databricks-solutionsOfficial·23 Agent Skills Included

ai-dev-kit

Build Databricks pipelines, jobs, and apps with AI coding agents

Teaches AI coding assistants how to build on Databricks, covering Spark pipelines, jobs, Unity Catalog, model serving, and full-stack apps. Eliminates guesswork around SDKs, SQL syntax, and deployment patterns that slow down data engineering work. Includes a visual builder app, MCP server, and testing framework so teams ship Databricks projects faster with fewer errors.

1,883|413

↗

npx skills add databricks-solutions/ai-dev-kit --all -g -y

All Skills in This Repository (23)

Pure Emerald Level Indicators

📦 In Repo

databricks-solutions

tool-selection

Evaluates whether agent traces use Databricks MCP tools instead of Bash workarounds.

sql-correctness

Evaluates SQL in agent traces against Databricks syntax and Unity Catalog standards.

general-quality

Evaluates agent response quality across actionability, structure, hallucination, and error handling.

skill-test

Create, run, and review Databricks skill tests via a YAML-first GRP pipeline.

python-dev

Enforce Python code quality, testing, and environment management standards.

databricks-python-sdk

Automate Databricks SDK workflows for Python developers.

databricks-docs

Retrieve Databricks documentation pages and the llms.txt index.

databricks-config

Configure Databricks profiles and authenticate across Connect, CLI, and SDK.

mlflow-evaluation

Automate GenAI evaluation of ML agents with MLflow workflows.

model-serving

Deploy MLflow models and GenAI agents to Databricks Model Serving endpoints.

synthetic-data-generation

Generate synthetic Databricks datasets with Faker and Spark, saved as Parquet.

spark-declarative-pipelines

Automate creation, configuration, and updating of Databricks Lakeflow Spark Declarative Pipelines.

Official

Advanced

Frequently Asked Questions

FAQPage Schema

How to install Databricks AI Dev Kit?▼

Run `npx skills add databricks-solutions/ai-dev-kit --all -g -y` in your terminal to install all skills in this suite globally.

What can I build with Databricks AI Dev Kit?▼

You can build Spark pipelines, scheduled jobs, AI/BI dashboards, Unity Catalog tables, Genie spaces, MLflow experiments, model serving endpoints, and full-stack Databricks apps.

Which AI coding tools work with this kit?▼

It works with Claude Code, Cursor, Codex, Gemini CLI, GitHub Copilot, Windsurf, and other agents that support the standard SKILL.md format.

Do I need Databricks experience to use it?▼

No. The skills give your AI agent expert Databricks knowledge, so you describe what you want in plain English and the agent writes correct SDK, SQL, and deployment code.

How does the skill testing framework work?▼

The built-in skill-test framework runs evaluations against ground truth datasets, compares skill versions, and uses MLflow judges to measure whether each skill actually improves agent output.