- Home
- Skills
- Data & Databases
- Power BI Semantic Model Review
Works with the AI Agents you already use
Power BI Semantic Model Review
Review model grain, keys, relationships, filter propagation, security assumptions, and release risks before changing a Power BI model.
$29
Power BI Semantic Model Review
Example session with this skill installed
Review this Import model. Product is one row per ProductKey; OrderLines is one row per order line with ProductKey and SalesAmount. Payments is one row per payment with OrderKey and Amount. OrderLines is joined directly to Payments on OrderKey with many-to-many, both directions. Product slicers must show sales by product; the report also sums Payments.Amount by product. An order can contain multiple products. No allocation rule exists. Static review only.
- Read your context and instructions
- Compiled the power bi semantic
Blocked for payment reporting by product: payment grain is order/payment, while product belongs to order lines. The bidirectional many-to-many relationship can associate an entire order payment with each product in the order; no supplied allocation rule makes those product amounts additive. This is a semantic concern from the stated grains, not an executed model test.
Keep Product -> OrderLines for sales. Introduce an Orders dimension with a unique OrderKey to filter OrderLines and Payments separately where appropriate. This clarifies order-level reporting but does not allocate payments to products. Hide or relabel the payment-by-product measure until the business chooses an allocation rule, then materialize or calculate that rule with explicit reconciliation.
Validate a two-product order with sales 60/40 and payment 100: sales must remain 60/40; payments by product remain undefined until allocation is approved. If proportional allocation is chosen, expected allocations are 60/40 and must total 100, including returns and zero-value-order cases. Recheck all visuals affected by the removed bidirectional path. These checks are unexecuted; no RLS or performance conclusion is supported by the supplied model description.
Connects securely to your tools. The creator never sees your data.
About this skill
Review model grain, keys, relationships, filter propagation, security assumptions, and release risks before changing a Power BI model.
What you receive
A scoped model verdict, evidence-linked structural findings, relationship recommendations, report-impact notes, and a validation matrix.
When to use it
Review supplied Power BI semantic model schemas, relationship definitions, TMDL, or model descriptions for grain, filter propagation, security assumptions, and release readiness. Focus on model structure rather than isolated DAX optimization.
What to provide
Supply the relevant code, schema, design notes, brief, or evidence together with the intended business result and constraints. Sanitized examples are sufficient to begin. The agent identifies missing details that materially affect the recommendation and labels conditional conclusions.
Boundaries
This is an advisory workflow for supplied evidence. It does not connect to a database, tenant, production system, or business application by itself. Runtime execution, deployment, remediation, and external actions are not included. No benchmark, security certification, compliance approval, or business outcome is guaranteed. Proposed validation remains unexecuted unless separately run with authorized tools.
Package
One SKILL.md with the complete workflow. One-time purchase. Your AI assistant and any source-system licenses are separate.
Requires provided schema, TMDL, or model evidence. Cannot connect to live Power BI instances or execute DAX queries against actual data. Static analysis only.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 21 days ago
Permissions
Read only user-authorized input files when provided; pasted input is sufficient. Write review artifacts only when requested. No unrestricted network access, credentials, live system changes, or automatic query execution are required.