ai-dev-kit
Databricks Toolkit for Coding Agents provided by Field Engineering
The Databricks AI Dev Kit delivers official Databricks agent skills and tools to AI coding assistants including Claude Code, Cursor, Copilot, and Gemini CLI. It provides curated skills that teach AI agents how to build Spark pipelines, manage Unity Catalog, deploy ML models, create Databricks Apps, and orchestrate workflows using Databricks best practices. Installed through the Databricks CLI (databricks aitools install), the kit integrates Databricks expertise directly into your preferred development environment, enabling AI-assisted development of data engineering and machine learning projects on the Databricks platform.
Key Features
Use Cases
- 01Building streaming data pipelines with Auto Loader, CDC, and SCD Type 2 transformations using AI assistance
- 02Creating and managing Unity Catalog tables, volumes, and governance policies through conversational interfaces
- 03Developing multi-task Databricks Jobs and orchestrating complex workflow DAGs with AI guidance
- 04Deploying ML models and AI agents to Databricks Model Serving endpoints with MLflow integration
- 05Building full-stack Databricks Apps combining foundation models with web interfaces
- 06Setting up RAG-based knowledge assistants for document Q&A and natural language data exploration with Genie Spaces
Related Skills
View moresuperpowers
An agentic skills framework & software development methodology that works.
skills
Skills for Real Engineers. Straight from my .agents directory.
skills
Public repository for Agent Skills
ponytail
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
ai-dev-kit — FAQ
What is the Databricks AI Dev Kit?+
It's a toolkit that brings Databricks expertise to AI coding assistants through official agent skills, teaching your AI assistant how to build data pipelines, manage Unity Catalog, deploy ML models, and develop Databricks Apps using platform best practices.
How do I install the Databricks AI Dev Kit skills?+
Run the installation script (bash <(curl -sL https://raw.githubusercontent.com/databricks-solutions/ai-dev-kit/main/install.sh)) which uses the Databricks CLI to install skills. You need Databricks CLI v1.0.0+ and an AI coding environment like Claude Code, Cursor, or Copilot.
Which AI coding assistants work with the Databricks AI Dev Kit?+
It supports Claude Code, Cursor, GitHub Copilot, Gemini CLI, Antigravity, Codex, Windsurf, OpenCode, Kiro, and other agent frameworks that can use skills or MCP servers.
Do I need API keys or a Databricks account to use these skills?+
Yes, you need a configured Databricks CLI (v1.0.0+) with authentication to a Databricks workspace. The skills interact with your Databricks environment through the CLI's credentials.
Is the Databricks AI Dev Kit free to use?+
The AI Dev Kit itself is open source and free. However, you need access to a Databricks workspace and an AI coding assistant, which may have their own licensing requirements.
Can I use these skills in Genie Code inside Databricks?+
Yes, you can upload skills to Genie Code by running the install_genie_code_skills.py notebook in your workspace, which installs skills to /Workspace/Users/<you>/.assistant/skills for use in Genie Code sessions.
How do I install ai-dev-kit?+
Open the source repository on GitHub and follow its README. ai-dev-kit is a skill — MCP Agents Market links you directly to the official repo.
Is ai-dev-kit free?+
ai-dev-kit is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.