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/authoring/preview.md

Report Preview

Core workflow
Host selection
- Desktop operation routing
Argument selection

Use this runbook for rendered inspection after PBIR validation. Always route through powerbi-report-author preview; do not invoke or describe an underlying Desktop or service host implementation directly.

Required continuations. The runbook continues in preview-part-02.md, preview-part-03.md, and preview-part-04.md. Open the named continuation when a section is identified there; do not resolve that section as a fragment in this file.

Direct topic routes

Open the named file directly; do not search the authoring reference tree first:

Request or decision	Read
Desktop status, open/attach, reload, unsaved-state handling, or exact command examples	`preview-part-02.md`
Screenshot destination, retention, temporary validation, exposure warning, or cleanup	`preview-part-03.md`
TMDL/model changes, `--reload-with-model`, processing, or DAX verification	`preview-part-04.md`
Reviewing captured report images	`screenshot-review.md`

Core workflow

Edit the report files.
Run powerbi-report-author validate "<folder>".
Derive the preview host and arguments from the request, conversation, and report context.
Open or reload the preview so it contains the latest PBIR.
Follow the screenshot artifact lifecycle in preview-part-03.md: classify retained output separately, then select and create the workflow-owned temporary validation screenshot directory.
Capture every affected page and review the screenshot files. Fix issues, validate, and repeat.
When the selected host is service and review passes, automatically display the validated report in a visible service preview.
Delete only the workflow-owned temporary screenshot directory; never delete explicitly retained output.
Accept the result only after review. Keep the changes local. Never publish or overwrite the remote report with local changes until the user explicitly gives permission; if the request does not ask to publish, or you are unsure, do not publish. Discard local changes only when explicitly requested.

Step 2 never ends the workflow on success. Every schema validation must continue through loading the validated PBIR and screenshot validation of every affected page.

Preview is inspection. Service preview renders the local edited PBIR layout against a published semantic model's live data. It does not publish or persist local report edits, and it does not require a published report ID.

Successful service screenshot review always continues to visible display, without requiring the user to ask. Reuse the validated folder and the same --group and --dataset; run visible-mode status first, then open/attach without --headless when permitted. Headless and visible service previews are separate instances, so this final display does not alter or repeat the completed screenshot validation. Leave the visible instance open. If it cannot be displayed, report that display is blocked without invalidating screenshots that already passed review. This automatic display step applies only to the service host. It adds no Desktop command and does not change any Desktop routing, operation, failure handling, or lifecycle rule.

For an authoring task, screenshot capture and review are mandatory completion steps, not optional user-requested output. Page-scoped edits require screenshots of each affected page; report-wide changes require --all-pages. Load/reload and screenshot must be separate CLI invocations because combining rendering and capture can exceed the 30-second command timeout. A standalone request to capture the current warm view still follows the direct screenshot routing below and does not implicitly open, reload, or run status.

Host selection

Use --host desktop when the request identifies local Desktop. The preview command is the source of truth for Desktop availability, capabilities, instance matching, and errors. These can vary with the installed CLI, bridge, Desktop build, and live instances. Do not bypass the preview command by calling powerbi-desktop directly.

Desktop preview requires the owning .pbip project file for the selected .Report folder. If no owning project file exists, report that prerequisite; do not silently switch to service preview.

Desktop preview resolves the report from <folder>. It never terminates Desktop. The plain command is open/attach and has no lifecycle flag; issue it only when the unsaved-changes preflight in Unsaved host changes passes with boolean false. When an instance already holds the report it attaches and re-reads PBIR into that window. The public preview command resolves the Desktop instance from <folder>; it does not accept --pid. The positional argument accepts the .Report folder, the directory containing definition/, or the owning .pbip file itself; an explicit .pbip always wins over folder-based resolution, which is how you proceed once the user has told you which project owns an otherwise unresolvable folder.

Desktop operation routing

Once the user selects Desktop and requests a specific operation, execute only that operation, preceded only by the unsaved-changes --status preflight when the exception list below requires it:

Construction rule: Every Desktop command explicitly contains --host desktop and never contains --pid. Every screenshot contains --screenshot "<path>", with the output path supplied as the value of --screenshot rather than as a separate positional argument. During a screenshot request, every executed preview command must contain that flag with its destination. This includes a structured-correction retry; never replace the screenshot with attach, reload, status, help, or host discovery.
Terminal rule (the single retry policy): After that command runs, any failure without an explicit machine-readable correction object ends the Desktop workflow. Make no more tool calls. An error message, hint, usage output, unknown-option response, or suggestion to run help is not a structured correction. When a correction object is present, retry the same operation once: patch the original command with only the named correction, keeping the operation, host, folder, screenshot destination, bindings, headless mode, and screenshot modifiers unchanged — so a screenshot retry still carries --screenshot "<same-path>". If the correction asks you to change one of those requested values, stop instead. This rule overrides every discovery, status, troubleshooting, and error-table instruction below, and applies equally to default-page, --page, --all-pages, and --scale screenshots. Do not inspect the folder, search for .pbip, change paths, or alter any screenshot modifier after failure. The requested host and operation are immutable. Never switch Desktop to service or replace attach/reload/screenshot with another lifecycle operation, even when a correction recommends it.
What counts as a failure here: an ok: false envelope — the command did not do its job. A capture that returns ok: true with status: "partial" is not a failure for this rule, even though it exits non-zero and carries per-page entries in failures[]: the command ran, and the captures it returned are valid. Report every capture and every failure, and see Preview lifecycle below for the one per-page cause you may act on.

Requested operation	Command shape
Attach/open	`powerbi-report-author preview "<folder>" --host desktop`
Reload	`powerbi-report-author preview "<folder>" --host desktop --reload`
Reload report and model	`powerbi-report-author preview "<folder>" --host desktop --reload-with-model`
Screenshot	`powerbi-report-author preview "<folder>" --host desktop --screenshot "<path>" [--page <id>

Every screenshot contains --screenshot "<path>", whose value is the output destination. A selected-page screenshot adds --page <id> and writes one PNG. An all-pages screenshot adds --all-pages and writes to a directory. The output path is the value of --screenshot; it is never a separate positional operand. For example:

powerbi-report-author preview "<folder>" --host desktop --screenshot "<validation-screenshot-dir>" --all-pages --scale 2

Desktop screenshot is a warm capture: it snapshots the current window as-is and does not reload PBIR. Use a separate explicit --reload operation before capture when the latest on-disk edits must be rendered. A reload reports LIVE_WINDOW_RELOADED; a --screenshot always reports LIVE_WINDOW_NOT_RELOADED, which describes only the screenshot operation and says nothing about whether a prior reload succeeded. Establish freshness from a reload's LIVE_WINDOW_RELOADED, not from the screenshot marker.

The LIVE_WINDOW_NOT_RELOADED advisory text suggests refreshing with the plain preview <folder> --host desktop form. Use --reload instead: the plain form is attach/open in this skill's protocol, and the rule below against translating attach into reload takes precedence over the advisory's wording.

Treat attach, open, connect, and show as attach/open. Never append --reload. Use --reload for PBIR-only reload or refresh. When TMDL/model files changed, follow Semantic-model reload workflow (see preview-part-04.md, section semantic-model-reload-workflow) and use --reload-with-model; never substitute plain --reload. It is a standalone Desktop operation; never combine it with --reload or another operation flag. Do not add --pid; instance selection is resolved from <folder>.

Do not run validation, --help, --list-hosts, --reload, or any other lifecycle command before the requested operation, and do not switch to service or call powerbi-desktop directly. Exactly two exceptions exist, and nothing else is one:

The unsaved-changes --status preflight required before --reload, --reload-with-model, and a bare preview — the forms that re-read files into a live window. For open/attach, proceed on explicit boolean false or structured HOST_UNAVAILABLE. For either reload form, proceed only on explicit boolean false; HOST_UNAVAILABLE is terminal. On true, missing, invalid, or any other failed status read, stop and report the safety-gate failure without running open/reload. For a standalone preview request, stop; never ask whether automatic open/reload should proceed despite the failed safety gate. During mandatory post-edit validation, explicit boolean true instead uses the manual-resolution resume path under Unsaved host changes. The preflight is never run before a screenshot on either host. See Unsaved host changes.
The partial-capture recovery described under Preview lifecycle, which runs as a new sequence after a partial returns, never fronted onto the original capture.

In particular, a screenshot request is capture only: never reload or check status first.

Execute the constructed Desktop command once. Retry the same operation once only when the structured result contains an explicit machine-readable correction object, patched as the Terminal rule above describes. Without that object, stop and report the failure immediately without another tool call. Do not diagnose it with --help, --list-hosts, --status, --reload, another preview operation, validation, a different host, or powerbi-desktop.

Use --host service when service rendering is requested. Service preview requires both --group <workspace-guid> and --dataset <semantic-model-guid>. Ask for either missing identifier; never infer tenant-scoped GUIDs.

If the user already selected service but omitted either identifier, ask immediately and stop before running any command or searching project files. Ask only for the missing workspace GUID used by --group and/or semantic-model GUID used by --dataset. Do not run --list-hosts, validation, status, or preview first, and do not inspect the report for tenant-scoped IDs. Do not add offers about headless mode, screenshots, pages, name resolution, publication, or unrelated validation.

When the service host, both identifiers, and a specific operation are supplied, preserve both binding flags unchanged. Execute service status or screenshot directly. Before service open/attach or reload, run service status with the same binding and instance mode, then follow Unsaved host changes. For a service screenshot, use --screenshot "<path>". The service host supports default-page capture, --page <id>, --all-pages, and --scale <1-3>. Use a PNG destination for one page and a directory for --all-pages. Preserve --headless when the existing instance is headless. Host and operation are immutable.

Before a host is selected, when host availability or capabilities are unknown, run:

powerbi-report-author preview --list-hosts

Use --list-hosts to choose a host, not as a replacement for status on a host the user already named and never to diagnose a failed selected-Desktop operation. For example, a request to check Desktop preview status uses:

powerbi-report-author preview "<folder>" --host desktop --status

Do not guess a host when the request distinguishes Desktop from service. Do not infer workspace or semantic-model IDs.

Always pass --host for report operations. Omitting it relies on a default that may select the wrong rendering environment for the request.

Argument selection

Derive every argument already established by the request, conversation, or report context. Ask only when a required value is missing or ambiguous.

--host desktop|service: required host selection.
--group <id>: service workspace GUID; required for every service command.
--dataset <id>: published semantic-model GUID; required for every service command.
--headless: service agent mode with no visible browser window.
--status: inspect an existing live preview instance for the selected host.
--reload: re-read edited PBIR files into an existing preview instance. For a headless service instance, include --headless. On every host, run the status preflight under Unsaved host changes first.
--reload-with-model: Desktop only. Re-read edited PBIR and TMDL/model files. Use only through Semantic-model reload workflow (see preview-part-04.md, section semantic-model-reload-workflow), including the required processing and DAX verification. Run the status preflight first.
--screenshot <path>: capture to a PNG file for a default-page or --page capture and a directory for --all-pages.
--page <id>: capture one page by ID or display name. Read the ID from powerbi-report-author preview-pages "<folder>", whose name field is the page ID and displayName the label; it reads the report from disk and needs no running Desktop instance. Supported by both hosts. Do not combine with --all-pages.
--all-pages: capture every page into the --screenshot directory. Supported by both hosts.
--scale <1-3>: optional capture scale on both hosts; host default is 2.
--close: tear down the service browser preview instance. Do not use it to close Power BI Desktop; Desktop is owned by the user.

Both hosts use --screenshot <path> and support page selection (--page, --all-pages) plus --scale. Service binding remains --group and --dataset. Do not invent --workspace or --report-id. For mandatory authoring validation, select <validation-screenshot-dir> through Screenshot artifact lifecycle (see preview-part-03.md, section screenshot-artifact-lifecycle). Use <validation-screenshot-dir>\<descriptive-name>.png for one page and the directory itself for --all-pages. Never use a current-directory-relative path or a path inside the PBIP project.

For operations that open or capture a service instance, keep visible/headless mode consistent. If the live instance was opened with --headless, include --headless on --screenshot as well; otherwise the binding is replaced with a visible instance.

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