data-goblin/power-bi-agentic-development

Power BI AI skills and Power BI agents for Claude Code and GitHub Copilot: a plugin marketplace of Power BI skills, subagents, and hooks for semantic models, DAX, TMDL, reports, and AI dashboards. Includes Microsoft Fabric skills and Fabric agents. Weekly updates.

What it solves

It provides a comprehensive library of resources to teach AI coding agents (such as Claude Code or GitHub Copilot) how to build, manage, and optimize Power BI and Microsoft Fabric artifacts. It bridges the gap between general-purpose AI agents and the specialized domain knowledge required for semantic models, reports, and deployment pipelines.

How it works

The project is structured as an Anthropic-format plugin marketplace. It provides a collection of plugins that can be installed into AI agents, which include:

  • Skills: Domain-specific knowledge and workflows that activate automatically or via manual commands to guide the agent through tasks like writing DAX or creating reports.
  • Agents: Autonomous subprocesses designed for complex, multi-step tasks, such as auditing semantic models or reviewing visual specifications.
  • Hooks: Deterministic scripts that run automatically after tool use to validate files (e.g., checking TMDL syntax or DAX references) and catch errors early.

Who it’s for

Developers and data analysts using AI coding agents to accelerate the development of Power BI reports, Microsoft Fabric environments, and semantic models.

Highlights

  • Broad Tool Support: Integrates with Tabular Editor, Power BI Desktop, and the pbir and fab CLIs.
  • Extensive Plugin Library: Includes specialized plugins for semantic models, report design, custom visuals (Deneb, Python, R, SVG), and Fabric administration.
  • Automated Validation: Uses hooks to enforce metadata standards, referential integrity, and schema validation.
  • Multi-Agent Compatibility: Works with both Claude Code and GitHub Copilot CLI.

Related

  • Project
  • Project
  • Project
  • Project
  • Project