What is build-power-bi-report?

A guided builder for Power BI reports and dashboards, which are pages of charts and other visuals used to understand data. It writes the report into a Power BI Project folder.

Use it to create or update Power BI pages, dashboards, sales reports, and individual report visuals.

It turns a report request into a structured build while asking only for important missing information when the scope is large or unclear.

build-power-bi-report — Skill for Claude Code by jonathan-pap

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add jonathan-pap/powerbi-report-mcp --skill build-power-bi-report

Clone the repo

git clone --depth 1 https://github.com/jonathan-pap/powerbi-report-mcp

Made for: Claude Code.

Or install powerbi-report-builder, the plugin that ships this one along with the rest of its 3 skills, 1 MCP server.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/jonathan-pap/powerbi-report-mcp/build-power-bi-report/github.svg)](https://agentmods.dev/skills/jonathan-pap/powerbi-report-mcp/build-power-bi-report)

Your own site

<a href="https://agentmods.dev/skills/jonathan-pap/powerbi-report-mcp/build-power-bi-report"><img src="https://agentmods.dev/badge/skills/jonathan-pap/powerbi-report-mcp/build-power-bi-report/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/jonathan-pap/powerbi-report-mcp/build-power-bi-report"><img src="https://agentmods.dev/badge/skills/jonathan-pap/powerbi-report-mcp/build-power-bi-report.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 969 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.

Model	Per session	Once invoked
Fable 5.1	$0.00091	$0.00969
Opus 5.5	$0.00036	$0.00388
Sonnet 5.5	$0.00018	$0.00194
Haiku 4.5	$0.00009	$0.00097

Measured 2mo ago against content hash de9c97137248, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

build-power-bi-report 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 2mo 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.

plugin/skills/build-power-bi-report/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Build a Power BI Report

This plugin wraps the powerbi-report-mcp server, which writes directly into a .pbip (Power BI Project) folder in PBIR format. Before you start building, decide how much to ask the user — and the answer is usually "nothing, just build it."

The default is BUILD

Asking questions has a cost: every unnecessary question trains the user to dread asking for things. Default to building. Elicit only when the work is large enough that guessing wrong wastes real time.

Trigger matrix — scale questions to scope

Request scope	Questions to ask
Atomic change (1 visual, 1 property)	Zero. Build it.
Small build (2-3 visuals on existing page)	Zero. Pick sensible defaults from `pbir_model_usage`, build.
Page build (4-7 visuals, new page)	One question — the single biggest missing signal (usually audience or the 2-3 must-have measures).
Dashboard build (8+ visuals, or multi-page)	The 5-signal form, in one batch.
Blank report, no context	Offer a menu. Don't auto-build.

Bypass phrases — always skip elicitation

If the user says any of these, go straight to building: "just build it", "go", "fast mode", "skip questions", "use defaults", "your call", "surprise me", "quick", "rough version", any explicit "skip the X" or "don't ask".

The 5-signal form (dashboard scope only)

Dashboard build, five quick questions (reply "defaults" to skip):

1. Audience — executive, analyst, ops, external?         (default: executive)
2. Purpose — monitor / explore / story / audit?          (default: monitor)
3. Must-include measures — which 2-4 are non-negotiable? (default: top from pbir_model_usage)
4. Layout — KPI strip / summary-detail / drill / sidebar? (default: KPI strip)
5. Brand — hex colors, or theme defaults?                (default: theme)

Session memory

Once the user answers in a session, those answers stick for the rest of the session. Don't re-ask. Reset only on a new pbir_set_report to a different report path.

Read the full file on GitHub · 66 lines

Files

What ships with it

1 file 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.

references/full.md 5.8 KB

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.

2mo ago First seen · 66 lines · 91 tokens per session scan A de9c97137248

Subscribe to this mod's changes

build-power-bi-report is a skill published in the GitHub repository jonathan-pap/powerbi-report-mcp (21 stars, last pushed 5mo ago), licensed MIT. It adds 91 tokens to every session and 969 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-08-30.

Analytics and metrics ai-tools claude copilot data-visualization mcp-server power-bi

build-power-bi-report next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
build-power-bi-reportjonathan-pap/powerbi-report-mcp	Skill	21	5mo ago	MIT	A	91	Claude Code
run-sequencemondaycom/mcp	Skill	436	yesterday	MIT	A	150	Claude Code
requirements-authoringgriddynamics/rosetta	Skill	370	today	Apache-2.0	A	0	Claude Code
specflow-usegriddynamics/rosetta	Skill	370	today	Apache-2.0	A	27	Claude Code
memorix-troubleshootingAVIDS2/memorix	Skill	906	yesterday	Apache-2.0	A	36	Claude Code
meeting-to-dealmondaycom/mcp	Skill	436	yesterday	MIT	A	137	Claude Code
qa-knowledgegriddynamics/rosetta	Skill	370	today	Apache-2.0	A	32	Claude Code, Codex