ClaudeMods
☰
ZH-TW
● 0 人在線上 · 瀏覽 0 次
贊助提交作品
GitHub 儲存庫 · 發布者 data-goblin

reports

建立、格式化、最佳化及檢視互動式 Power BI 報表,並提供遵循 pbir CLI 的報表面板,顯示 Claude 讀取與修改的內容。

data-goblin@data-goblin

data-goblin/power-bi-agentic-development/tree/main/plugins/reports

原貼文圖片1
已翻譯

關於這個 mod

<p align="center"> <img src="media/bg42-11-4.png" alt="" width="800"> </p> <h1 align="center">power-bi-agentic-development</h1> <p align="center"> 一個市集中最完整的 Power BI AI 技能與代理式開發資源來源 <br></br> <i>教 Claude Code 或 GitHub Copilot 等 AI 代理使用 Power BI 和 Microsoft Fabric</i> </p> <p align="center"> <img src="https://img.shields.io/badge/version-26.40.3-blue" alt="版本"> <img src="https://img.shields.io/badge/Power_BI-F2C811?logo=powerbi&logoColor=000" alt="Power BI"> <img src="https://img.shields.io/badge/Microsoft_Fabric-008272" alt="Microsoft Fabric"> <img src="https://img.shields.io/badge/Tabular_Editor-2E7D32" alt="Tabular Editor"> <img src="https://img.shields.io/badge/license-GPL--3.0-green" alt="授權條款"> </p>

[!WARNING] 這些技能仍在積極開發中,並以每週發布的節奏更新,因此名稱與結構會定期變更。

**26.26 到 26.38 是刻意安排的破壞性過渡。**在這段每週發布期間,技能可能會合併、重新命名、移除,或變得不那麼自動。如果需要過渡前的技能結構與行為,請固定使用 26.25 或更早版本;不要假設前後兩個過渡版本互相相容。


什麼是代理式開發?

  • 代理式開發是指使用代理協助建立、管理和最佳化成品與軟體。這包括語意模型、報表,以及周邊的工作區、部署管線和流程。
  • 市集提供可安裝的 外掛。外掛是一組幫助程式碼代理更有效工作的資源,通常是專用的指令檔案和腳本。外掛可以包含專注於特定主題或工作的技能、子代理、hooks 和 MCP 伺服器。
  • 這個市集專注於協助你的代理與 Power BI 和 Fabric 協作所需的一切:Power BI 技能、Fabric 技能、子代理,以及給程式碼代理使用的 hooks。繼續閱讀可取得更多資訊。

安裝

以下是在 Claude Code 中開始使用的方法;在終端機執行這個指令以取得市集:

claude plugin marketplace add data-goblin/power-bi-agentic-development

使用 pbir-cli 搭配技能的範例

點擊此處觀看 YouTube 示範

pbir-cli 示範

Claude Code

加入市集後,使用 /plugin 前往已安裝的市集並安裝外掛。

<table> <tr> <td align="center"><img src="media/marketplace-ui.png" alt="市集介面" width="400"></td> <td align="center"><img src="media/marketplace-auto-update.png" alt="市集自動更新" width="400"></td> </tr> <tr> <td align="center"><em>從市集安裝外掛</em></td> <td align="center"><em>啟用市集自動更新</em></td> </tr> </table>

另一種方式是透過命令列加入外掛:

claude plugin install goblin-mode@power-bi-agentic-development
claude plugin install tabular-editor@power-bi-agentic-development
claude plugin install pbi-desktop@power-bi-agentic-development
claude plugin install pbip@power-bi-agentic-development
claude plugin install semantic-models@power-bi-agentic-development
claude plugin install reports@power-bi-agentic-development
claude plugin install paginated-reports@power-bi-agentic-development
claude plugin install custom-visuals@power-bi-agentic-development
claude plugin install fabric-cli@power-bi-agentic-development
claude plugin install fabric-admin@power-bi-agentic-development
claude plugin install databricks-cli@power-bi-agentic-development
claude plugin install fabric-data-app@power-bi-agentic-development
claude plugin install etl@power-bi-agentic-development

Copilot CLI

獨立的 Copilot CLI 支援從 GitHub 存放庫安裝外掛。Copilot CLI 會讀取此存放庫使用的相同 .claude-plugin/marketplace.json 清單,因此市集與子外掛配置不需要修改就能運作。

<details> <summary><strong>Windows 長路徑</strong></summary>

TMDL 檔案處理超過 260 個字元的存放庫相對路徑時會遇到問題。Windows 舊版 MAX_PATH 會阻止 git clone 寫入這些路徑,除非同時在作業系統與 git 層級啟用長路徑支援。否則,copilot plugin install 會因 Filename too long 而中止。

請參考 useful-stuff/agent-scripts/enable-windows-longpaths.ps1,其中示範了如何從提升權限的 ps 環境執行腳本來啟用長路徑;你也可以在線上找到其他做法……直接問 Copilot 即可。變更登錄後建議重新開機。這是 Windows 作業系統的限制,詳見 Maximum Path Length Limitation。

也請參閱下面的 git config 指令:

git config --system core.longpaths true
</details> <details> <summary><strong>其他安裝說明</strong></summary>

這個存放庫是 Anthropic 格式的外掛市集(一組外掛),不是單一可散發的外掛,因此根目錄 .claude-plugin/ 只有 marketplace.json。有兩條有文件記載的安裝路徑:

1. 註冊一次市集,再安裝指定名稱的子外掛。範例:

copilot plugin marketplace add data-goblin/power-bi-agentic-development
copilot plugin install tabular-editor@power-bi-agentic-development

2. 或直接從子目錄安裝單一外掛,不需要註冊市集。範例:

copilot plugin install data-goblin/power-bi-agentic-development:plugins/pbip

兩種形式都記載於 Copilot CLI 外掛參考 和 外掛使用方式。在互動式 Copilot 工作階段中,/plugin install PLUGIN-NAME@MARKETPLACE-NAME 等同於 (1)。不帶限定詞的 copilot plugin install data-goblin/power-bi-agentic-development 不會安裝任何有用內容,因為根目錄是市集目錄,不是外掛。

</details> <details> <summary><strong>在 Copilot CLI 中驗證安裝</strong></summary>

在 Copilot CLI 中:

/env                    # Loaded instructions, MCP servers, skills, agents, plugins, LSPs, extensions
/plugin list            # Installed plugins
/skills list            # Available skills
/skills info pbip       # Details for a specific skill
/agent                  # Browse installed agents
</details> <details> <summary><strong>相容性說明</strong></summary>
  • 技能的載入方式相同;Copilot CLI 會讀取 skills/<name>/SKILL.md。
  • 代理使用 Copilot CLI 文件慣例要求的 *.agent.md 副檔名。Claude Code 會比對 agents/ 中任何 *.md 檔案,因此雙重副檔名在兩個工具中都能運作。
  • MCP 伺服器從 .mcp.json(外掛根目錄)或 .github/mcp.json 載入。此存放庫的外掛目前不提供 MCP 伺服器。
  • Hooks會提供兩份。Claude Code 讀取 hooks/hooks.json(含每個 hook 的 if 路徑篩選器)。Copilot CLI 讀取 .github/plugin/plugin.json,該檔案指向 hooks/copilot-hooks.json:這些是相同的腳本,透過明確的 bash 與 powershell 指令連接,因此在 PATH 沒有 Git Bash 的 Windows 主機上會得到乾淨的 no-op,不會啟動失敗。Copilot 沒有 if 篩選器,而且任何非零的 PreToolUse 結束碼都會拒絕工具呼叫,所以每個腳本也會重新套用自己的路徑與指令篩選器,對不相關內容以 0 結束。CLAUDE_PLUGIN_ROOT 需要 Copilot CLI >= 1.0.26(2026-04-14)(見 changelog);較舊版本會略過 hooks,而不是失敗。原生 Windows bash 使用者也可能遇到上游追蹤的另一個路徑格式錯誤:claude-code#11984。
  • 範圍在 Copilot CLI 中永遠是使用者層級:外掛會安裝到 ~/.copilot/installed-plugins/,其 hooks 會在這台機器的每個工作階段執行。它沒有逐專案安裝,因此下面的「優先使用專案範圍」建議只適用於 Claude Code;在 Copilot 中只在需要時安裝外掛。
</details> <details> <summary><strong>在 Windows 上解除安裝 Copilot CLI 的外掛</strong></summary>

/plugin rm 或 copilot plugin uninstall 可能失敗並顯示 Access is denied. (os error 5)。這是 Copilot CLI 的公開 bug,不是外掛問題:安裝程式會透過重新命名外掛資料夾來替換它,而當另一個程序持有資料夾控制代號時,Windows 會拒絕重新命名。VS Code 的 Copilot 擴充功能會在每個已安裝外掛的 hooks/、agents/ 和 skills/ 資料夾上保留目錄監看器,第二個 Copilot CLI 工作階段也會這樣做。問題記錄在 github/copilot-cli#4095 和 #4151。

  1. 關閉每個 VS Code 視窗和其他所有 Copilot CLI 工作階段,然後重試解除安裝。
  2. 如果仍然失敗,手動刪除外掛:移除 %USERPROFILE%\\.copilot\\installed-plugins\\(或 %COPILOT_HOME%\\installed-plugins\\)底下的外掛資料夾,然後重新啟動 Copilot CLI。
  3. 如果不想解除安裝,只想停止 hooks,請從同一個位置刪除外掛的 hooks 資料夾。
</details>

概覽

此存放庫包含技能、代理與 hooks。

  • 技能教授代理領域知識和工作流程。它們會依工作情境自動啟用,也可以用 /skill-name 手動呼叫。在 Claude Code 中,技能與指令已經合併;指令只是規範性更強的技能工作流程。
  • 代理是能獨立處理複雜多步驟工作的自主子程序;通常用於檢視與驗證。
  • Hooks會在工具使用後自動執行,以驗證檔案並及早捕捉錯誤。它們是確定性的;只有符合特定模式時才會觸發,不是由 LLM 判斷。
  • Mods會在 Claude Code 本身加入面板;請參閱 Claude Code mods。

可以透過設定檔個別切換 hook 檢查。將任何檢查設為 false 即可停用:

  • plugins/pbip/hooks/config.yaml -- PBIR、TMDL 與報表繫結驗證
  • plugins/pbi-desktop/hooks/config.yaml -- DAX 參照、量值中繼資料、參照完整性、中繼資料快取

可用的 Power BI 與 Fabric 技能、代理和 hooks:外掛

[!WARNING] 不要安裝所有外掛。每項技能都會爭奪代理的注意力與內容視窗,因此只在需要時安裝外掛,不需要時移除。優先安裝專案範圍的外掛,而不是使用者範圍的外掛,讓每個專案只帶有實際使用的技能。

<details> <summary><strong>goblin-mode</strong> &ensp; 開始使用、設定工具,並檢查與改善完整的代理式開發環境</summary>

| 類型 | 名稱 | 說明 | |------|------|-------------| | 技能 | help-me-get-started | 給代理新手的慢速、友善、不使用術語的代理式開發指南;會討論你想做什麼,了解你的角色和存取權限,透過本機互動式解說工具教導五大支柱(模型、內容、提示、工具、環境),並檢查及安裝所需內容(Windows/macOS 指令)。可調整速度:完整教學或快速安裝 | | 技能 | improve-my-agent-setup | 具有多種模式(shallow/deep/ultra/yolo)的整體設定健康檢查:技能、記憶、工具、STT、模型獨立性

安裝

請先查看作者 README,確認 marketplace 與外掛名稱;指令可能隨儲存庫結構而變動。

claude plugin marketplace add data-goblin/power-bi-agentic-development
claude plugin install reports
原文 / README
<p align="center"> <img src="media/bg42-11-4.png" alt="" width="800"> </p> <h1 align="center">power-bi-agentic-development</h1> <p align="center"> The best source for Power BI AI skills and agentic development resources in one marketplace <br></br> <i> Teach AI agents like Claude Code or GitHub Copilot Power BI and Microsoft Fabric </i> </p> <p align="center"> <img src="https://img.shields.io/badge/version-26.40.3-blue" alt="Version"> <img src="https://img.shields.io/badge/Power_BI-F2C811?logo=powerbi&logoColor=000" alt="Power BI"> <img src="https://img.shields.io/badge/Microsoft_Fabric-008272" alt="Microsoft Fabric"> <img src="https://img.shields.io/badge/Tabular_Editor-2E7D32" alt="Tabular Editor"> <img src="https://img.shields.io/badge/license-GPL--3.0-green" alt="License"> </p>

[!WARNING] These skills are under active development with a weekly release cadence, so expect regular renaming and restructuring.

Versions 26.26 through 26.38 are a deliberate breaking transition. Skills may be consolidated, renamed, removed, or made less automatic between weekly releases in this range. Pin 26.25 or earlier if you need the pre-transition skill structure and behavior; do not assume compatibility from one transition release to the next.


What is agentic development?

  • Agentic development is when you use agents to help you build, manage, and optimize artifacts and software. This includes semantic models, reports, and the things around them, like workspaces, deployment pipelines, and also processes.
  • A marketplace hosts plugins that you can install. Plugins are a collection of resources that help coding agents perform better. They are typically special instruction files and scripts. Plugins can contain skills, subagents, hooks, and MCP servers focused on special topics or tasks.
  • This marketplace is focused on everything to help your agent work well with Power BI and Fabric: Power BI skills, Fabric skills, subagents, and hooks for coding agents. Read further for more information.

Installation

Here's how you get started in Claude Code; run this in the terminal to get the marketplace:

claude plugin marketplace add data-goblin/power-bi-agentic-development

Example: Using the pbir-cli with the skills

Click here for a YouTube walkthrough

pbir-cli demo

Claude Code

Add the marketplace, then install plugins via /plugin and navigating to the installed marketplace.

<table> <tr> <td align="center"><img src="media/marketplace-ui.png" alt="Marketplace UI" width="400"></td> <td align="center"><img src="media/marketplace-auto-update.png" alt="Marketplace auto-update" width="400"></td> </tr> <tr> <td align="center"><em>Install plugins from the marketplace</em></td> <td align="center"><em>Enable marketplace auto-update</em></td> </tr> </table>

Alternative; add plugins via command line:

claude plugin install goblin-mode@power-bi-agentic-development
claude plugin install tabular-editor@power-bi-agentic-development
claude plugin install pbi-desktop@power-bi-agentic-development
claude plugin install pbip@power-bi-agentic-development
claude plugin install semantic-models@power-bi-agentic-development
claude plugin install reports@power-bi-agentic-development
claude plugin install paginated-reports@power-bi-agentic-development
claude plugin install custom-visuals@power-bi-agentic-development
claude plugin install fabric-cli@power-bi-agentic-development
claude plugin install fabric-admin@power-bi-agentic-development
claude plugin install databricks-cli@power-bi-agentic-development
claude plugin install fabric-data-app@power-bi-agentic-development
claude plugin install etl@power-bi-agentic-development

Copilot CLI

The standalone Copilot CLI supports plugin installation from GitHub repos. Copilot CLI reads the same .claude-plugin/marketplace.json manifest this repo uses, so the marketplace and child-plugin layout works without modification.

<details> <summary><strong>Windows long paths</strong></summary>

TMDL files have a problem with repository-relative paths over 260 characters. Windows' legacy MAX_PATH blocks git clone from writing them unless long path support is enabled at both the OS and git level. Without this, copilot plugin install aborts with Filename too long.

Check useful-stuff/agent-scripts/enable-windows-longpaths.ps1 as an example of a script you can run from an elevated ps environment to enable long paths; there are other routes to do this that you can find online, too... just ask Copilot. A reboot is recommended after the registry change. This is a Windows OS limitation, documented at Maximum Path Length Limitation.

See also the below git config command:

git config --system core.longpaths true
</details> <details> <summary><strong>Additional installation instructions</strong></summary>

This repository is an Anthropic-format plugin marketplace (a set of plugins), not a single distributable plugin, so the root .claude-plugin/ contains only marketplace.json. Two documented install paths work:

1. Register the marketplace once, then install named child plugins. Example:

copilot plugin marketplace add data-goblin/power-bi-agentic-development
copilot plugin install tabular-editor@power-bi-agentic-development

2. Or install a single plugin directly from its subdirectory, no marketplace registration needed. Example:

copilot plugin install data-goblin/power-bi-agentic-development:plugins/pbip

Both forms are documented in the Copilot CLI plugin reference and the plugins how-to. Inside an interactive Copilot session, /plugin install PLUGIN-NAME@MARKETPLACE-NAME is the equivalent of (1). The bare copilot plugin install data-goblin/power-bi-agentic-development (no qualifier) will not install anything useful, because the root is a marketplace catalog, not a plugin.

</details> <details> <summary><strong>Verify installation in Copilot CLI</strong></summary>

Inside Copilot CLI:

/env                    # Loaded instructions, MCP servers, skills, agents, plugins, LSPs, extensions
/plugin list            # Installed plugins
/skills list            # Available skills
/skills info pbip       # Details for a specific skill
/agent                  # Browse installed agents
</details> <details> <summary><strong>Compatibility notes</strong></summary>
  • Skills load identically; Copilot CLI reads skills/<name>/SKILL.md.
  • Agents use the *.agent.md extension required by Copilot CLI's documented convention. Claude Code matches any *.md file in agents/, so the dual extension works in both tools.
  • MCP servers load from .mcp.json (plugin root) or .github/mcp.json. The plugins in this repo do not currently ship MCP servers.
  • Hooks ship twice. Claude Code reads hooks/hooks.json (with per-hook if path filters). Copilot CLI reads .github/plugin/plugin.json, which points it at hooks/copilot-hooks.json: the same scripts, wired with explicit bash and powershell commands so a Windows host without Git Bash on PATH gets a clean no-op instead of a failed launch. Copilot has no if filter and denies a tool call on any non-zero PreToolUse exit, so every script also re-applies its own path and command filters and exits 0 on anything unrelated. Requires Copilot CLI >= 1.0.26 (2026-04-14) for CLAUDE_PLUGIN_ROOT (changelog); older builds skip the hooks rather than fail. Native Windows bash users may also hit a separate path-format bug tracked upstream at claude-code#11984.
  • Scope is always user-wide in Copilot CLI: plugins install to ~/.copilot/installed-plugins/ and their hooks run in every session on the machine. There is no per-project install, so the "prefer project scope" advice below applies to Claude Code only; in Copilot, install a plugin only while you need it.
</details> <details> <summary><strong>Uninstalling in Copilot CLI on Windows</strong></summary>

/plugin rm or copilot plugin uninstall can fail with Access is denied. (os error 5). This is an open Copilot CLI bug, not a plugin problem: the installer swaps the plugin folder by renaming it, and Windows refuses the rename while another process holds a handle on it. VS Code's Copilot extension keeps directory watchers on every installed plugin's hooks/, agents/ and skills/ folders, and a second Copilot CLI session does the same. Tracked at github/copilot-cli#4095 and #4151.

  1. Close every VS Code window and every other Copilot CLI session, then retry the uninstall.
  2. If it still fails, delete the plugin by hand: remove its folder under %USERPROFILE%\.copilot\installed-plugins\ (or %COPILOT_HOME%\installed-plugins\) and restart Copilot CLI.
  3. To stop the hooks without uninstalling, delete the plugin's hooks folder from that same location.
</details>

Overview

The repo contains skills, agents, and hooks.

  • Skills teach agents domain knowledge and workflows. They activate automatically based on task context, or can be invoked manually with /skill-name. In Claude Code, skills and commands have coalesced; commands are simply more prescriptive skill workflows.
  • Agents are autonomous subprocesses that handle complex, multi-step tasks independently; typically used for review and validation.
  • Hooks run automatically after tool use to validate files and catch errors early. They are deterministic; they fire when a specific pattern is matched, not by LLM judgment.
  • Mods add a pane to Claude Code itself; see Claude Code mods.

Hook checks can be individually toggled via config files. Set any check to false to disable it:

  • plugins/pbip/hooks/config.yaml -- PBIR, TMDL, and report binding validation
  • plugins/pbi-desktop/hooks/config.yaml -- DAX references, measure metadata, referential integrity, metadata cache

Power BI and Fabric skills, agents, and hooks: available plugins

[!WARNING] Don't install every plugin. Each skill competes for the agent's attention and context window, so install a plugin only when you need it and remove it when you don't. Prefer installing plugins scoped to a project rather than to your user, so each project carries only the skills it actually uses.

<details> <summary><strong>goblin-mode</strong> &ensp; Get started, set up your tools, and audit and improve your whole agentic setup</summary>

| Type | Name | Description | |------|------|-------------| | Skill | help-me-get-started | A slow, friendly, jargon-free guide to agentic development for people new to agents; talks through what you want to do, feels out your role and access, teaches the five pillars (model, context, prompt, tools, environment) with local interactive explainers, and checks and installs what you need (Windows/macOS commands). Adapts pace: full tutorial or a fast install run | | Skill | improve-my-agent-setup | Setup-wide health check with modes (shallow/deep/ultra/yolo): skills, memory, tools, STT, model independence, other clients, harness config, git, permission/isolation, network and autonomous-agent exposure, safety enforcement, secrets and PII hygiene, and workflow habits; then offers to fix what's weak. Absorbs the old /audit-context |

</details> <details> <summary><img src="media/icons/tabular-editor.svg" alt="" height="20"> <strong>tabular-editor</strong> &ensp; BPA rules, C# scripting, and CLI automation for Tabular Editor</summary>

| Type | Name | Description | |------|------|-------------| | Skill | bpa-rules | Create and improve Best Practice Analyzer rules for models | | Skill | c-sharp-scripting | C# scripting and macros for TE | | Skill | te-cli | Cross-platform Tabular Editor CLI (te, preview) for semantic models from the terminal | | Skill | te2-cli | Tabular Editor 2 CLI usage and automation (not TE3) | | Skill | te-docs | Tabular Editor documentation search, TE3 config files. Uses pbi-search CLI | | Command | /suggest-rule | Generate BPA rules from descriptions | | Agent | bpa-expression-helper | Debug and improve BPA rule expressions |

</details> <details> <summary><img src="media/icons/pbi-desktop.svg" alt="" height="20"> <strong>pbi-desktop</strong> &ensp; Connect to, query, and modify models in Power BI Desktop</summary>

| Type | Name | Description | |------|------|-------------| | Skill | connect-pbid | Explore, query, and modify a model in Power BI Desktop, and reload/screenshot the report canvas via the Desktop Bridge | | Agent | query-listener | Capture DAX queries from Power BI Desktop visuals in real time | | Hook | DAX reference validation | Validates table, column, and measure references against the connected model; suggests corrections | | Hook | Measure metadata enforcement | Blocks adding measures without DisplayFolder, Description, and FormatString | | Hook | Referential integrity check | Reports unmatched many-side keys after relationship or column changes | | Hook | Metadata cache refresh | Auto-snapshots model metadata on TOM connect or model modification | | Hook | Compatibility level check | Reports features available by upgrading; optional auto-upgrade |

</details> <details> <summary><img src="media/icons/pbip.svg" alt="" height="20"> <strong>pbip</strong> &ensp; Author and validate TMDL, PBIR, and PBIP project files</summary>

| Type | Name | Description | |------|------|-------------| | Skill | pbip | Power BI Project (PBIP) format, structure, and file types | | Skill | tmdl | Author and edit TMDL files directly | | Skill | pbir-format | Author and edit PBIR metadata files directly (visual.json, report.json, themes, filters, report extensions, visual calculations) | | Agent | pbip-validator | Validate PBIP project structure, TMDL syntax, and PBIR schemas | | Hook | PBIR validation | Validates PBIR structure, required fields, naming conventions, and schema URLs | | Hook | Report binding validation | Validates semantic model binding (byPath directory exists; byConnection model exists via fab exists) | | Hook | TMDL validation | Validates TMDL structural syntax |

</details> <details> <summary><img src="media/icons/reports.svg" alt="" height="20"> <strong>reports</strong> &ensp; Build, format, optimize, and review interactive Power BI reports</summary>

| Type | Name | Description | |------|------|-------------| | Skill | create-pbi-report | Step-by-step workflow for building a complete report from scratch via the pbir CLI: model discovery, pages, theme, visuals, field binding, filtering, formatting, validation, publishing | | Skill | pbi-report-design | The Power BI report design canon: design identity, visual hierarchy, layout, color discipline, chart selection, KPI/table design, accessibility. Shared reference used by the other report skills | | Skill | modifying-theme-json | Design, enforce, audit, and validate report themes through the pbir CLI | | Skill | review-report | Actionable feedback on report quality, usage, and effectiveness; usage analysis, health checks | | Skill | pbir-cli | Programmatic report manipulation via the pbir CLI, including live Power BI Desktop refresh and page screenshots | | Mod | /report-pane | Report pane: pages, visuals, bookmarks, filters and report measures of the .Report folder as a tree that follows pbir, with live highlights of what Claude reads or changes. Optional arg: a path to a .Report folder. Icons: FabricSymbols NF | | Agent | deneb-reviewer | Review Deneb visual specs for Vega/Vega-Lite syntax and conventions | | Agent | svg-reviewer | Review SVG DAX measures for syntax and design quality | | Agent | r-reviewer | Review R visual scripts (ggplot2) for Power BI conventions | | Agent | python-reviewer | Review Python visual scripts (matplotlib/seaborn) for Power BI conventions |

</details> <details> <summary><strong>paginated-reports</strong> &ensp; Author, validate, publish, and test print-ready paginated reports</summary>

| Type | Name | Description | |------|------|-------------| | Skill | paginated-report | Author, validate, publish, and test Power BI paginated reports in RDL format (Report Builder, PBIRS/SSRS-compatible); connect to a semantic model, render to PDF/Excel | | Hook | RDL validation | Validates .rdl structure after Write/Edit and on Bash commands touching .rdl files; blocks on structural errors only |

</details> <details> <summary><strong>custom-visuals</strong> &ensp; Build Deneb, Python, R, SVG, and pbiviz custom visuals for Power BI</summary>

| Type | Name | Description | |------|------|-------------| | Skill | deneb-visuals | Deneb visual creation, Vega/Vega-Lite spec authoring, Deneb best practices for PBIR reports | | Skill | r-visuals | Custom R visuals (ggplot2) for Power BI reports | | Skill | python-visuals | Custom Python visuals (matplotlib/seaborn) for Power BI reports | | Skill | svg-visuals | SVG generation via DAX measures and extension measures for inline chart visualizations (sparklines, bullet charts, KPI indicators, and more) | | Skill | powerbi-custom-visuals | Power BI developer custom visual (.pbiviz) development with the pbiviz toolchain and its MCP server: scaffold, build, debug, package, certify, publish to AppSource |

Reviewer agents for these visual types (deneb-reviewer, svg-reviewer, r-reviewer, python-reviewer) ship in the reports plugin above.

</details> <details> <summary><img src="media/icons/semantic-models.svg" alt="" height="20"> <strong>semantic-models</strong> &ensp; DAX, Power Query, naming, lineage, refresh, and model auditing</summary>

| Type | Name | Description | |------|------|-------------| | Skill | semantic-model | Design, build, refresh, and review semantic models through a te-first tool cascade | | Skill | standardize-naming-conventions | Audit and standardize naming conventions in semantic models | | Skill | refresh-semantic-model | Trigger or troubleshoot refreshes | | Skill | lineage-analysis | Trace downstream reports from a semantic model across workspaces | | Skill | power-query | Write M expressions, debug query folding, execute M locally or via Fabric API | | Skill | dax | Write, debug, and optimize DAX in semantic models. Contributed by Justin Martin | | Agent | semantic-model-auditor | Audit semantic models for quality, memory, DAX, and design issues |

</details> <details> <summary><img src="media/icons/fabric-cli.svg" alt="" height="20"> <strong>fabric-cli</strong> &ensp; Remote operations via Fabric CLI; works on Pro, PPU, or Fabric</summary>

| Type | Name | Description | |------|------|-------------| | Skill | fabric-cli | Fabric CLI (fab) for any remote operation in Power BI or Fabric (works fully on Pro, PPU; Fabric not required) | | Command | /migrating-fabric-trial-capacities | Migrate workspaces from trial to production capacity | | Mod | /fabric-pane | Fabric pane: workspaces and items as a tree that follows fab, with live highlights, copy of fab paths, open in Fabric, and open semantic models in te. Optional arg: a workspace to reveal. Icons: FabricSymbols NF |

</details> <details> <summary><img src="media/icons/fabric-cli.svg" alt="" height="20"> <strong>fabric-admin</strong> &ensp; Tenant settings audits, governance, delegated overrides; requires fabric-cli</summary>

| Type | Name | Description | |------|------|-------------| | Skill | audit-tenant-settings | Audit Fabric and Power BI tenant settings, delegated overrides, and Entra security group membership |

</details> <details> <summary><strong>databricks-cli</strong> &ensp; Databricks pane that follows the databricks CLI</summary>

| Type | Name | Description | |------|------|-------------| | Mod | /databricks-pane | Databricks pane: workspace, Unity Catalog, compute, jobs, pipelines, apps and dashboards as a tree that follows databricks, with live highlights, profile switching (-p or DATABRICKS_CONFIG_PROFILE), copy of CLI arguments, and open in Databricks. Optional arg: a profile. Icons: DatabricksSymbols NF |

</details> <details> <summary><strong>fabric-data-app</strong> &ensp; Fabric Fabric app pane that follows the rayfin CLI</summary>

| Type | Name | Description | |------|------|-------------| | Mod | /fabric-app-pane | Fabric app pane: every Fabric App (rayfin/rayfin.yml) under the working directory with its data sources, deploy state and files, as a tree that follows rayfin, with live highlights of what Claude deploys or changes. Optional arg: a folder. Icons: FabricSymbols NF |

</details> <details> <summary><strong>etl</strong> &ensp; Inspect, query, and transform lakehouse data with Spark, Livy, and DuckDB</summary>

| Type | Name | Description | |------|------|-------------| | Skill | executing-spark | Execute arbitrary Python or PySpark code on Fabric Spark compute without creating a notebook artifact; ephemeral Livy sessions with full Delta table access | | Skill | using-duckdb | Query Fabric lakehouse and warehouse data with DuckDB, locally or inside a Fabric notebook; data freshness and quality checks |

</details>

Claude Code mods

[!WARNING] Mods only work in Claude Code 2.1.287 or newer. In other tools, such as Copilot CLI, the panes do not appear.

Mods add a pane to Claude Code's sidebar. These panes show your Fabric tenant, Databricks workspace, Power BI report or Fabric data apps as a tree beside the conversation, highlight what Claude reads, downloads, uploads, deploys or changes through the CLI, say when Claude is working, show spinners while a command runs, and pass the item you select to Claude as context. See the Claude Code mod docs.

Fabric pane

/fabric-pane from the fabric-cli plugin follows fab: workspaces grouped by domain, items, lakehouse tables and files.

<img src="media/mods/fabric-pane.gif" alt="The Fabric pane highlighting a semantic model Claude reads" width="720">

Databricks pane

/databricks-pane from the databricks-cli plugin follows databricks: workspace, Unity Catalog, compute, jobs, pipelines, apps and dashboards.

<img src="media/mods/databricks-pane.gif" alt="The Databricks pane highlighting a table Claude reads" width="720">

Report pane

/report-pane from the reports plugin follows pbir: pages, visuals, bookmarks, filters and report measures of a .Report folder.

<img src="media/mods/report-pane.gif" alt="The report pane highlighting a visual Claude reads" width="720">

Fabric app pane

/fabric-app-pane from the fabric-data-app plugin follows rayfin: every Fabric App under the working directory, its data sources, deploy state and files.

<img src="media/mods/fabric-app-pane.gif" alt="The Fabric app pane highlighting an app Claude deploys" width="720">

Setup

  • Layout: the sidebar needs the fullscreen layout (/tui fullscreen, or "tui": "fullscreen" in ~/.claude/settings.json) and a terminal at least 110 columns wide. In the default layout or tmux the panes stay hidden and their command tells you how to switch. In a fullscreen session the Fabric, Databricks and report panes open by themselves on Claude's first fab, databricks or pbir command, and the Fabric app pane when the working directory holds a Fabric App
  • Icons: install FabricSymbols NF (Fabric, report and Fabric app panes) or DatabricksSymbols NF together with a Nerd Font, then restart the terminal. Without them the panes use a Nerd Font alone, then plain Unicode. Auto detection covers Linux and macOS; on Windows set the glyphs option
  • Getting started: when the CLI is missing, you are not signed in or the service can't be reached, the Fabric and Databricks panes show the steps to fix it, with commands you can copy
  • Options: glyphs forces an icon set; follow (Follow Claude) decides whether the tree scrolls to what Claude touches; fontHint turns off the one-line install hint Claude gets once per session when the icons fall back to plain Unicode

Useful stuff

General-purpose agent resources that don't fit into a plugin: defensive hooks, patterns, and tools. See useful-stuff/.

Use or re-use of these skills

These plugins are intended for free community use.

You do not have the license to copy and incorporate them into your own products, trainings, courses, or tools. If you copy these skills - manually or by using an agent to rewrite them - you must include attribution and a link to this original project. That includes you, Microsoft.

<br> <p align="center"> <img src="media/bg22-06-2.png" alt="" width="800"> </p>
<p align="center"> <em>Built with assistance from <a href="https://claude.ai/claude-code">Claude Code</a>. AI-generated code has been reviewed but may contain errors. Use at your own risk.</em> </p> <p align="center"> <em>Context files are human-written and revised by Claude Code after iterative use.</em> </p>
<p align="center"> <a href="https://github.com/data-goblin">Kurt Buhler</a> · <a href="https://data-goblins.com">Data Goblins</a> · part of <a href="https://tabulareditor.com">Tabular Editor</a> </p>

其他同名作品

更多類似作品