- Home
- Skills
- Data & Databases
- Power Query M Code Review
Works with the AI Agents you already use
Power Query M Code Review
Review Power Query M transformations for join multiplication, schema drift, conversion errors, and refresh risks.
$19
Power Query M Code Review
Example session with this skill installed
Review this M step for a US-locale import of European decimal strings: Table.TransformColumns(Source, {{"Amount", each try Number.FromText(_) otherwise 0, type number}}). Input Amount text values are "1,25", "0", "bad", and null. We need German decimal interpretation and must not silently turn invalid amounts into zero. Static review.
- Read your context and instructions
- Compiled the power query m
High priority: parsing uses the current culture, while the supplied data requires German decimal interpretation. The catch-all otherwise 0 also makes invalid data indistinguishable from a legitimate zero. Retain Amount and add an explicit parse result:
let
Parsed = Table.AddColumn(Source, "AmountParse", each
if [Amount] = null then [Value = null, HasError = false]
else let p = try Number.FromText([Amount], "de-DE")
in [Value = if p[HasError] then null else p[Value],
HasError = p[HasError]], type record),
Expanded = Table.ExpandRecordColumn(Parsed, "AmountParse",
{"Value", "HasError"}, {"AmountValue", "AmountHasError"}),
Typed = Table.TransformColumnTypes(Expanded,
{{"AmountValue", type number}, {"AmountHasError", type logical}})
in
Typed
Replace the supplied conversion with this block, using its Source step. Expected cases: "1,25" -> 1.25/false; "0" -> 0/false; "bad" -> null/true; null -> null/false. Null here means missing, by assumption. These results are expected from the stated parsing rules; the M was not executed. Inspect the diagnostic rows and reconcile accepted amounts before refresh approval. Folding remains unverified.
Connects securely to your tools. The creator never sees your data.
About this skill
Review Power Query M transformations for join multiplication, schema drift, conversion errors, and refresh risks.
What you receive
Evidence-linked M-code findings, targeted corrections, explicit query-folding assumptions, and representative refresh checks.
When to use it
Review supplied Power Query M scripts for correctness, schema drift, data types, errors, join cardinality, and query folding hypotheses. Use for transformation review and refresh diagnostics rather than DAX or semantic relationship design.
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.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Data & Databases.
No live execution environment. Logic is based on static analysis of provided M code. Query folding analysis requires manual validation in Power BI via Native Query view.
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 buying a skill.
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
Nothing to install. It runs in your AI agent.
Optional execution needs your own runtime, licenses and authorized access.
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.