composition templates	All reference documents' archetype sections

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

2026-11-09

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