Skip to main content
skill CX Codex

databricks-apps — Claude Code skill for Databricks Apps builds

A skill that walks your agent through building a custom Databricks Apps project: data access check first, then scaffolding, SQL, UI and deploy.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add databricks/databricks-agent-skills --skill databricks-apps -a claude-code
Open on GitHub

What databricks-apps does

Before any scaffolding, the skill asks how the app should read data — through analytics queries or through Lakebase synced tables. It also checks whether a custom app is warranted at all: for a plain dashboard request it points to a managed AI/BI (Lakeview) dashboard and the databricks-aibi-dashboards skill instead.

Reference guides are split by task: SQL, frontend components, the AppKit SDK including useAnalyticsQuery, custom API endpoints, Lakebase, Genie chat, Model Serving, UC Volumes files and Lakeflow Jobs. Projects built on Streamlit, FastAPI, Flask, Gradio or Next.js get their own guide, and so does platform behaviour around permissions and limits.

You need databricks CLI v0.294.0 or newer plus the parent databricks-core skill, which handles auth and profile choice. Only npm and pnpm are supported — a yarn or bun project makes the skill stop and ask you to pick. Deploy checks run through databricks apps validate --profile <PROFILE>. The bundled Playwright smoke test is written for the starter app and looks for its “Minimal Databricks App” heading, so rewrite the selectors before validating or it will fail.

What it helps with

  • decide between a managed AI/BI dashboard and a custom app
  • pick analytics queries or Lakebase synced tables for data access
  • build a Genie chat surface or write-back flow AI/BI can't do
  • call Model Serving or Lakeflow Jobs from the app UI
  • fix Playwright smoke tests so validation passes

Example prompts for the agent

  • Build a Databricks app with a query table and a chart grouped by status
  • Add a Genie chat page to this app and wire it to the warehouse
  • Run databricks apps validate on this project and fix what it reports

How to install databricks-apps

1Skills CLI (Vercel)

npx skills add databricks/databricks-agent-skills --skill databricks-apps -a claude-code

2Manually: put the files in place

~/.claude/skills/databricks-apps/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/databricks-apps/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about databricks-apps

How do I install databricks-apps in Claude Code?

Run npx skills add databricks/databricks-agent-skills --skill databricks-apps -a claude-code. The skill file then sits at ~/.claude/skills/databricks-apps/SKILL.md.

What does databricks-apps do?

It guides the agent through a Databricks Apps build: choosing the data access pattern, scaffolding, queries, UI work, smoke tests and deployment.

What do I need for it to work?

databricks CLI from v0.294.0 up, and the databricks-core skill for auth and profiles. Installs go through npm or pnpm; yarn and bun are not supported.

Similar skills

All skills for Data and databases →

From the same set18

databricks-core Guides Databricks CLI work around authentication, profile choice, and bundles. Use it before CLI tasks involving Databricks resources. CX Codex +1 1,700installs databricks-pipelines Guides agents in designing Lakeflow Spark Declarative Pipelines on Databricks with Python or SQL. It selects dataset types and configures Auto CDC before coding begins. CX Codex +1 987installs databricks-jobs Teaches your coding agent to build and ship Lakeflow Jobs on Databricks: tasks, dependencies, triggers, alerts. Useful when a new data pipeline should be defined in code, not clicked together. CX Codex +1 943installs databricks-lakebase This skill guides agents through Databricks Lakebase Postgres projects, app connectivity, scaling, and synced tables. Use it when working with Lakebase databases or OLTP storage. CX Codex +1 903installs databricks-dabs Teaches the agent to build, validate and deploy Declarative Automation Bundles in Databricks, covering jobs, pipelines, dashboards and apps. CX Codex +1 892installs databricks-model-serving A skill that steers the agent through Databricks Model Serving endpoint work: creation, version swaps, traffic splits, logs. Useful when model rollouts go through CLI or MLflow. CX Codex +1 715installs databricks-serverless-migration A skill that checks Databricks notebooks and jobs for serverless compatibility, names the broken parts and walks the migration step by step. CX Codex +1 631installs databricks-vector-search Skill for creating Databricks vector indexes and querying embeddings in Delta tables. Useful for RAG applications and semantic search. CX Codex +1 380installs

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor