Agent skills for AI coding assistants
Agent skills are task-specific instruction files that AI coding assistants like Claude and GitHub Copilot can load to perform Databricks development tasks. Skills package domain-specific knowledge, best practices, and workflows into a format optimized for AI consumption. To learn how to extend Genie Code in the Databricks workspace, see Extend Genie Code with agent skills.
Skills follow the open Agent Skills standard. Each skill is a Markdown file with front-matter metadata that describes when and how the skill should be used. AI coding assistants automatically discover and load relevant skills based on the task at hand.
Install skills
Install skills using the Skills CLI, an open-source package manager for agent skills. The CLI scans a GitHub repository for skill files and installs them into your project so that your AI coding assistant can discover and use them automatically.
# List skills in a repository
npx skills add databricks/databricks-agent-skills --list
# Install specific skills
npx skills add databricks/databricks-agent-skills --skill databricks-apps --skill databricks-pipelines
# Install all skills from a repo to all agents
npx skills add databricks/databricks-agent-skills --all
# Remove interactively (select from installed skills)
npx skills remove
The CLI requires only that the repository contains skill files. Repository owners do not need to configure anything for the CLI to work with their skills.
Skill repositories
GitHub repository | Description | Skills |
|---|---|---|
Officially maintained core skills for Databricks development across compute, orchestration, storage, and apps. | Databricks CLI, Databricks Apps, Asset Bundles, Lakeflow Jobs, Lakebase, Model Serving, Lakeflow Spark Declarative Pipelines, serverless migration | |
Task-specific skills embedded inside Databricks app templates for agents (LangGraph, LangChain, OpenAI Agents SDK), App Kits (Lakebase, Genie, Analytics), and chatbot/data app frameworks (Streamlit, Dash, Gradio, Shiny, Flask, Node.js). | Quickstart, deploy, modify-agent, add-tools, create-tools, discover-tools, migrate-from-model-serving, run-locally, load-testing, supervisor APIs | |
Curated community skills covering 25+ Databricks development patterns. | Agent Bricks, AI Functions, AI/BI Dashboards, Databricks Apps, Asset Bundles, Databricks Lakehouse, Genie, Iceberg, Lakebase, Lakeflow Jobs, metric views, MLflow evaluation, Model Serving, Python SDK, Lakeflow Spark Declarative Pipelines, Structured Streaming, synthetic data, Unity Catalog, Vector Search, Zerobus ingest | |
Skills for instrumenting, debugging, and evaluating LLM agents with MLflow. | MLflow onboarding, MLflow agent, instrumenting tracing, retrieving and analyzing traces, querying metrics, agent evaluation, chat session analysis, MLflow doc search |
Next steps
- Extend Genie Code with agent skills: Create skills for the built-in Genie Code in your workspace.
- Migrate an agent from Model Serving to Databricks Apps: Use agent skills to migrate an agent from Model Serving to Databricks Apps.
- Author an AI agent and deploy it on Databricks Apps: Build and deploy an AI agent on Databricks Apps.