Databricks AI Tools skill
Official Databricks skills guide coding agents through data work, Lakeflow jobs and resource deployment on the platform.
- 384 ★ on the repository
- Last commit
Extended access
Why this level
- Following these skills, the agent uses your Databricks profile for queries and resource changes, subject to account and agent permissions.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/databricks-ai-toolsDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Following these skills, the agent uses your Databricks profile for queries and resource changes, subject to account and agent permissions.
This is third-party code. Review the repository files before installing.
What it does
Databricks AI Tools adds task-specific Databricks guidance to a coding agent. Following the core instruction, the agent chooses a profile and checks authentication, then loads the relevant product guide. The collection covers data work, jobs and platform applications. Skills install through the official CLI or an agent’s marketplace. Plugins also provide supported commands and hooks to route tasks toward the relevant guide and diagnose authentication failures.
Who it is for. Data teams on Databricks building pipelines and maintaining jobs through Claude Code, Cursor or Codex.
Good fit when
- A new Lakeflow pipeline should follow platform-specific practices.
- An agent working across workspaces must select the correct profile before issuing commands.
- A project deploys resources through Declarative Automation Bundles.
- An authentication failure interrupted work and the profile needs a read-only diagnostic.
Not a fit when
- The project does not use Databricks and must remain platform-independent.
- You expect installing a skill to grant data access.
- You need experimental skills but can only install through a marketplace.
Example request
Check the Databricks profile and propose a Lakeflow job for this ingestion task. Show the selected workspace before creating resources.Limitations
The canonical installation path requires Databricks CLI 1.0.0 or newer and access to your workspace. CLI installation provides skills only; commands and hooks come through plugins and differ between clients. In Codex, review and enable hooks with `/hooks` after installation and each update. Experimental skills are excluded by default and do not receive the same official review and support as the stable collection.
How to disable. Uninstall the plugin through your agent’s manager or remove skill directories installed by the CLI. Databricks access and existing platform resources are managed separately.
FAQ
How do I install stable skills?
Run `databricks aitools install`. The CLI detects supported agents and writes skills into their directories.
Does CLI installation include plugin commands?
No. Use a supported agent’s marketplace installation for setup and diagnostic commands.
Do hooks block unwanted operations?
No. They route instructions and suggest authentication checks without blocking commands. Review profile rights and agent permissions separately.
How do CLI-installed skills update?
Use `databricks aitools update`. Update plugins through the agent’s marketplace mechanism.
Can I install one experimental skill?
Yes. Supply the skill name and `--experimental` to the CLI install command. Evaluate it separately before production use.
Discussion
No questions or reviews yet.
Related
SkillsDatabricks Field Engineering's agent kit: an installer for Databricks skills, an MCP server and a visual Builder App
Official Elastic skills for Elasticsearch, Kibana, Observability, Security and Elastic Cloud: ES|QL, indices, dashboards, alert triage
dbt Agent Skills
dbt-agent-skills
Official dbt Labs skills: the agent understands dbt projects, runs workflows and helps with migration
A Microsoft plugin with nine skills for Dataverse and Dynamics 365: queries, data import, data model, solutions, admin
A local Databricks API emulator with a 67-tool MCP server: agents run SQL and jobs without a real workspace
The official MathWorks kit that connects an AI agent to MATLAB through an MCP server and curated skills
README in short
This repository is the current source for Databricks skills, with some experimental material imported from AI Dev Kit. Stable guidance is organized by product under a shared core skill.
README badge
Original SKILL.md
---
name: "databricks-core"
description: "Databricks CLI operations and the parent/entry-point skill for Databricks CLI use: authentication, profile selection, and bundles. Load this first for CLI, auth, profile, and bundle tasks, then load the matching product skill. For finding or exploring data, answering questions about the data, or generating SQL, load the databricks-data-discovery skill (it routes to Genie One). Contains up-to-date guidelines for Databricks-related CLI tasks."
compatibility: Requires databricks CLI (>= v1.0.0)
metadata:
version: "0.1.0"
---
# Databricks
Core skill for Databricks CLI, authentication, and data exploration.
## Product Skills
For specific products, use dedicated skills:
- **databricks-jobs** - Lakeflow Jobs development and deployment
- **databricks-pipelines** - Lakeflow Spark Declarative Pipelines (batch and streaming data pipelines)
- **databricks-serverless** - Compute choice for jobs and pipelines (serverless, performance mode, classic fallback)
- **databricks-apps** - Full-stack TypeScript app development and deployment
- **databricks-lakebase** - Lakebase Postgres Autoscaling project management
- **databricks-model-serving** - Model Serving endpoint management and inference
For **data discovery, exploration, and query generation** — finding tables,
answering natural-language questions about the data, or generating SQL — use
**databricks-data-discovery** (it asks Genie One first, then falls back to manual
exploration). If it isn't installed, use the AI-tool commands below and
[Manual Data Exploration](manual-data-exploration.md).
## Prerequisites
1. **CLI installed and current**: the CLI must be >= v1.0.0. A CLI that is present but
too old is not "good enough" — it must be upgraded, not worked around.
- **Run the floor check in [CLI Installation](databricks-cli-install.md).** If it reports
`UPGRADE` or `INSTALL`: STOP and follow that reference file to upgrade or install — do
not proceed or tell the user their CLI is fine.
- **If another skill routed you here to upgrade** (it needs a newer CLI than v1.0.0 — e.g.
`databricks-setup-local` needs v1.16.0), that skill already detected the gap. A passing
v1.0.0 floor check is not enough: follow the Update / repair procedures to install the
latest stable, which satisfies any skill's floor.
- Note: In sandboxed environments (Cursor IDE, containers), install commands write outside the workspace and may be blocked. Present the install command to the user and ask them to run it in their own terminal.
- **Exception:** If CLI installation is blocked (sandboxed containers, restricted environments), ask the user whether to fall back to direct REST API calls using `DATABRICKS_HOST` and `DATABRICKS_TOKEN` environment variables if present in the shell. See the [Databricks REST API docs](https://docs.databricks.com/api/workspace/).