convez.ai
SkillDados & AnalyticsAvançado
data-goblin

Power BI Agentic Development

data-goblin/power-bi-agentic-development

Skills e plugins para agentes IA dominar Power BI e Fabric

Ver no GitHub
BomPluginScore · de 0 a 100

Marketplace de skills, subagents e hooks para agentes de IA (Claude Code, GitHub Copilot) trabalharem com Power BI e Microsoft Fabric. Oferece recursos especializados como CLI tools, semantic models, reports e integração com Tabular Editor para automação completa de workflows analíticos.

Instalação

$npx convez-ai data-goblin/power-bi-agentic-development

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
1,1 mil
Forks
156
Acompanhando
37
Saúde
57%
Último commit
há 1 semana
Versão
v26.45
Issues abertas
0
Contribuidores
4

Casos de uso

  • Automação de desenvolvimento de modelos semânticos no Power BI
  • Geração e otimização de relatórios via agentes IA
  • Integração com Tabular Editor para manipulação avançada de metadados
  • Automação de pipelines de deployment em Microsoft Fabric

Veredito

Solução especializada e técnica para equipes que usam agentes IA com Power BI/Fabric em produção. Ainda em desenvolvimento ativo (updates semanais), exige conhecimento profundo de BI e agentic systems para máximo aproveitamento.

README

A tradução para o português deste README ainda está na fila.

[!WARNING] Under active development with a weekly release cadence; regular renaming or restructuring.


What is agentic development?

  • Agentic development is when you use agents to help you build, manage, and optimize artifacts and software. This includes semantic models, reports, and the things around them, like workspaces, deployment pipelines, and also processes.
  • A marketplace hosts plugins that you can install. Plugins are a collection of resources that help coding agents perform better. They are typically special instruction files and scripts. Plugins can contain skills, subagents, hooks, and MCP servers focused on special topics or tasks.
  • This marketplace is focused on everything to help your agent work well with Power BI and Fabric! Read further for more information.

Installation

Here's how you get started in Claude Code; run this in the terminal to get the marketplace:

claude plugin marketplace add data-goblin/power-bi-agentic-development

Example: Using the pbir-cli with the skills

Click here for a YouTube walkthrough

pbir-cli demo

Claude Code

Add the marketplace, then install plugins via /plugin and navigating to the installed marketplace.

Alternative; add plugins via command line:

claude plugin install tabular-editor@power-bi-agentic-development
claude plugin install pbi-desktop@power-bi-agentic-development
claude plugin install semantic-models@power-bi-agentic-development
claude plugin install reports@power-bi-agentic-development
claude plugin install pbip@power-bi-agentic-development
claude plugin install fabric-cli@power-bi-agentic-development

Copilot CLI

The standalone Copilot CLI supports plugin installation from GitHub repos. Copilot CLI reads the same .claude-plugin/marketplace.json manifest this repo uses, so the marketplace and child-plugin layout works without modification.

TMDL files have a problem with repository-relative paths over 260 characters. Windows' legacy MAX_PATH blocks git clone from writing them unless long path support is enabled at both the OS and git level. Without this, copilot plugin install aborts with Filename too long.

Check useful-stuff/agent-scripts/enable-windows-longpaths.ps1 as an example of a script you can run from an elevated ps environment to enable long paths; there are other routes to do this that you can find online, too... just ask Copilot. A reboot is recommended after the registry change. This is a Windows OS limitation, documented at Maximum Path Length Limitation.

See also the below git config command:

git config --system core.longpaths true

This repository is an Anthropic-format plugin marketplace (a set of plugins), not a single distributable plugin, so the root .claude-plugin/ contains only marketplace.json. Two documented install paths work:

1. Register the marketplace once, then install named child plugins. Example:

copilot plugin marketplace add data-goblin/power-bi-agentic-development
copilot plugin install tabular-editor@power-bi-agentic-development

2. Or install a single plugin directly from its subdirectory, no marketplace registration needed. Example:

copilot plugin install data-goblin/power-bi-agentic-development:plugins/pbip

Both forms are documented in the Copilot CLI plugin reference and the plugins how-to. Inside an interactive Copilot session, /plugin install PLUGIN-NAME@MARKETPLACE-NAME is the equivalent of (1). The bare copilot plugin install data-goblin/power-bi-agentic-development (no qualifier) will not install anything useful, because the root is a marketplace catalog, not a plugin.

Inside Copilot CLI:

/env                    # Loaded instructions, MCP servers, skills, agents, plugins, LSPs, extensions
/plugin list            # Installed plugins
/skills list            # Available skills
/skills info pbip       # Details for a specific skill
/agent                  # Browse installed agents
  • Skills load identically; Copilot CLI reads skills/<name>/SKILL.md.
  • Agents use the *.agent.md extension required by Copilot CLI's documented convention. Claude Code matches any *.md file in agents/, so the dual extension works in both tools.
  • MCP servers load from .mcp.json (plugin root) or .github/mcp.json. The plugins in this repo do not currently ship MCP servers.
  • Hooks are registered via hooks.json and reference scripts using ${CLAUDE_PLUGIN_ROOT}. Copilot CLI ≥ 1.0.26 (2026-04-14) sets CLAUDE_PLUGIN_ROOT for plugin hooks (changelog); older builds do not, which causes hook commands to resolve to broken paths. Run copilot update if hooks fail to fire. Native Windows bash users may also hit a separate path-format bug tracked upstream at claude-code#11984.

Overview

The repo contains skills, agents, and hooks.

  • Skills teach agents domain knowledge and workflows. They activate automatically based on task context, or can be invoked manually with /skill-name. In Claude Code, skills and commands have coalesced; commands are simply more prescriptive skill workflows.
  • Agents are autonomous subprocesses that handle complex, multi-step tasks independently; typically used for review and validation.
  • Hooks run automatically after tool use to validate files and catch errors early. They are deterministic; they fire when a specific pattern is matched, not by LLM judgment.

Hook checks can be individually toggled via config files. Set any check to false to disable it:

  • plugins/pbip/hooks/config.yaml -- PBIR, TMDL, and report binding validation
  • plugins/pbi-desktop/hooks/config.yaml -- DAX references, measure metadata, referential integrity, metadata cache

Available plugins for Power BI and Fabric

TypeNameDescription
Skillbpa-rulesCreate and improve Best Practice Analyzer rules for models
Skillc-sharp-scriptingC# scripting and macros for TE
Skillte-cliCross-platform Tabular Editor CLI (te, preview) for semantic models from the terminal
Skillte2-cliTabular Editor 2 CLI usage and automation (not TE3)
Skillte-docsTabular Editor documentation search, TE3 config files. Uses pbi-search CLI
Command/suggest-ruleGenerate BPA rules from descriptions
Agentbpa-expression-helperDebug and improve BPA rule expressions
TypeNameDescription
Skillconnect-pbidExplore, query, and modify a model in Power BI Desktop, and reload/screenshot the report canvas via the Desktop Bridge
Agentquery-listenerCapture DAX queries from Power BI Desktop visuals in real time
HookDAX reference validationValidates table, column, and measure references against the connected model; suggests corrections
HookMeasure metadata enforcementBlocks adding measures without DisplayFolder, Description, and FormatString
HookReferential integrity checkReports unmatched many-side keys after relationship or column changes
HookMetadata cache refreshAuto-snapshots model metadata on TOM connect or model modification
HookCompatibility level checkReports features available by upgrading; optional auto-upgrade
TypeNameDescription
SkillpbipPower BI Project (PBIP) format, structure, and file types
SkilltmdlAuthor and edit TMDL files directly
Skillpbir-formatAuthor and edit PBIR metadata files directly (visual.json, report.json, themes, filters, report extensions, visual calculations)
Agentpbip-validatorValidate PBIP project structure, TMDL syntax, and PBIR schemas
HookPBIR validationValidates PBIR structure, required fields, naming conventions, and schema URLs
HookReport binding validationValidates semantic model binding (byPath directory exists; byConnection model exists via fab exists)
HookTMDL validationValidates TMDL structural syntax
TypeNameDescription
Skillpbi-report-design (Very WIP)Power BI report best practices, design and style
Skillmodifying-theme-json (WIP)Working with theme files
Skilldeneb-visualsDeneb visuals with Vega and Vega-Lite specs
Skillr-visualsCustom R visuals in Power BI reports
Skillpython-visualsCustom Python visuals in Power BI reports
Skillsvg-visualsSVG visuals via DAX measures in Power BI reports
Skillreview-report (WIP)Review Power BI reports for usage metrics and best practices
Skillpbir-cliProgrammatic report manipulation via the pbir CLI, including live Power BI Desktop refresh and page screenshots
Agentdeneb-reviewerReview Deneb visual specs for Vega/Vega-Lite syntax and conventions
Agentsvg-reviewerReview SVG DAX measures for syntax and design quality
Agentr-reviewerReview R visual scripts (ggplot2) for Power BI conventions
Agentpython-reviewerReview Python visual scripts (matplotlib/seaborn) for Power BI conventions
TypeNameDescription
Skillsemantic-modelDesign, build, refresh, and review semantic models through a te-first tool cascade
Skillstandardize-naming-conventionsAudit and standardize naming conventions in semantic models
Skillrefresh-semantic-modelTrigger or troubleshoot refreshes
Skilllineage-analysisTrace downstream reports from a semantic model across workspaces
Skillpower-queryWrite M expressions, debug query folding, execute M locally or via Fabric API
SkilldaxWrite, debug, and optimize DAX in semantic models. Contributed by Justin Martin
Agentsemantic-model-auditorAudit semantic models for quality, memory, DAX, and design issues
TypeNameDescription
Skillfabric-cliFabric CLI (fab) for any remote operation in Power BI or Fabric (works fully on Pro, PPU; Fabric not required)
Command/audit-contextReview project context files (CLAUDE.md, agents.md, memory files)
Command/migrating-fabric-trial-capacitiesMigrate workspaces from trial to production capacity
TypeNameDescription
Skillaudit-tenant-settingsAudit Fabric and Power BI tenant settings, delegated overrides, and Entra security group membership

Useful stuff

General-purpose agent resources that don't fit into a plugin: defensive hooks, patterns, and tools. See useful-stuff/.

Use or re-use of these skills

These plugins are intended for free community use.

You do not have the license to copy and incorporate them into your own products, trainings, courses, or tools. If you copy these skills - manually or by using an agent to rewrite them - you must include attribution and a link to this original project. That includes you, Microsoft.



Ver o original no GitHub

Bom para

Relacionados