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/authoring/conditional-formatting-part-05.md

Conditional Formatting Patterns - Part 5

Contents

  • Type 2: Rules-Based Formatting

    • Number vs percent thresholds (and percentile)

    • Rule bounds: one-sided vs two-sided ranges

Continuation of conditional-formatting.md. Open this file directly from the skill reference index.

Type 2: Rules-Based Formatting

Applies colors based on value conditions using Conditional.Cases[] inside a color property. The structure is the same for charts (dataPoint.fill) and tables/matrices (values.backColor or values.fontColor).

⚠️ There is no backColorRule or fontColorRule property — these do not exist. Rules are expressed as Conditional.Cases[] inside the standard color property path (backColor.solid.color.expr.Conditional).

fontColor is skipped on sparkline columns. A backColor/fontColor rule works on ordinary columns; a fontColor rule targeting a sparkline column is ignored (backColor still applies).

⚠️ Every color band that users must edit in Power BI Desktop must be an explicit Cases[] entry. Desktop renders DefaultValue, but its conditional-formatting dialog does not expose that fallback as an editable rule row. Do not encode an intended low/red band only as DefaultValue. Add an explicit comparison for it (for example, < 1000000) and reserve DefaultValue for blanks or otherwise unmatched values. It may repeat the lowest-band color when that is the safest fallback.

Table/matrix example (entry in values array):

{
  "properties": {
    "backColor": {
      "solid": {
        "color": {
          "expr": {
            "Conditional": {
              "Cases": [
                {
                  "Condition": {
                    "Comparison": {
                      "ComparisonKind": 2,
                      "Left": { "Measure": { "Expression": { "SourceRef": { "Entity": "Sales" } }, "Property": "TotalProfit" } },
                      "Right": { "Literal": { "Value": "500D" } }
                    }
                  },
                  "Value": { "Literal": { "Value": "'#1AAB40'" } }
                },
                {
                  "Condition": {
                    "Comparison": {
                      "ComparisonKind": 2,
                      "Left": { "Measure": { "Expression": { "SourceRef": { "Entity": "Sales" } }, "Property": "TotalProfit" } },
                      "Right": { "Literal": { "Value": "0D" } }
                    }
                  },
                  "Value": { "Literal": { "Value": "'#FFFFFF'" } }
                },
                {
                  "Condition": {
                    "Comparison": {
                      "ComparisonKind": 3,
                      "Left": { "Measure": { "Expression": { "SourceRef": { "Entity": "Sales" } }, "Property": "TotalProfit" } },
                      "Right": { "Literal": { "Value": "0D" } }
                    }
                  },
                  "Value": { "Literal": { "Value": "'#D64554'" } }
                }
              ]
            }
          }
        }
      }
    }
  },
  "selector": {
    "data": [{ "dataViewWildcard": { "matchingOption": 1 } }],
    "metadata": "Sum(Sales.TotalProfit)"
  }
}

The three ordered cases cover every value (>= 500 green, >= 0 white, < 0 red) — no DefaultValue needed; each is an editable rule in the dialog.

Chart example (entry in a supported chart object array):

{
  "properties": {
    "<colorProperty>": {
      "solid": {
        "color": {
          "expr": {
            "Conditional": {
              "Cases": [
                {
                  "Condition": {
                    "Comparison": {
                      "ComparisonKind": 2,
                      "Left": { "Measure": { "Expression": { "SourceRef": { "Entity": "Sales" } }, "Property": "TotalProfit" } },
                      "Right": { "Literal": { "Value": "500D" } }
                    }
                  },
                  "Value": { "Literal": { "Value": "'#1AAB40'" } }
                },
                {
                  "Condition": {
                    "Comparison": {
                      "ComparisonKind": 3,
                      "Left": { "Measure": { "Expression": { "SourceRef": { "Entity": "Sales" } }, "Property": "TotalProfit" } },
                      "Right": { "Literal": { "Value": "500D" } }
                    }
                  },
                  "Value": { "Literal": { "Value": "'#118DFF'" } }
                }
              ]
            }
          }
        }
      }
    }
  },
  "selector": {
    "data": [{ "dataViewWildcard": { "matchingOption": 1 } }]
  }
}

Replace <colorProperty> and its containing object using the capability matrix. For example:

ResultObjectReplace <colorProperty> with
Bar/column/slice/rectangle/bubble colordataPointfill
Full line/area series colordataPointfill
Single-series line/area marker color by categorydataPointfill
Single-series line segment colorlineStylesstrokeColor
Data-label colorlabelscolor

Key rules:

  • All keys are PascalCase: Conditional, Cases, Condition, Comparison, ComparisonKind, Value, and DefaultValue.

  • The operator is Comparison (not Compare).

  • Left must be a self-aggregating expression: use Measure (already aggregated) or wrap a Column in Aggregation { Expression: Column, Function: N }. A raw Column in Left breaks the visual. See Aggregation: columns vs. measures for the full Function enum and valid/invalid examples.

  • DefaultValue provides the fallback color when no case matches.

  • For "is not equal", use Not { Expression: { Comparison: { ComparisonKind: 0, ... } } }; there is no NotEqual ComparisonKind.

Selector requirements (critical — wrong selector silently drops all formatting):

Visual typeRequired selectorNotes
Tables/matrices{ "data": [{ "dataViewWildcard": { "matchingOption": 1 } }], "metadata": "<queryRef>" }Both data AND metadata required — either alone fails
Single-series chart points{ "data": [{ "dataViewWildcard": { "matchingOption": 1 } }] }Matches identity-bearing instances and excludes totals
Category-role chart rules{ "data": [{ "roles": ["Category"] }] }Replace Category with the visual's actual category role name
Dynamic legend-series rules{ "data": [{ "roles": ["Series"] }], "hierarchyMatching": 1 }hierarchyMatching: 1 is Partial; it enables per-series evaluation

ComparisonKind values:

ValueOperatorMeaning
0==Equal
1>Greater Than
2>=Greater Than or Equal
3<Less Than
4<=Less Than or Equal
Number vs percent thresholds (and percentile)

A rule threshold is the Right operand of each Comparison. In Power BI Desktop the rules dialog exposes a per-boundary Number / Percent dropdown; these are the only two threshold kinds. They encode differently:

Threshold kindMeaningRight encoding
Number (default)A fixed, absolute cutoffLiteral — { "Literal": { "Value": "500D" } }
PercentA percent of the based-on field's min→max range; recomputed as the data changesRangePercent (see below)
PercentileNot a conditional-formatting threshold kind— unsupported; see note

📊 Where the Percent kind is available (tables/matrices and charts). The Percent (RangePercent) kind is offered for any Type-2 rules visual that has a category grouping — table/matrix rows, or a chart Category/Axis. Two preconditions are enforced by Desktop (disableAutoRange = !hasGrouping || totalMatchingOption.disableAutoRange):

  • Grouping required. A visual with no grouping (e.g. a single-value card) offers Number only.

  • Instances, not totals. The rule must target instances — use the instances-only selector matchingOption: 1 (InstancesOnly). With InstancesAndTotals (0, the default) or TotalsOnly (2) Desktop disables Percent and the boundary falls back to Number.

Number thresholds on a percentage-valued measure. When the based-on field is itself a percentage (e.g. Margin % stored as 0.25 for 25%), a Number threshold must be the actual decimal value, not the display percentage: 0.25D, never 25D. This matches Desktop's guidance to pick Number (not Percent) and type decimals for percentage fields. The Percent kind below is a different concept — percent of the value range, not the field's own units.

🟢 Detect a percentage field before authoring a Number threshold. Read the based-on field (the rule's Left) in the semantic model and inspect its formatString — the TMDL measure/column line, or the measure/column formatString in model.bim. Look for an active % token — a % that is not escaped as \% and not inside a quoted literal ("…"). An active % (e.g. 0.0%, #,0.0%;-#,0.0%, 0.0%;-0.0%;0.0%) means the field is stored as a decimal and Power BI multiplies by 100 for display — choose a Number Literal and type the decimal (0.25D for 25%). An escaped or quoted percent sign (0\%, 0"%") prints a literal % without ×100 scaling, so the stored value already equals the displayed number — type it as-is (25 displays 25% → author 25D). When unsure, read the field's stored values against its display: 0.0% storing 0.25 shows 25% (author 0.25); 0\% storing 25 shows 25% (author 25). If there is no active %, type the value as-is. validate runs structurally on the PBIR only and does not read the model, so it cannot enforce this — the agent must perform the check (needs a local .pbip semantic model or a live model via Modeling MCP). Do not use the Percent (RangePercent) kind just because the field is a percentage — that is a different concept (percent of the value range).

Percent-of-range thresholds (RangePercent). A Percent boundary is not a static number: Desktop resolves it against the current minimum and maximum of the based-on field, so the effective cutoff moves as the data range changes (e.g. "top 25% of the range"). Encode the threshold's Right as a RangePercent whose Min/Max are the global aggregate min/max of the based-on field:

  • Percent is a fraction 0–1 (Desktop shows 0–100; divide by 100 — 25 → 0.25).

  • Min / Max wrap the based-on field in ScopedEval → Aggregation (Function 3 = Min, 4 = Max) → ScopedEval with an AllRolesRef scope. The field inside Min/Max must be the same field as the rule's Left (the based-on field).

{
  "Condition": {
    "Comparison": {
      "ComparisonKind": 2,
      "Left": { "Measure": { "Expression": { "SourceRef": { "Entity": "Sales" } }, "Property": "TotalProfit" } },
      "Right": {
        "RangePercent": {
          "Percent": 0.25,
          "Min": {
            "ScopedEval": {
              "Expression": {
                "Aggregation": {
                  "Expression": {
                    "ScopedEval": {
                      "Expression": { "Measure": { "Expression": { "SourceRef": { "Entity": "Sales" } }, "Property": "TotalProfit" } },
                      "Scope": [{ "AllRolesRef": {} }]
                    }
                  },
                  "Function": 3
                }
              },
              "Scope": []
            }
          },
          "Max": {
            "ScopedEval": {
              "Expression": {
                "Aggregation": {
                  "Expression": {
                    "ScopedEval": {
                      "Expression": { "Measure": { "Expression": { "SourceRef": { "Entity": "Sales" } }, "Property": "TotalProfit" } },
                      "Scope": [{ "AllRolesRef": {} }]
                    }
                  },
                  "Function": 4
                }
              },
              "Scope": []
            }
          }
        }
      }
    }
  },
  "Value": { "Literal": { "Value": "'#1AAB40'" } }
}

The Min/Max shape is fixed boilerplate — only the inner based-on field and the Percent value change per rule. Keep the two boundaries within a single rule the same kind (both Number, or both Percent) — see Rule bounds: one-sided vs two-sided ranges.

Charts use the identical RangePercent encoding. Percentage thresholds are not table/matrix-only — place the same Right RangePercent block in the chart's color object (e.g. dataPoint.fill; see the Type 2 chart example and capability matrix for the object/property per visual) and use a chart instances-only selector { "data": [{ "dataViewWildcard": { "matchingOption": 1 } }] } (no metadata). The Min/Max inner field is still the rule's based-on Left, and the same grouping/instances preconditions above apply (the chart's Category/Axis provides the grouping).

⚠️ Percentile thresholds are not supported in conditional formatting on any visual — tables, matrices, or charts. The rules dialog offers only Number and Percent — there is no percentile threshold kind, and there is no expression that encodes one here. (The Percentile { Expression, K, Exclusive } expression is a DAX aggregation for summarizing a field, not a CF threshold.) To approximate a percentile cutoff, add a measure that computes the percentile (e.g. PERCENTILEX.INC) and compare the based-on field against that measure or an absolute Number.

ℹ️ Gradient (color scale) stops are not percent/percentile either. A FillRule min/mid/max stop takes only auto (omit value → Desktop uses the data's lowest/highest) or an absolute custom number (value Literal). Do not place a RangePercent in a gradient stop — percent semantics are a rules-only feature. See Type 1.

Rule bounds: one-sided vs two-sided ranges

One-sided Cases[] entries — a single Comparison like the examples above — are valid and render correctly. Author them freely; do not pad rules with synthetic sentinel bounds to force a closed range. Encode every color band — including the default/"else" color — as an explicit Cases[] entry rather than relying on DefaultValue (see Type 2: Rules-Based Formatting).

Use a two-sided Condition.And band only for interior bands that need both a floor and a ceiling. Keep the outermost bands open-ended (a single Comparison) so the full data domain stays covered — do not add sentinel outer bounds unless they are verified business-domain limits, since a sentinel leaves values beyond it uncovered. Both Comparisons in an interior band use the same threshold kind on their Right operands (both Literal Number, or both RangePercent):

"Cases": [
  {
    "Condition": { "Comparison": { "ComparisonKind": 2, "Left": { "Measure": { "Expression": { "SourceRef": { "Entity": "Sales" } }, "Property": "TotalProfit" } }, "Right": { "Literal": { "Value": "500D" } } } },
    "Value": { "Literal": { "Value": "'#1AAB40'" } }
  },
  {
    "Condition": {
      "And": {
        "Left":  { "Comparison": { "ComparisonKind": 2, "Left": { "Measure": { "Expression": { "SourceRef": { "Entity": "Sales" } }, "Property": "TotalProfit" } }, "Right": { "Literal": { "Value": "0D" } } } },
        "Right": { "Comparison": { "ComparisonKind": 3, "Left": { "Measure": { "Expression": { "SourceRef": { "Entity": "Sales" } }, "Property": "TotalProfit" } }, "Right": { "Literal": { "Value": "500D" } } } }
      }
    },
    "Value": { "Literal": { "Value": "'#FFFFFF'" } }
  },
  {
    "Condition": { "Comparison": { "ComparisonKind": 3, "Left": { "Measure": { "Expression": { "SourceRef": { "Entity": "Sales" } }, "Property": "TotalProfit" } }, "Right": { "Literal": { "Value": "0D" } } } },
    "Value": { "Literal": { "Value": "'#D64554'" } }
  }
]

Rules:

  • And { Left, Right } and Comparison { ComparisonKind, Left, Right } are PascalCase (matches the Desktop serializer).

  • Every Comparison in a rule must use the same Left (the based-on field), and both bounds of an interior And band must use the same threshold kind on Right.

  • Desktop's canonical operators are lower >= (2) and upper < (3) — keep that ordering so contiguous [min, max) bands leave no gaps or overlaps.

  • Cases evaluate top-down (first match wins); order them so the intended band is reached first.

  • Keep the outermost bands open-ended so the full domain is covered; reach for an interior And band only where a color needs both a floor and a ceiling.

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