# Powerbi AI Model Graph Validator

> Use when a Power BI semantic model relationship graph must be checked for ambiguous paths, fact-to-fact chains, wrong filter direction, unsupported topology, DirectQuery/OLAP limitations, or certification risk.

- Skill: `rweisssieker-xp/powerbi-ai-model-graph-validator` (Agent Skill)
- Install (CLI): `npx skillmds@latest add rweisssieker-xp/powerbi-ai-model-graph-validator`
- Raw SKILL.md: https://api.skillmd.com/api/skills/rweisssieker-xp/powerbi-ai-model-graph-validator/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: rweisssieker-xp (https://skillmd.com/u/rweisssieker-xp)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/rweisssieker-xp/powerbi-ai-model-graph-validator

---


# Power BI AI Model Graph Validator

Use this skill before publishing or opening generated TMDL models.

## Validation Areas

- Star-schema topology: facts filter to dimensions through many-to-one relationships.
- Ambiguous paths between facts and dimensions.
- Fact-to-fact relationships and accidental bridge paths.
- Many-to-many risk and bridge-table requirements.
- Active/inactive relationship strategy and role-playing dates.
- Cross-filter direction and bidirectional filter risks.
- Unsupported DirectQuery, composite model, or live/OLAP edits.

## Output Requirements

- Include relationship inventory, invalid paths, severity, and remediation.
- Mark models as `pass`, `pass-with-risk`, or `fail`.

## Executable Support

- Use `scripts/powerbi_expert_factory.py validate --project <pbip-folder>` for the current local static model-graph gate.
- Treat any `model_graph` error as release blocking.