Te2 Cli logo

Te2 Cli

CommunityPopular
data-goblin
te2-cli

CLI syntax reference for Tabular Editor 2 (TabularEditor.exe); deployment, scripting, BPA analysis, and CI/CD integration. Automatically invoke when the user mentions "TabularEditor.exe", TE2 CLI flags (-D, -S, -A, -B, -TMDL, -O, -C), or asks to "deploy a model via CLI", "set up CI/CD for Power BI", "automate model deployment", "run BPA from command line", "save model as TMDL".

Overview

Publisherdata-goblin
Repositorypower-bi-agentic-development
Skill namete2-cli
Stars
1K
Forks
149
Bundled files
1
LicenseGPL-3.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by data-goblin on GitHub. Read the source before you install it.

Installation

Install the Te2 Cli AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/data-goblin/power-bi-agentic-development/tree/main/plugins/tabular-editor/skills/te2-cli
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/data-goblin/power-bi-agentic-development.git /tmp/power-bi-agentic-development
mkdir -p .claude/skills
cp -r /tmp/power-bi-agentic-development/plugins/tabular-editor/skills/te2-cli .claude/skills/te2-cli
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Te2 Cli in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Te2 Cli on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Te2 Cli is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Tabular Editor 2 CLI

Command-line interface for Tabular Editor 2 (TE2). This skill covers the TabularEditor.exe executable; TE3 has its own CLI and is a separate product.

[!NOTE] The TE2 CLI (TabularEditor.exe) is still supported and stable, and remains a solid choice for existing Windows CI/CD pipelines. It is now considered outdated against the newer cross-platform Tabular Editor CLI (te), which is built on TE3 and is in preview until Q4 2026. For the te command set and a flag-by-flag migration, see the te-cli skill. Download te preview binaries from the Tabular Editor CLI downloads page.

Installation

Tabular Editor 2 (Free)

Executable

TabularEditor.exe -- free, Windows-only. For Mac/Linux, run via a Windows VM or container.

Connection Sources

Local Files

bash
# model.bim (JSON format)
TabularEditor.exe Model.bim

# TMDL folder
TabularEditor.exe definition/

# PBIP project
TabularEditor.exe MyReport.pbip

Remote XMLA Endpoints

bash
# Analysis Services
TabularEditor.exe "localhost\tabular" "AdventureWorks"

# Power BI Premium/Fabric
TabularEditor.exe "powerbi://api.powerbi.com/v1.0/myorg/WorkspaceName" "ModelName"

Power BI Desktop

bash
# Auto-detect running instance
TabularEditor.exe localhost:PORT DatabaseName

Note: Find the port in PBIDesktop diagnostic files or use tools like DAX Studio.

Command-Line Reference

Basic Syntax

bash
TabularEditor.exe <source> [options]

Script Execution

bash
# Inline C# script
TabularEditor.exe Model.bim -S "Info(Model.Name);"

# Script file
TabularEditor.exe Model.bim -S script.csx

# Multiple scripts (executed in order)
TabularEditor.exe Model.bim -S script1.csx -S script2.csx

Deployment

bash
# Deploy to XMLA endpoint
TabularEditor.exe Model.bim -D "server" "database"

# Deploy with options
TabularEditor.exe Model.bim -D "server" "database" -O -C -P -R -M -E -V -W

Deployment Options

FlagLong FormDescription
-O-OVERWRITEOverwrite existing database
-C-CONNECTIONSDeploy/overwrite data sources (supports connection string placeholder substitution)
-P-PARTITIONSDeploy/overwrite existing table partitions
-R-ROLESDeploy roles
-M-MEMBERSDeploy role members
-S-SHAREDDeploy shared expressions (within -D context; note: -S also means script outside -D)
-E-ERRReturn non-zero exit code if AS returns error messages after deployment
-V-VSTSOutput Azure DevOps logging commands
-W-WARNOutput warnings for unprocessed objects
-F-FULLFull deployment (equivalent to -O -C -P -S -R -M)
-X-XMLAGenerate XMLA/TMSL script instead of deploying
-L-LOGINDisable integrated security for deployment
-Y-SKIPPOLICYSkip incremental refresh policy partitions

Save Output

bash
# Save to model.bim
TabularEditor.exe Model.bim -S script.csx -B Output.bim

# Save to TMDL folder
TabularEditor.exe Model.bim -S script.csx -TMDL output/

# Save to legacy folder structure
TabularEditor.exe Model.bim -S script.csx -F output/

Best Practice Analyzer

bash
# Run BPA rules
TabularEditor.exe Model.bim -A rules.json

# Run BPA with Azure DevOps logging output
TabularEditor.exe Model.bim -A rules.json -V

# Run BPA with GitHub Actions logging output
TabularEditor.exe Model.bim -A rules.json -G

# Analyze excluding rules embedded in model annotations
TabularEditor.exe Model.bim -AX rules.json

Schema Check

bash
# Validate data source schemas against the model
TabularEditor.exe Model.bim -SC

Common Operations

1. Deploy Local Model to Service

bash
TabularEditor.exe Model.bim ^
    -D "powerbi://api.powerbi.com/v1.0/myorg/Workspace" "SemanticModel" ^
    -O -C

2. Run Script and Save

bash
TabularEditor.exe Model.bim -S format-dax.csx -B Model.bim

3. Run BPA Analysis

bash
TabularEditor.exe Model.bim ^
    -A https://raw.githubusercontent.com/microsoft/Analysis-Services/master/BestPracticeRules/BPARules.json ^
    -V

4. Refresh Model Data

bash
TabularEditor.exe "server" "database" ^
    -S "Model.RequestRefresh(RefreshType.Full);" ^
    -D "server" "database"

5. Export Model from Service

bash
TabularEditor.exe "powerbi://api.powerbi.com/v1.0/myorg/Workspace" "Model" ^
    -TMDL output/definition

Authentication

For authentication methods (Windows, Service Principal, Interactive) and CI/CD integration (Azure DevOps, GitHub Actions), see references/auth-and-cicd.md.

Exit Codes

CodeDescription
0Success
1Any error-level output (script error, deployment failure, BPA violations at severity >= 3)

File Formats

Input Formats

  • model.bim - Tabular JSON (legacy)
  • definition/ - TMDL folder (modern)
  • *.pbip - Power BI Project (TE3)

Output Formats

FlagFormatDescription
-B.bimTabular JSON
-TMDLfolderTMDL
-FfolderLegacy folder structure

Troubleshooting

For common errors (database not found, authentication failed, script execution failed), see references/auth-and-cicd.md.

Quick Reference Card

+---------------------------------------------------------+
| TABULAR EDITOR CLI QUICK REFERENCE                      |
+---------------------------------------------------------+
| SOURCES                                                 |
|   Model.bim           Local JSON model                  |
|   definition/         TMDL folder                       |
|   "server" "db"       XMLA connection                   |
+---------------------------------------------------------+
| SCRIPTS                                                 |
|   -S "code"           Inline C# script                  |
|   -S file.csx         Script file                       |
+---------------------------------------------------------+
| DEPLOYMENT                                              |
|   -D "server" "db"    Deploy to target                  |
|   -O                  Overwrite existing                |
|   -C                  Create if not exists              |
+---------------------------------------------------------+
| OUTPUT                                                  |
|   -B output.bim       Save as JSON                      |
|   -TMDL folder/       Save as TMDL                      |
+---------------------------------------------------------+
| BPA                                                     |
|   -A rules.json       Run BPA analysis                  |
|   -G results.sarif    Output BPA results                |
+---------------------------------------------------------+

References

To retrieve current XMLA and deployment docs, use microsoft_docs_search + microsoft_docs_fetch (MCP) if available, otherwise mslearn search + mslearn fetch (CLI). Search based on the user's request and run multiple searches as needed to ensure sufficient context before proceeding.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Te2 Cli AI skill do?

CLI syntax reference for Tabular Editor 2 (TabularEditor.exe); deployment, scripting, BPA analysis, and CI/CD integration. Automatically invoke when the user mentions "TabularEditor.exe", TE2 CLI flags (-D, -S, -A, -B, -TMDL, -O, -C), or asks to "deploy a model via CLI", "set up CI/CD for Power BI", "automate model deployment", "run BPA from command line", "save model as TMDL".

Why use Te2 Cli on TypingMind?

Because you install it once and use it with any model. Te2 Cli is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Te2 Cli in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/data-goblin/power-bi-agentic-development/tree/main/plugins/tabular-editor/skills/te2-cli. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Te2 Cli?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Te2 Cli?

As many as you like. As long as a model supports skills, you can use Te2 Cli with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Te2 Cli AI skill free?

Yes. It is published on GitHub by data-goblin under the GPL-3.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇