Skip to content
Databricks Core

Databricks Core Skill

Databricks' official entry-point agent skill: CLI authentication, profile and workspace selection, asset bundles, and routing to the right product skill for the task.

GitHub Docs

Install

Install with the skills CLI

One command for Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf and dozens of other agents. Needs Node.js; the skill is fetched straight from databricks/databricks-agent-skills.

$ npx skills add databricks/databricks-agent-skills --skill databricks-core

Run it in a terminal. The CLI finds the agents installed on your machine, asks which ones to add the skill to, and whether to install it into the folder you ran it from or for all your projects.

Other ways to install

Copy the whole skill folder — SKILL.md and any scripts or references beside it — into ~/.claude/skills/databricks-core/, where Claude Code picks it up in every project. Only git is needed.

tmp=$(mktemp -d) && \
  git clone --depth 1 --branch main https://github.com/databricks/databricks-agent-skills.git "$tmp" && \
  mkdir -p ~/.claude/skills && \
  cp -R "$tmp"/skills/databricks-core ~/.claude/skills/databricks-core

No scripts or references next to it? Saving the SKILL.md alone as ~/.claude/skills/databricks-core/SKILL.md works too.

Using another agent? Its personal skills folder
Codex
~/.agents/skills/
Cursor
~/.cursor/skills/
GitHub Copilot
~/.copilot/skills/
Gemini CLI
~/.gemini/skills/
Windsurf
~/.codeium/windsurf/skills/
OpenCode
~/.config/opencode/skills/

About

  • Entry-point skill that routes to the right Databricks product skill
  • Covers CLI authentication, profile selection and workspace targeting
  • Handles Asset Bundle (DAB) workflows for deploying resources
  • Falls back to manual data exploration when Genie One is unavailable
  • Requires the Databricks CLI at v0.292.0 or newer

databricks-core is the front door to Databricks' officially published agent skill collection — 29 stable skills covering everything from Lakeflow Jobs and Spark Declarative Pipelines to Unity Catalog, Vector Search, Model Serving and AI/BI dashboards.

Its job is deliberately narrow: get the agent authenticated and pointed at the right workspace, then hand off. That means Databricks CLI basics, profile management and workspace targeting, plus Databricks Asset Bundle (DAB) workflows for declaratively deploying jobs, pipelines and other resources. It requires the Databricks CLI at v0.292.0 or newer and checks with databricks --version before doing anything.

The routing behaviour is what makes it worth installing first rather than cherry-picking a product skill. For data discovery — finding tables, answering natural-language questions about a dataset, or generating SQL — it defers to databricks-data-discovery, which asks Genie One first and only then falls back to manual schema exploration. For product work it names the specific skill: databricks-jobs, databricks-pipelines, databricks-apps, databricks-lakebase, databricks-model-serving and the rest. If a downstream skill is not installed, it degrades to CLI commands and a bundled manual data-exploration guide rather than guessing.

Installation. The canonical path is the Databricks CLI itself: databricks aitools install. It is also published to the Claude Code marketplace (/plugin marketplace add databricks/databricks-agent-skills), Cursor (/add-plugin databricks), and the GitHub Copilot and Codex marketplaces. Experimental skills live in experimental/ behind an --experimental flag. Distributed under the Databricks License rather than a standard OSS licence — read it before redistributing.

Best for data and platform engineers who already work in a Databricks workspace and want their agent to stop hallucinating CLI flags. It is not a general Spark or SQL tutor; it assumes a Databricks account exists.

Try it

Once installed, ask your agent something like:

Authenticate to my Databricks workspace with the prod profile and deploy this asset bundle.

SKILL.md

The instructions your agent loads, as published by Databricks.

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 (>= v0.292.0)
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-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: Run databricks --version to check.
  • If the CLI is missing or outdated (< v0.292.0): STOP. Do not proceed or work around a missing CLI.
  • Read the [CLI Installation](databricks-cli-install.md) reference file and follow the instructions to guide the user through installation.
  • 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.
  1. Authenticated: databricks auth profiles
  • If not: see [CLI Authentication](databricks-cli-auth.md)
Profile Selection - CRITICAL

NEVER auto-select a profile.

  1. List profiles: databricks auth profiles
  2. Present ALL profiles to user with workspace URLs
  3. Let user choose (even if only one exists)
  4. Offer to create new profile if needed
Claude Code - IMPORTANT

Each Bash command runs in a separate shell session.

# WORKS: --profile flag
databricks apps list --profile my-workspace

# WORKS: chained with &&
export DATABRICKS_CONFIG_PROFILE=my-workspace && databricks apps list

# DOES NOT WORK: separate commands
export DATABRICKS_CONFIG_PROFILE=my-workspace
databricks apps list  # profile not set!
Data Exploration — Use AI Tools

Use these instead of manually navigating catalogs/schemas/tables:

# discover table structure (columns, types, sample data, stats)
databricks experimental aitools tools discover-schema catalog.schema.table --profile <PROFILE>

# run ad-hoc SQL queries
databricks experimental aitools tools query "SELECT * FROM table LIMIT 10" --profile <PROFILE>

# find the default warehouse
databricks experimental aitools tools get-default-warehouse --profile <PROFILE>

Names are literal. Use catalog/schema/table names exactly as given — never change a
hyphen to an underscore or otherwise normalize them. In SQL, backtick-quote any name part
with special characters (e.g. ` my-catalog.schema.table `); unquoted hyphens cause a
parse error.

These commands are first-class for running known SQL and profiling — Genie isn't
required for that. For natural-language data questions, locating data you can't
pin down, or generating a query from a question, prefer the databricks-data-discovery
skill (above) if it's installed. See [Manual Data Exploration](manual-data-exploration.md) for the
full command surface, quoting rules, and troubleshooting.

Quick Reference

⚠️ CRITICAL: Some commands use positional arguments, not flags

# current user
databricks current-user me --profile <PROFILE>

# list resources
databricks apps list --profile <PROFILE>
databricks jobs list --profile <PROFILE>
databricks clusters list --profile <PROFILE>
databricks warehouses list --profile <PROFILE>
databricks pipelines list --profile <PROFILE>
databricks serving-endpoints list --profile <PROFILE>

# ⚠️ Unity Catalog — POSITIONAL arguments (NOT flags!)
databricks catalogs list --profile <PROFILE>

# ✅ CORRECT: positional args
databricks schemas list <CATALOG> --profile <PROFILE>
databricks tables list <CATALOG> <SCHEMA> --profile <PROFILE>
databricks tables get <CATALOG>.<SCHEMA>.<TABLE> --profile <PROFILE>

# ❌ WRONG: these flags/commands DON'T EXIST
# databricks schemas list --catalog-name <CATALOG>    ← WILL FAIL
# databricks tables list --catalog <CATALOG>           ← WILL FAIL
# databricks sql-warehouses list                       ← doesn't exist, use `warehouses list`
# databricks execute-statement                         ← doesn't exist, use `experimental aitools tools query`
# databricks sql execute                               ← doesn't exist, use `experimental aitools tools query`

# When in doubt, check help:
# databricks schemas list --help

# get details
databricks apps get <NAME> --profile <PROFILE>
databricks jobs get --job-id <ID> --profile <PROFILE>
databricks clusters get --cluster-id <ID> --profile <PROFILE>

# bundles
databricks bundle init --profile <PROFILE>
databricks bundle validate --profile <PROFILE>
databricks bundle deploy -t <TARGET> --profile <PROFILE>
databricks bundle run <RESOURCE> -t <TARGET> --profile <PROFILE>
Troubleshooting
ErrorSolution
cannot configure default credentialsUse --profile flag or authenticate first
configuration does not support OAuth tokensThe command requires OAuth (e.g., databricks apps logs). Re-authenticate with databricks auth login --host <URL> --profile <PROFILE>. See [CLI Authentication](databricks-cli-auth.md).
PERMISSION_DENIEDCheck workspace/UC permissions
RESOURCE_DOES_NOT_EXISTVerify resource name/id and profile
Required Reading by Task
TaskREAD BEFORE proceeding
First time setup[CLI Installation](databricks-cli-install.md)
Auth issues / new workspace[CLI Authentication](databricks-cli-auth.md)
Exploring tables/schemas[Manual Data Exploration](manual-data-exploration.md) (or databricks-data-discovery if installed)
Deploying jobs/pipelinesUse /databricks-dabs
Reference Guides
  • [CLI Installation](databricks-cli-install.md)
  • [CLI Authentication](databricks-cli-auth.md)
  • [Manual Data Exploration](manual-data-exploration.md)
Install
New

Firecrawl's skill for reading known web pages with its CLI: scrape a URL to markdown, links or schema-typed JSON, batch-scrape URL lists, cap PDF pages, and discover and run data-provider tools for structured results.

New

Firecrawl's official routing skill for its CLI: lets an agent search the web, scrape and map sites, crawl sections, monitor pages for changes and interact with pages behind clicks or logins, saving clean markdown to .firecrawl/.

Browse all skills →