power-bi-agent-skills: Skill for Claude Code

.github/skills/power-query/SKILL.md

power-query is a skill for Claude Code, Codex from kpbray/power-bi-agent-skills. It costs 33 tokens per session (3,625 once invoked), scanned A, original, MIT.

A skill for writing Power Query code in the M language. Power Query is used to connect to data sources and transform data for tools such as Power BI.

In plain words
What is it for?
Use it to connect to SQL, Excel, or APIs; filter, merge, or pivot data; create parameters; improve query performance; configure incremental refresh; and handle errors.
Why use it?
It helps turn raw data into usable tables and reduces the effort of writing connection, cleaning, combining, and refresh logic by hand.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

This is kpbray/power-bi-agent-skills's own configuration. It tells Claude Code and Codex how to work on power-bi-agent-skills itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything power-bi-agent-skills configures →

Reuse

Borrowing it

Nothing to install: this file belongs to kpbray/power-bi-agent-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/kpbray/power-bi-agent-skills/master/.github/skills/power-query/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/kpbray/power-bi-agent-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for power-query

README.md
[![agentmods](https://agentmods.dev/badge/skills/kpbray/power-bi-agent-skills/power-query/github.svg)](https://agentmods.dev/skills/kpbray/power-bi-agent-skills/power-query)
Your own site
<a href="https://agentmods.dev/skills/kpbray/power-bi-agent-skills/power-query"><img src="https://agentmods.dev/badge/skills/kpbray/power-bi-agent-skills/power-query/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for power-query

Your own site · 80×15
<a href="https://agentmods.dev/skills/kpbray/power-bi-agent-skills/power-query"><img src="https://agentmods.dev/badge/skills/kpbray/power-bi-agent-skills/power-query.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,625 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00033 $0.03625
Opus 5 $0.00016 $0.01813
Sonnet 5 $0.00007 $0.00725
Haiku 4.5 $0.00003 $0.00363

Measured 11d ago against content hash bc8220b8ca16, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

power-query scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.github/skills/power-query/SKILL.md · 600 lines

How it starts

The opening of the file, as written. The whole thing — 600 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Power Query Skill

This skill helps write Power Query (M language) for data transformation in Power BI semantic models.

When to Use This Skill

  • Connecting to data sources (SQL, Excel, APIs, etc.)
  • Transforming data (filtering, merging, pivoting)
  • Creating parameters for dynamic queries
  • Optimizing query performance (query folding)
  • Setting up incremental refresh
  • Error handling in data loads

M Language Fundamentals

Basic Structure

Every M query follows this pattern:

let
    // Step 1: Connect to source
    Source = ...,

    // Step 2: Transform
    Transformed = ...,

    // Step 3: More transformations
    Final = ...
in
    Final

Key Concepts

Concept Description
let...in Defines a query with steps
Step names Descriptive, PascalCase
#"Name" Names with spaces/special chars
each Shorthand for (_) => _
_ Current row/value in each

Data Types

// Primitive types
type text
type number
type date
type datetime
type datetimezone
type time
type duration
type logical
type null
type binary

// Complex types
type list
type record
type table
type function

// Nullable types
type nullable text

Type Conversion

// Convert to types
Text.From(123)                    // "123"
Number.From("123")                // 123
Date.From("2024-01-15")           // #date(2024, 1, 15)
DateTime.From("2024-01-15 10:30") // #datetime(2024, 1, 15, 10, 30, 0)
Logical.From(1)                   // true

// Parse with format
Date.FromText("15/01/2024", [Format="dd/MM/yyyy"])

Data Source Connections

SQL Server

let
    Source = Sql.Database("server.database.windows.net", "DatabaseName"),
    Schema = Source{[Schema="dbo", Item="TableName"]}[Data]
in
    Schema

SQL Server with Query

let
    Source = Sql.Database("server.database.windows.net", "DatabaseName", [
        Query = "SELECT * FROM dbo.Sales WHERE Year >= 2023"
    ])
in
    Source

Read the full file on GitHub · 600 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 600 lines · 33 tokens per session scan A bc8220b8ca16

Subscribe to this mod's changes

power-query is a skill published in the GitHub repository kpbray/power-bi-agent-skills (9 stars, last pushed 7mo ago), licensed MIT. It adds 33 tokens to every session and 3,625 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens