pbi-modelo-review

pbi-modelo-review is a skill for Claude Code, Codex from xperiun/claude-code-powerbi-skills. It costs 77 tokens per session (3,473 once invoked), scanned A, original, MIT.

A review tool for Power BI projects in PBIP format. Power BI is Microsoft's tool for building data reports and dashboards, while PBIP is its project-based file format.

In plain words
What is it for?
It is for checking a Power BI data model, assigning an overall score, grouping issues by seriousness and category, and explaining how to fix each issue.
Why use it?
It gives teams a prioritized view of model problems before they scale, migrate, hand the project to another team, or release it.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md; mentions Claude Code.

Good fit It is for checking a Power BI data model, assigning an overall score, grouping issues by seriousness and category, and explaining how to fix each issue.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/xperiun/claude-code-powerbi-skills/pbi-modelo-review
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 xperiun/claude-code-powerbi-skills --skill pbi-modelo-review
Clone the repo
git clone --depth 1 https://github.com/xperiun/claude-code-powerbi-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 pbi-modelo-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/xperiun/claude-code-powerbi-skills/pbi-modelo-review/github.svg)](https://agentmods.dev/skills/xperiun/claude-code-powerbi-skills/pbi-modelo-review)
Your own site
<a href="https://agentmods.dev/skills/xperiun/claude-code-powerbi-skills/pbi-modelo-review"><img src="https://agentmods.dev/badge/skills/xperiun/claude-code-powerbi-skills/pbi-modelo-review/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 pbi-modelo-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/xperiun/claude-code-powerbi-skills/pbi-modelo-review"><img src="https://agentmods.dev/badge/skills/xperiun/claude-code-powerbi-skills/pbi-modelo-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,473 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 $0.00077 $0.03473
Opus 5 $0.00039 $0.01736
Sonnet 5 $0.00015 $0.00695
Haiku 4.5 $0.00008 $0.00347

Measured 13d ago against content hash 93ad48229b32, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

pbi-modelo-review 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 13d 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.

claude-code/pbi-modelo-review/SKILL.md · 246 lines

How it starts

The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/pbi-modelo-review — Auditoria de modelo Power BI

📦 Distribuída publicamente: github.com/xperiun/claude-code-powerbi-skills — pasta claude-code/pbi-modelo-review/ (skill nativa) + claude-web/pbi-modelo-review.zip (upload no Claude.ai). Mudança aqui exige sincronizar lá: atualizar pasta + regenerar ZIP (Python zipfile, ver CLAUDE.md) + commit + bump CHANGELOG. Repo é open-source, leiame público — evitar referências internas (Xperiun-only) na SKILL.md.

Audita um projeto Power BI (formato PBIP) e devolve relatório priorizado com:

  • Score geral (0–100)
  • Issues agrupados por severidade (crítico / médio / leve)
  • Distribuição por categoria (6 famílias de check)
  • Cada issue com: o que é, onde está, por que importa, como corrigir (snippet quando aplicável)

Quando usar

  • Analista herdou um .pbix e quer mapa rápido de qualidade
  • Líder de dados pedindo auditoria antes de escalar/migrar modelo
  • Consultor entrando em cliente novo
  • Pré-handoff entre times
  • Você quer um "linter" rodando antes de subir pra produção

Não usar quando:

  • Quer apenas documentação descritiva → use /pbi-doc
  • Quer criar uma medida nova → use /pbi-dax-create
  • Quer otimização de performance específica de uma query (skill futura /pbi-perf)

Pré-requisitos

  1. Projeto em formato PBIP (Power BI Project) — pasta com .SemanticModel/ e .Report/. Se o usuário só tem .pbix, instruir conversão antes de prosseguir:
    • Power BI Desktop → File → Save as → Power BI Project (.pbip)
  2. Acesso aos arquivos .tmdl (via filesystem ou upload — ver "Modos de execução" abaixo)

Se faltar PBIP, retornar mensagem curta:

Esse projeto ainda está em .pbix (binário). Pra eu auditar, salva como Power BI Project: File → Save as → Power BI Project (.pbip). Vira uma pasta de texto e aí eu consigo ler. Avisa quando converter.

E encerrar — não tentar rodar nada.

Modos de execução

A skill detecta automaticamente o ambiente e adapta input/output:

Read the full file on GitHub · 246 lines

Files

What ships with it

4 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. 13d ago First seen · 246 lines · 77 tokens per session scan A 93ad48229b32

Subscribe to this mod's changes

pbi-modelo-review is a skill published in the GitHub repository xperiun/claude-code-powerbi-skills (115 stars, last pushed 4mo ago), licensed MIT. It adds 77 tokens to every session and 3,473 once invoked, about $0.0004 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 2026-08-30.