Generated banner for Powerbi Report CLI
Generated logo for Powerbi Report CLI

Powerbi Report CLI

MicrosoftOfficialPublished by Microsoft

  • Skill
  • Tool integration
  • Data and AI
  • MIT
  • Low risk

From the author

Plan, design, author, preview, publish, and manage Power BI reports across requirements, page design, local PBIR/PBIP edits, validation, screenshots, Fabric upload/download, and rebinding. Use for report lifecycle work; use semantic-model-authoring for model or DAX changes and fabriciq for data questions. Triggers: plan Power BI report, design report page, edit PBIR, preview PBIP, publish report, rebind report
— the description by Microsoft

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

The powerbi-report-cli skill provides a structured, mode-based framework for managing the entire Power BI report lifecycle. It acts as a dispatcher across four distinct phases: planning (requirements and scope), design (visual and layout strategy), authoring (local PBIR/PBIP file manipulation and validation), and management (Fabric item transport and rebinding). The skill enforces strict boundaries between these modes to ensure quality, requiring explicit approval for new reports and utilizing a dedicated CLI for metadata-driven validation and authoring tasks.

What it does

  • Guides users through report requirements, scope, and page planning.
  • Provides design contracts for visual archetypes, layouts, and branding.
  • Enables local editing, validation, and previewing of PBIR and PBIP files.
  • Handles report item transport to and from Microsoft Fabric.
  • Supports re-theming, conditional formatting, and visual configuration.
  • Enforces a mandatory approval gate for greenfield report development.

When to use it

  • When planning a new Power BI report from a semantic model.
  • When you need to define a professional design brief or layout strategy.
  • When editing local PBIR/PBIP files, including visuals, filters, and themes.
  • When validating report structure and formatting before deployment.
  • When publishing or managing report items within a Fabric workspace.

Advantages

  • Ensures consistent report quality through a structured, multi-mode workflow.
  • Prevents premature publishing by enforcing a mandatory approval barrier.
  • Uses a dedicated CLI to eliminate guesswork in PBIR schema and property editing.
  • Maintains clear separation between design intent and technical implementation.
  • Provides robust validation tools to catch errors before Fabric deployment.

Usage examples

“Create a new executive report from this semantic model.”
The agent enters planning mode, inspects the model, generates a report spec, and requests user approval before proceeding.
“Design an operational page and choose the right charts.”
The agent enters design mode, produces a design brief with page archetypes and chart recommendations.
“Add a KPI page to this PBIP, validate it, and take screenshots.”
The agent enters authoring mode, modifies the local PBIP files, runs validation, and captures screenshots for review.
“Publish this local PBIP to my Fabric workspace and rebind it.”
The agent enters management mode, performs the upload to Fabric, and completes the rebind operation.

Install

  1. Download the skill as a ZIP:

    https://autogineer.com/agent-skills/microsoft/powerbi-report-cli/download
  2. Unzip it into the cross-client skills folder of your project:

    mkdir -p .agents/skills && unzip powerbi-report-cli.zip -d .agents/skills

Documentation by Microsoft

Telemetry — MANDATORY. Every api.fabric.microsoft.com call must carry x-ms-fabric-skill: powerbi-report-cli (az rest: --headers "x-ms-fabric-skill=powerbi-report-cli"), including every LRO poll, fabric_lro and retry. Snippets omit it — add it anyway.

CRITICAL NOTES

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

  2. To find item details, including its ID, from a workspace ID, item type, and item name: list all items of that type in that workspace, then use JMESPath filtering.

  3. Use powerbi-report-cli for the report artifact: requirements, design, PBIR/PBIP page and visual edits, preview, and publishing. Semantic model, measure, and DAX work belongs to a semantic-model skill. Natural-language questions about report data belong to fabriciq.

Power BI Reports - CLI Skill

This skill owns the Power BI report lifecycle end to end: requirements and scope, visual design, local PBIR/PBIP authoring and preview, and report-item transport to and from Microsoft Fabric.

It is a mode dispatcher and intentionally contains no detailed procedures. Select the mode that matches the request, then read the matching mode reference end to end before acting. The mode file holds the required workflow, commands, payloads, templates, and failure rules.

Mode Selection

ModeUse when the request...Existing route examplesRead first
planningcreates a new report/dashboard and needs requirements, model/dependency inspection, scope, a page plan, and approval before implementationcreate a report, build a dashboard, create from a semantic model, plan then implement, walk me through creating a reportreferences/planning.md, then references/planning-part-02.md
designdecides what a report should look like: tone, signature, page archetype, chart type, layout, color, typography, theme direction, accessibility, brand application, redesign, or critiquedesign a Power BI report, make the dashboard professional, choose a chart, apply a brand, redesign the report, create a design briefreferences/design.md
authoringreads or edits local PBIR/PBIP files, validates them, previews the report, or captures screenshotsedit PBIR, create/add a report page or visual, format a visual, add filters/slicers/bookmarks/themes, validate PBIR, preview/reload/screenshot in Desktop or servicereferences/authoring.md
managementmoves a report definition to or from Fabric or manages the workspace report itempublish/upload/download PBIR or PBIP, list reports, get/update/delete a report, rebind a reportreferences/management.md

Mode Boundary Rules

  • Classify by intent, not by which file or tool is already open.

  • design decides what the report should look like; authoring writes the PBIR that realizes it. Choosing a chart type is design; encoding it into visual.json is authoring.

  • Restyling or reformatting an existing local report is authoring, even when the request uses design language. Use design when the user wants advice or a design contract rather than a file change.

  • authoring changes local files and performs preview/validation. It does not publish to Fabric.

  • management transports definitions and manages Fabric report items. It does not invent or directly author PBIR content.

  • planning owns the guided requirements-to-approval flow for a new report. A focused edit to an existing report goes directly to authoring.

A greenfield request can span modes in this order:

planning -> design -> authoring -> management

Handle one mode at a time. Announce each switch and read the new mode reference before starting that part. The planning approval gate is a turn boundary: never build or publish until the user explicitly approves the locked spec in a later reply.

GREENFIELD APPROVAL BARRIER — MANDATORY. When a new-report request asks to plan, build, and/or publish but the user has not approved a locked spec in a prior reply, set the current phase to approval_pending and keep planning as the only active mode. In this phase, do not load authoring or management, edit/scaffold PBIR or semantic-model files, generate synthetic data, call Fabric write APIs, or publish. Persist _brief/report-spec.md, ask for explicit approval, and end the turn. The build/publish wording in the original request is desired future scope, not approval to cross this barrier.

Required Deliverable by Mode

ModeCompletion requirement
planningPersist _brief/report-spec.md or the user-named equivalent, ask for explicit approval, and stop before implementation.
designProduce the complete Design Brief: contract, including design_identity and a page archetype/layout contract for every page. Do not edit PBIR or call Fabric APIs.
authoringPersist the requested PBIR/PBIP changes, validate each logical batch, then complete the selected preview and screenshot-review workflow required by the authoring reference. Do not publish.
managementComplete the requested Fabric report operation, including LRO polling and documented readback verification.

Rules

MUST
  • Select the narrowest mode that fully covers the current request.

  • Read references/<mode>.md end to end before the first command or file edit in that mode. When an already-loaded mode explicitly routes one narrow cross-mode operation to a named topic reference, treat that topic reference as the complete handoff; do not load the target mode's umbrella file unless the work expands beyond that operation.

  • In planning mode, also read references/planning-part-02.md before producing _brief/report-spec.md; it contains the required canonical design contract and approval checks.

  • Across a multi-turn task, retain a compact working state containing resolved workspace/item/model IDs, local and downloaded paths, and references already read. Reuse it in later turns unless the user explicitly requests a fresh query or the preceding operation invalidated a value.

  • Preserve every argument and safety boundary documented by the selected mode.

  • Announce and perform an explicit mode switch when the request crosses a boundary.

  • Use the powerbi-report-author CLI metadata and validation surfaces instead of guessing PBIR schemas, roles, formatting properties, selectors, or enum values.

  • Keep local edits local unless the user explicitly requests publishing.

  • Resolve Fabric workspace and item IDs by listing and filtering rather than guessing identifiers.

  • Produce the artifact the user requested; reading or summarizing a reference is not task completion.

PREFER
  • Infer facts already present in the prompt, semantic model, existing PBIP, or prior approved spec instead of asking again.

  • Load only the selected mode and its directly relevant topic references.

  • Reuse reference guidance already loaded in the current task. Open a new reference only when the requested operation or an observed mismatch requires it.

  • Preserve the user's existing project structure, schemas, host, operation, binding, and delivery target unless the selected mode explicitly requires a change.

AVOID
  • Acting from this dispatcher without reading the selected mode reference.

  • Reloading this dispatcher, a mode file, or a topic reference already read in the current task solely because the conversation advanced to a later turn.

  • Loading a retired sibling skill name; planning, design, authoring, and management are modes of this skill.

  • Editing PBIR or calling Fabric APIs in planning or design.

  • Publishing from authoring, or authoring PBIR content from management.

  • Bypassing the planning approval gate because the original request also asked to build or publish.

<!-- BEGIN GENERATED REFERENCE INDEX -->

Complete Reference Index

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

Authoring
Design
Mode Guides

<!-- END GENERATED REFERENCE INDEX -->

Examples

User requestMode
"Create a new executive report from this semantic model."planning
"Design an operational page and choose the right charts."design
"Add a KPI page to this PBIP, validate it, and take screenshots."authoring
"Publish this local PBIP to my Fabric workspace and rebind it."management

Route Compatibility

The merged skill preserves the four previous route surfaces. Treat the following phrases as explicit aliases for the corresponding mode:

ModePreserved route phrases
planningcreate a report; build a report; create a dashboard; create a new report from scratch; create a report from a semantic model or dataset link; build a report for this model; make me a dashboard; plan then implement; walk me through creating a report
designdesign Power BI report; make dashboard look professional; choose chart type; apply brand to report; redesign report; create design brief; Power BI report design archetype
authoringedit PBIR; create Power BI report page; add visual to PBIP; format report visual; validate Power BI report; preview Power BI report; Power BI Desktop preview status; preview report in service; preview report in browser; screenshot report page; screenshot all report pages; list preview hosts; implement dashboard in PBIP; add dashboard visuals to report; implement an approved PBIP report spec; edit PBIR pages/visuals; edit a Power BI report
managementupload PBIR report definition; upload Power BI report; download PBIR definition; publish PBIR definition; publish Power BI report to Fabric; manage Power BI reports; list workspace reports

Files

references/management-part-03.md

powerbi-report-cli management mode -- Power BI Report Items in Fabric - Part 3

Continuation of management.md. Open this file directly from the skill reference index.

Must/Prefer/Avoid

MUST
  • ALL PBIR content MUST go through the authoring mode — this is the single most important rule. Whether creating a brand-new report or modifying an existing one, every PBIR file (definition.pbir, report.json, version.json, pages.json, page configs, visuals, filters, formatting, themes, expressions) must be authored using the authoring mode. Follow its guidance for correct PBIR structure, schemas, and field values. Use its CLI tools for validation. Never construct any PBIR JSON from memory or guesswork — not even "simple" files like definition.pbir or version.json. This mode is strictly for API transport (download, encode, upload) — it does not author PBIR content.

  • Always pass --resource "https://api.fabric.microsoft.com" to az rest — omitting it causes silent auth failures.

  • Always pass ?format=PBIR on getDefinition — without it, older reports return PBIR-Legacy format which is not supported by this skill.

  • Only work with PBIR format — if a definition comes back with "format": "PBIR-Legacy", stop and tell the user that PBIR-Legacy is not supported.

  • Include ALL definition parts in updateDefinition — modified + unmodified. The API replaces the entire definition; omitting parts deletes them.

  • Base64-encode all part payloads — every payload value must be base64-encoded.

  • Use powerbi-report-author pack/unpack for every base64 + directory-walk transport step — powerbi-report-author >= 0.3.0 is a hard requirement for this skill's primary workflows. Management invokes these deterministic transport helpers but still never authors PBIR content. The fallback section is conceptual safety guidance only, not an executable non-CLI workflow.

  • Use byConnection in definition.pbir for Fabric API — byPath is for local/Git scenarios only.

  • Poll LRO to completion — Create, getDefinition, and updateDefinition return 202 Accepted. Poll until terminal state.

  • Always use --verbose on LRO operations — az rest does not expose response headers by default. Without --verbose, you cannot capture the x-ms-operation-id header needed for polling, and there is no other way to retrieve it after the fact.

  • Clean up temporary files — delete any local temp directories and files (decoded definitions, JSON payloads) created during the workflow once the operation completes. These can be large and accumulate on the user's machine.

  • Verify semantic-model bindings after the target model is resolved — once the report's target semantic model is known (whether by a fresh deploy through an available semantic-model authoring skill or by selecting an existing workspace model), download its deployed TMDL once and build one compact inventory of table, column, and measure names. Compare all PBIR bindings (Entity, queryRef, nativeQueryRef, filter Source/Entity references) against that inventory. This applies to both branches: even a hand-off deploy may rename or transform the model during publish, so the diff is not optional. Do not also connect through the modeling MCP or separately enumerate tables, columns, and measures when the downloaded TMDL is complete and parseable. Use granular live-model inspection only when TMDL retrieval fails or the first diff identifies an ambiguous or missing binding. If names differ but models are structurally equivalent (same columns/measures), remap all table-qualified bindings via the authoring mode. If the models are not structurally equivalent, prompt the user before attempting to re-author — explain which tables/columns/measures don't match and ask whether to proceed.

  • Local edits stay local by default — when a user requests changes to a local .pbip report, apply the changes to the local files only. Never publish or overwrite the remote report with local changes until the user explicitly gives permission to do it. Do not publish to Fabric unless the current request explicitly asks to publish, upload, push, or deploy those local changes. Never infer publish permission from approval of the report design, edits, validation, screenshots, preview, or an earlier publish. If intent is absent, ambiguous, or you are unsure, keep the changes local and do not publish — do not pack, make a remote write, or ask to publish. For example, if the user only asks to modify a report against the service host, make the local changes, validate, and show the preview; do not publish until the user later asks you to. Even with a publish request, never call updateDefinition until the user confirms they agree to overwrite the existing remote report. When the user does request publishing a local .pbip, follow the Publishing a local .pbip workflow in management-part-04.md workflow: (a) confirm the target workspace once up front, (b) prompt publish-the-local-model vs. connect-to-an-existing-workspace-model, (c) on the publish-model branch, check whether a semantic-model authoring skill is available in the current session and degrade gracefully if not, (d) confirm create-new vs. update-existing for the report itself.

PREFER
  • Soft delete over hard delete — allows recovery.

  • az rest with JMESPath --query for filtering — built-in JSON parsing, no extra tools needed.

  • File-based pack/unpack handoff for any shell with uncertain pipe encoding — save the synchronous 200 response body or terminal LRO result body with az rest --output-file payload.json before unpack --input payload.json, and pack --raw --out body.json then az rest --body @body.json.

  • One compact run-state record — retain workspace, model, and report names and IDs; local and downloaded definition paths; and active LRO endpoints. Reuse those values across later turns instead of repeating discovery or directory inspection, unless the user explicitly asks for a fresh listing.

AVOID
  • Hand-writing or directly constructing PBIR JSON — whether creating new files or modifying existing ones, all PBIR content (definition.pbir, report.json, version.json, pages, visuals, filters, formatting, themes, expressions) must go through the authoring mode. Never construct any PBIR JSON from memory or guesswork — not even "simple" structural files. No exceptions.

  • PBIR-Legacy format — do not create, read, or update PBIR-Legacy definitions. Only modern PBIR format is supported.

  • Sending only modified parts in updateDefinition — the API replaces the full definition; missing parts are deleted.

  • Using byPath in definition.pbir for API payloads — only works for local/Git scenarios.

  • Hardcoded workspace/report IDs — resolve dynamically via the List APIs.

  • Skipping LRO polling — definition operations may be async; always check for 202 responses.

  • Omitting ?format=PBIR on getDefinition — may return unusable PBIR-Legacy format.

  • Retrying a create POST after receiving 202 — risks creating duplicates. See Long-Running Operations (LRO) in management-part-02.md for the correct recovery pattern.

  • Using jq/base64/find/PowerShell hand-walking instead of installing or upgrading powerbi-report-author — the fallback section documents conceptual safety requirements only; it is not a supported executable workflow in this skill.

Requirements and compatibility

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Security

What our scanner noticed· Low risk

  • Phrasing that asks for actions without confirmation
  • Instructions that use the network

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Attribution and licence

Published by
Microsoft
Publisher
Microsoft (Official)
Source
microsoft/skills-for-fabric · skills/powerbi-report-cli · commit f8fac11
Licence
MIT License (redistribution allowed)
  • LICENSE (added by AutoGineer from LICENSE)
  • ATTRIBUTION.md (written by AutoGineer)
Synced
Also distributed in
microsoft/skills-for-fabric

AutoGineer is not affiliated with or endorsed by Microsoft or Microsoft.

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download powerbi-report-cli.zip