README.md
July 27, 2026 · View on GitHub
power-bi-agentic-development
The best source for Power BI AI skills and agentic development resources in one marketplace
Teach AI agents like Claude Code or GitHub Copilot Power BI and Microsoft Fabric
Warning
These skills are under active development with a weekly release cadence, so expect regular renaming and restructuring.
Versions 26.26 through 26.38 are a deliberate breaking transition. Skills may be consolidated, renamed, removed, or made less automatic between weekly releases in this range. Pin 26.25 or earlier if you need the pre-transition skill structure and behavior; do not assume compatibility from one transition release to the next.
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: Power BI skills, Fabric skills, subagents, and hooks for coding agents. 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
Claude Code
Add the marketplace, then install plugins via /plugin and navigating to the installed marketplace.
 |
 |
| Install plugins from the marketplace | Enable marketplace auto-update |
Alternative; add plugins via command line:
claude plugin install goblin-mode@power-bi-agentic-development
claude plugin install tabular-editor@power-bi-agentic-development
claude plugin install pbi-desktop@power-bi-agentic-development
claude plugin install pbip@power-bi-agentic-development
claude plugin install semantic-models@power-bi-agentic-development
claude plugin install reports@power-bi-agentic-development
claude plugin install paginated-reports@power-bi-agentic-development
claude plugin install custom-visuals@power-bi-agentic-development
claude plugin install fabric-cli@power-bi-agentic-development
claude plugin install fabric-admin@power-bi-agentic-development
claude plugin install etl@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.
Windows long paths
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
Additional installation instructions
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.
Verify installation in Copilot CLI
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
Compatibility notes
- Skills load identically; Copilot CLI reads
skills/<name>/SKILL.md. - Agents use the
*.agent.mdextension required by Copilot CLI's documented convention. Claude Code matches any*.mdfile inagents/, 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.jsonand reference scripts using${CLAUDE_PLUGIN_ROOT}. Copilot CLI ≥ 1.0.26 (2026-04-14) setsCLAUDE_PLUGIN_ROOTfor plugin hooks (changelog); older builds do not, which causes hook commands to resolve to broken paths. Runcopilot updateif 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 validationplugins/pbi-desktop/hooks/config.yaml-- DAX references, measure metadata, referential integrity, metadata cache
Power BI and Fabric skills, agents, and hooks: available plugins
Warning
Don't install every plugin. Each skill competes for the agent's attention and context window, so install a plugin only when you need it and remove it when you don't. Prefer installing plugins scoped to a project rather than to your user, so each project carries only the skills it actually uses.
goblin-mode Get started, set up your tools, and audit and improve your whole agentic setup
| Type | Name | Description |
|---|---|---|
| Skill | help-me-get-started | A slow, friendly, jargon-free guide to agentic development for people new to agents; talks through what you want to do, feels out your role and access, teaches the five pillars (model, context, prompt, tools, environment) with local interactive explainers, and checks and installs what you need (Windows/macOS commands). Adapts pace: full tutorial or a fast install run |
| Skill | improve-my-agent-setup | Setup-wide health check with modes (shallow/deep/ultra/yolo): skills, memory, tools, STT, model independence, other clients, harness config, git, permission/isolation, network and autonomous-agent exposure, safety enforcement, secrets and PII hygiene, and workflow habits; then offers to fix what's weak. Absorbs the old /audit-context |
tabular-editor BPA rules, C# scripting, and CLI automation for Tabular Editor
| Type | Name | Description |
|---|---|---|
| Skill | bpa-rules | Create and improve Best Practice Analyzer rules for models |
| Skill | c-sharp-scripting | C# scripting and macros for TE |
| Skill | te-cli | Cross-platform Tabular Editor CLI (te, preview) for semantic models from the terminal |
| Skill | te2-cli | Tabular Editor 2 CLI usage and automation (not TE3) |
| Skill | te-docs | Tabular Editor documentation search, TE3 config files. Uses pbi-search CLI |
| Command | /suggest-rule | Generate BPA rules from descriptions |
| Agent | bpa-expression-helper | Debug and improve BPA rule expressions |
pbi-desktop Connect to, query, and modify models in Power BI Desktop
| Type | Name | Description |
|---|---|---|
| Skill | connect-pbid | Explore, query, and modify a model in Power BI Desktop, and reload/screenshot the report canvas via the Desktop Bridge |
| Agent | query-listener | Capture DAX queries from Power BI Desktop visuals in real time |
| Hook | DAX reference validation | Validates table, column, and measure references against the connected model; suggests corrections |
| Hook | Measure metadata enforcement | Blocks adding measures without DisplayFolder, Description, and FormatString |
| Hook | Referential integrity check | Reports unmatched many-side keys after relationship or column changes |
| Hook | Metadata cache refresh | Auto-snapshots model metadata on TOM connect or model modification |
| Hook | Compatibility level check | Reports features available by upgrading; optional auto-upgrade |
pbip Author and validate TMDL, PBIR, and PBIP project files
| Type | Name | Description |
|---|---|---|
| Skill | pbip | Power BI Project (PBIP) format, structure, and file types |
| Skill | tmdl | Author and edit TMDL files directly |
| Skill | pbir-format | Author and edit PBIR metadata files directly (visual.json, report.json, themes, filters, report extensions, visual calculations) |
| Agent | pbip-validator | Validate PBIP project structure, TMDL syntax, and PBIR schemas |
| Hook | PBIR validation | Validates PBIR structure, required fields, naming conventions, and schema URLs |
| Hook | Report binding validation | Validates semantic model binding (byPath directory exists; byConnection model exists via fab exists) |
| Hook | TMDL validation | Validates TMDL structural syntax |
reports Build, format, optimize, and review interactive Power BI reports
| Type | Name | Description |
|---|---|---|
| Skill | create-pbi-report | Step-by-step workflow for building a complete report from scratch via the pbir CLI: model discovery, pages, theme, visuals, field binding, filtering, formatting, validation, publishing |
| Skill | pbi-report-design | The Power BI report design canon: design identity, visual hierarchy, layout, color discipline, chart selection, KPI/table design, accessibility. Shared reference used by the other report skills |
| Skill | modifying-theme-json | Design, enforce, audit, and validate report themes through the pbir CLI |
| Skill | review-report | Actionable feedback on report quality, usage, and effectiveness; usage analysis, health checks |
| Skill | pbir-cli | Programmatic report manipulation via the pbir CLI, including live Power BI Desktop refresh and page screenshots |
| Agent | deneb-reviewer | Review Deneb visual specs for Vega/Vega-Lite syntax and conventions |
| Agent | svg-reviewer | Review SVG DAX measures for syntax and design quality |
| Agent | r-reviewer | Review R visual scripts (ggplot2) for Power BI conventions |
| Agent | python-reviewer | Review Python visual scripts (matplotlib/seaborn) for Power BI conventions |
paginated-reports Author, validate, publish, and test print-ready paginated reports
| Type | Name | Description |
|---|---|---|
| Skill | paginated-report | Author, validate, publish, and test Power BI paginated reports in RDL format (Report Builder, PBIRS/SSRS-compatible); connect to a semantic model, render to PDF/Excel |
| Hook | RDL validation | Validates .rdl structure after Write/Edit and on Bash commands touching .rdl files; blocks on structural errors only |
custom-visuals Build Deneb, Python, R, SVG, and pbiviz custom visuals for Power BI
| Type | Name | Description |
|---|---|---|
| Skill | deneb-visuals | Deneb visual creation, Vega/Vega-Lite spec authoring, Deneb best practices for PBIR reports |
| Skill | r-visuals | Custom R visuals (ggplot2) for Power BI reports |
| Skill | python-visuals | Custom Python visuals (matplotlib/seaborn) for Power BI reports |
| Skill | svg-visuals | SVG generation via DAX measures and extension measures for inline chart visualizations (sparklines, bullet charts, KPI indicators, and more) |
| Skill | powerbi-custom-visuals | Power BI developer custom visual (.pbiviz) development with the pbiviz toolchain and its MCP server: scaffold, build, debug, package, certify, publish to AppSource |
Reviewer agents for these visual types (deneb-reviewer, svg-reviewer, r-reviewer, python-reviewer) ship in the reports plugin above.
semantic-models DAX, Power Query, naming, lineage, refresh, and model auditing
| Type | Name | Description |
|---|---|---|
| Skill | semantic-model | Design, build, refresh, and review semantic models through a te-first tool cascade |
| Skill | standardize-naming-conventions | Audit and standardize naming conventions in semantic models |
| Skill | refresh-semantic-model | Trigger or troubleshoot refreshes |
| Skill | lineage-analysis | Trace downstream reports from a semantic model across workspaces |
| Skill | power-query | Write M expressions, debug query folding, execute M locally or via Fabric API |
| Skill | dax | Write, debug, and optimize DAX in semantic models. Contributed by Justin Martin |
| Agent | semantic-model-auditor | Audit semantic models for quality, memory, DAX, and design issues |
fabric-cli Remote operations via Fabric CLI; works on Pro, PPU, or Fabric
| Type | Name | Description |
|---|---|---|
| Skill | fabric-cli | Fabric CLI (fab) for any remote operation in Power BI or Fabric (works fully on Pro, PPU; Fabric not required) |
| Command | /migrating-fabric-trial-capacities | Migrate workspaces from trial to production capacity |
fabric-admin Tenant settings audits, governance, delegated overrides; requires fabric-cli
| Type | Name | Description |
|---|---|---|
| Skill | audit-tenant-settings | Audit Fabric and Power BI tenant settings, delegated overrides, and Entra security group membership |
etl Inspect, query, and transform lakehouse data with Spark, Livy, and DuckDB
| Type | Name | Description |
|---|---|---|
| Skill | executing-spark | Execute arbitrary Python or PySpark code on Fabric Spark compute without creating a notebook artifact; ephemeral Livy sessions with full Delta table access |
| Skill | using-duckdb | Query Fabric lakehouse and warehouse data with DuckDB, locally or inside a Fabric notebook; data freshness and quality checks |
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.
Built with assistance from Claude Code. AI-generated code has been reviewed but may contain errors. Use at your own risk.
Context files are human-written and revised by Claude Code after iterative use.
Kurt Buhler · Data Goblins · part of Tabular Editor