Power Bi AI Readiness
DKH-DK/Self-Service-Power-BI-Fabric
Score and prepare Power BI semantic models for AI (Fabric Data Agent / Copilot).
Audita modelo Power BI (PBIP) e gera relatório priorizado com anti-patterns, score 0-100 e recomendações acionáveis.
$ npx skills add xperiun/skills-xperiun-free --skill pbi-modelo-review -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install xperiun/skills-xperiun-free pbi-modelo-review --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/xperiun/skills-xperiun-free.git skills-src && mkdir -p .claude/skills && cp -r skills-src/claude-code/pbi-modelo-review .claude/skills/pbi-modelo-review && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "pbi-modelo-review" agent skill from https://github.com/xperiun/skills-xperiun-free/tree/main/claude-code/pbi-modelo-review into .claude/skills/pbi-modelo-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pbi-modelo-review", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/xperiun/skills-xperiun-free/tree/main/claude-code/pbi-modelo-reviewType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add xperiun/skills-xperiun-free --skill pbi-modelo-review -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install xperiun/skills-xperiun-free pbi-modelo-review --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/xperiun/skills-xperiun-free.git skills-src && mkdir -p .agents/skills && cp -r skills-src/claude-code/pbi-modelo-review .agents/skills/pbi-modelo-review && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "pbi-modelo-review" agent skill from https://github.com/xperiun/skills-xperiun-free/tree/main/claude-code/pbi-modelo-review into .agents/skills/pbi-modelo-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pbi-modelo-review", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add xperiun/skills-xperiun-free --skill pbi-modelo-review -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install xperiun/skills-xperiun-free pbi-modelo-review --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/xperiun/skills-xperiun-free.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/claude-code/pbi-modelo-review .cursor/skills/pbi-modelo-review && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "pbi-modelo-review" agent skill from https://github.com/xperiun/skills-xperiun-free/tree/main/claude-code/pbi-modelo-review into .cursor/skills/pbi-modelo-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pbi-modelo-review", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/xperiun/skills-xperiun-free.git --path claude-code/pbi-modelo-review--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add xperiun/skills-xperiun-free --skill pbi-modelo-review -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install xperiun/skills-xperiun-free pbi-modelo-review --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/xperiun/skills-xperiun-free.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/claude-code/pbi-modelo-review .gemini/skills/pbi-modelo-review && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "pbi-modelo-review" agent skill from https://github.com/xperiun/skills-xperiun-free/tree/main/claude-code/pbi-modelo-review into .gemini/skills/pbi-modelo-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pbi-modelo-review", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install xperiun/skills-xperiun-free pbi-modelo-reviewInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add xperiun/skills-xperiun-free --skill pbi-modelo-review -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/xperiun/skills-xperiun-free.git skills-src && mkdir -p .github/skills && cp -r skills-src/claude-code/pbi-modelo-review .github/skills/pbi-modelo-review && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "pbi-modelo-review" agent skill from https://github.com/xperiun/skills-xperiun-free/tree/main/claude-code/pbi-modelo-review into .github/skills/pbi-modelo-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pbi-modelo-review", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add xperiun/skills-xperiun-free --skill pbi-modelo-review -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install xperiun/skills-xperiun-free pbi-modelo-review --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/xperiun/skills-xperiun-free.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/claude-code/pbi-modelo-review .opencode/skills/pbi-modelo-review && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "pbi-modelo-review" agent skill from https://github.com/xperiun/skills-xperiun-free/tree/main/claude-code/pbi-modelo-review into .opencode/skills/pbi-modelo-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pbi-modelo-review", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
pbi-modelo-reviewAudita modelo Power BI (PBIP) e gera relatório priorizado com anti-patterns, score 0-100 e recomendações acionáveis.
Pbi Modelo Review is an agent skill from xperiun/skills-xperiun-free. Audita modelo Power BI (PBIP) e gera relatório priorizado com anti-patterns, score 0-100 e recomendações acionáveis. Use quando o usuário pedir "audita esse modelo", "revisa esse power bi", "tá bem feito?", "manda ver no review", ou apontar uma pasta PBIP pra análise crítica.
Its SKILL.md is about 2.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including reference files (for example `references/checks.md`, `references/design-tokens.md` and `templates/relatorio.md`).
It sits in Data & Analytics. It works with Power BI. The repository describes itself as: 3 skills oficiais do Claude pra documentar, auditar e criar DAX no Power BI. Funciona no Claude.ai grátis. Open source. 2 minutos pra instalar. The licence is MIT.
6 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit a99d99e. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Pbi Modelo Review loads about 2.9k tokens when it runs, and up to ~10k if it reads all its reference files. Until then it costs about 74 tokens; SKILL.md has 1,386 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from xperiun/skills-xperiun-free at commit a99d99e, republished under its MIT licence (© xperiun). 1,386 words, ~2,866 tokens.
.claude/skills/pbi-modelo-review/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.📦 Parte do xperiun/skills-xperiun-free: pasta
claude-code/pbi-modelo-review/(Claude Code) +claude-web/pbi-modelo-review.zip(upload no Claude.ai).
Audita um projeto Power BI (formato PBIP) e devolve relatório priorizado com:
.pbix e quer mapa rápido de qualidadeNão usar quando:
/pbi-doc/pbi-dax-create/pbi-perf).SemanticModel/ e .Report/. Se o usuário só tem .pbix, instruir conversão antes de prosseguir:Power BI Desktop → File → Save as → Power BI Project (.pbip).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.
A skill detecta automaticamente o ambiente e adapta input/output:
.SemanticModel/.tmdl da pasta ./SemanticModel/./_review/index.html + ./_review/relatorio.md na raiz do projeto Power BIPra eu auditar, anexe nesse chat:
- Os arquivos
.tmdlda pastaSemanticModel/definition/(model.tmdl, relationships.tmdl, expressions.tmdl)- Os arquivos da pasta
SemanticModel/definition/tables/(1 .tmdl por tabela)Pode arrastar todos de uma vez ou zipar a pasta
SemanticModel/e subir o ZIP.
Verificar se a pasta .SemanticModel/ é acessível via filesystem:
Se ambíguo, perguntar uma vez:
Você tá rodando isso no Claude Code (CLI/IDE com acesso à pasta) ou no claude.ai (web)? Pra Code eu leio a pasta sozinho; pra web preciso que você suba os arquivos.
tudo)tudo → reporta crítico + médio + levecrítico+médio → ignora leves (foco no que cobra juros)só crítico → só o que bloqueia produçãoSe o usuário não especificar, perguntar uma vez antes de rodar:
Quer auditoria completa (todos os níveis) ou só os críticos+médios? Default é completa.
./SemanticModel/ (ou *.SemanticModel/ na raiz).tmdl em ./SemanticModel/tables/./SemanticModel/model.tmdl, ./SemanticModel/relationships.tmdl (se existir)measure em todos os tmdl), N relacionamentos, tamanho do projetoLer references/checks.md e rodar as 6 famílias de check descritas lá:
/, variáveis não usadas, CALCULATE aninhadoCada check encontrado vira um issue com:
id (slug único, ex: model-flat-detected)categoria (uma das 6 acima)severidade (critical | medium | light)titulo (uma frase, máx 90 chars)path (caminho do arquivo + linha quando aplicável)por_que_importa (1-2 parágrafos explicativos)como_corrigir (1 parágrafo + opcionalmente um snippet TMDL/DAX)Fórmula simples:
score = max(0, 100 - (criticos × 4) - (medios × 1.5) - (leves × 0.4))Limites:
A label sempre usa champagne gold (vibe v4 "alerta elegante", não "vermelho de painel").
Filtrar issues conforme severidade mínima escolhida e gerar dois arquivos:
A. Markdown (versionável Git):
templates/relatorio.md./_review/relatorio.md na raiz do projeto Power BIB. HTML standalone (visual):
🚨 REGRA INVIOLÁVEL — usar templates/relatorio.html LITERAL:
LER templates/relatorio.html — esse arquivo já tem todo o CSS, todo o HTML estrutural, todos os tokens DS v4 (Bebas Neue, accent-gold, gold-grid + beams animados, orb-v2 elipses blue/purple, brackets), todo o JS de filtro de severidade.
SUBSTITUIR APENAS os placeholders {{...}} pelos dados de auditoria reais. Lista completa em references/checks.md desta skill (seção "Placeholders do templates/relatorio.html").
PROIBIDO:
--accent-gold-bright #E8C9A0, --accent-glow #7099FF, --neon-magenta #C47FFF)<div class="gold-grid">, <div class="section-orb">, ou ornamentos do template<!-- ... --> — comentários são instruções pra você, não conteúdo a substituir.<style>...</style> ou <script>...</script> — CSS e JS ficam intocados.🚨 ENCODING — UTF-8 PURO, sem escape. Caracteres PT-BR (ã, ç, é, á, õ, ê, í, ú) e símbolos especiais (├, └, ─, →, ↔, ↑, ↓, ⚠, ·, —) devem aparecer como caracteres reais UTF-8, NÃO como sequências escapadas/HTML entities/mojibake.
críticos, →, Atenção, ⚠crÃticos, â, AtençãoGarantir que CSS continua inline (sem dependências externas além das fontes Google).
SALVAR em ./_review/index.html (modo Code) ou retornar como artifact (modo Web).
Sintomas de erro:
#f5a623 (laranja) ou #7c6af7 (roxo), ou fonte 'Segoe UI' → ignorou template, refaz.ã ou â → encoding quebrado, refaz UTF-8.Devolver mensagem curta no chat com:
_review/index.html no navegador pra ver completo"[raiz do projeto Power BI do usuário]/
├── SemanticModel/ ← input (não tocar)
├── Report/ ← input (não tocar)
└── _review/ ← OUTPUT da skill
├── relatorio.md ← versão markdown (commitável)
└── index.html ← versão visual standalone| Cenário | O que fazer |
|---|---|
Modelo sem .SemanticModel/ | Mensagem de pré-requisito (PBIP), encerra |
Pasta _review/ já existe | Sobrescrever (skill é idempotente) — mas avisar no chat |
| Modelo perfeito (zero issues) | Score 100 + celebrar + listar 3 melhores patterns encontrados (já que não tem o que reclamar) |
| Modelo apocalíptico (>50 críticos) | Truncar relatório nos top 30 críticos + linha "+ N issues não listados — começa por aqui antes" |
Erro lendo um .tmdl específico (corrupção) | Reportar arquivo problemático no chat, seguir com os demais |
| Projeto enorme (>500 medidas) | Avisar "modelo grande, vou processar em chunks · ~5min" antes de começar |
_review/.SemanticModel/ ou .Report/ — somente leitura nesses./_review/ (cria se não existe, sobrescreve se existe).SemanticModel/, .Report/, ou qualquer arquivo binárioEstilo Xperiun:
Exemplos de bom vs ruim:
❌ Ruim: "Identificou-se a presença de relacionamento bi-direcional que pode impactar negativamente a performance do modelo."
✅ Bom: "Bi-direcional em N:1 com calendário causa ambiguidade de filtro e duplica scan no engine. Em modelo de 1.4GB você está pagando ~30% de overhead por refresh sem ganhar nada."
O relatório HTML tem footer fixo:
Branding é sempre Xperiun: mesmo quando a skill roda no projeto de outra pessoa, o footer mantém a referência.
Avisar ao usuário se > 3min esperados.
Distribuída no repo público xperiun/skills-xperiun-free.
© xperiun, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. 1 hidden character (zero-width or bidirectional) removed. Raw file
SKILL.md and 4 other files (references) in claude-code/pbi-modelo-review of xperiun/skills-xperiun-free.
Open the folder on GitHubat commit a99d99e
Pbi Modelo Review next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Pbi Modelo Review this skillxperiun/skills-xperiun-free | 116 | — | ~2.9k | Automated safety check: Pass | MIT | |
| Power Bi AI ReadinessDKH-DK/Self-Service-Power-BI-Fabric | 113 | — | ~2k | Automated safety check: Pass | None | |
| Pbi Report Builderlukasreese/powerbi-claude-skills | 129 | — | ~7.5k | Automated safety check: Pass | None | |
| Pbip Dependency Analyzerlukasreese/powerbi-claude-skills | 129 | — | ~3.2k | Automated safety check: Pass | None | |
| Audit Tenant Settingsdata-goblin/power-bi-agentic-development | 1k | — | ~4.7k | Automated safety check: Pass | GPL-3.0 | |
| Bpa Rulesdata-goblin/power-bi-agentic-development | 1k | — | ~4.4k | Automated safety check: Pass | GPL-3.0 |
DKH-DK/Self-Service-Power-BI-Fabric
Score and prepare Power BI semantic models for AI (Fabric Data Agent / Copilot).
lukasreese/powerbi-claude-skills
[power-bi] Power BI PBIR Report Builder with IBCS Visuals. An agent skill from lukasreese/powerbi-claude-skills.
lukasreese/powerbi-claude-skills
Power BI PBIP Dependency Analyzer. An agent skill from lukasreese/powerbi-claude-skills.
data-goblin/power-bi-agentic-development
Automatically invoke this skill whenever the user asks about Fabric tenant settings or Power BI tenant settings or auditing tenant settings.
data-goblin/power-bi-agentic-development
Interactive BPA rule generation for Power BI semantic models; guided discovery, model investigation, and expert rule authoring.
data-goblin/power-bi-agentic-development
Guidance for Power BI Project (PBIP) structure, thick and thin reports, project renames, forks, and validation.
xperiun/skills-xperiun-free
Documenta projeto Power BI (PBIP) inteiro em markdown estruturado + HTML navegável (mini-site de doc).
xperiun/skills-xperiun-free
Cria medida DAX a partir de descrição em PT, respeitando o modelo Power BI existente (colunas reais, naming convention, padrões DAX).
Works with
Categories
Audita modelo Power BI (PBIP) e gera relatório priorizado com anti-patterns, score 0-100 e recomendações acionáveis. Pbi Modelo Review is an agent skill from xperiun/skills-xperiun-free. Audita modelo Power BI (PBIP) e gera relatório priorizado com anti-patterns, score 0-100 e recomendações acionáveis.
Pbi Modelo Review fits situations like: data & Analytics work in your project.
Run `npx skills add xperiun/skills-xperiun-free --skill pbi-modelo-review -a claude-code`. Or copy the skill folder (claude-code/pbi-modelo-review in xperiun/skills-xperiun-free) into .claude/skills/pbi-modelo-review in your project. Claude Code loads it when a task matches its description.
Run `npx skills add xperiun/skills-xperiun-free --skill pbi-modelo-review -a codex`. Or copy the skill folder (claude-code/pbi-modelo-review in xperiun/skills-xperiun-free) into .agents/skills/pbi-modelo-review in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add xperiun/skills-xperiun-free --skill pbi-modelo-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pbi-modelo-review, .gemini/skills/pbi-modelo-review, .github/skills/pbi-modelo-review and .opencode/skills/pbi-modelo-review in your project.
SKILL.md names no scripts, command-line tools or credentials: Pbi Modelo Review is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Pbi Modelo Review is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.9k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 7.1k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Pbi Modelo Review: Power Bi AI Readiness (DKH-DK/Self-Service-Power-BI-Fabric, 113 stars), Pbi Report Builder (lukasreese/powerbi-claude-skills, 129 stars), Pbip Dependency Analyzer (lukasreese/powerbi-claude-skills, 129 stars) and Audit Tenant Settings (data-goblin/power-bi-agentic-development, 1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
xperiun (a GitHub organization) maintains it in xperiun/skills-xperiun-free, which has 116 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on September 16, 2026.
Source: xperiun/skills-xperiun-free on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.