Build and manage Databricks data engineering pipelines, ML models, AI agents, and dashboards from Claude Code. Supports SQL and PySpark execution, Unity Catalog, model serving, Vector Search, and multi-environment deployments.
A brief one-sentence description of what this skill helps with.
Create and manage Databricks Agent Bricks: Knowledge Assistants (KA) for document Q&A, Genie Spaces for SQL exploration, and Supervisor Agents (MAS) for multi-agent orchestration. Use when building conversational AI applications on Databricks.
Use Databricks built-in AI Functions (ai_classify, ai_extract, ai_summarize, ai_mask, ai_translate, ai_fix_grammar, ai_gen, ai_analyze_sentiment, ai_similarity, ai_parse_document, ai_prep_search, ai_query, ai_forecast) to add AI capabilities directly to SQL and PySpark pipelines without managing model endpoints. Also covers document parsing and building custom RAG pipelines (parse → prep_search → index → query).
Create Databricks AI/BI dashboards. Use when creating, updating, or deploying Lakeview dashboards. CRITICAL: You MUST test ALL SQL queries via execute_sql BEFORE deploying. Follow guidelines strictly.
Builds Databricks applications. Prefers AppKit (TypeScript + React SDK) for new apps; falls back to Python frameworks (Dash, Streamlit, Gradio, Flask, FastAPI, Reflex) when Python is required. Handles OAuth authorization, app resources, SQL warehouse and Lakebase connectivity, model serving, foundation model APIs, and deployment. Use when building web apps, dashboards, ML demos, or REST APIs for Databricks, or when the user mentions AppKit, Streamlit, Dash, Gradio, Flask, FastAPI, Reflex, or Databricks app.
Admin access level
Server config contains admin-level keywords
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
📣 Heads up: a major evolution is coming
This will be the last release where AI Dev Kit skills are installed from the skill files in this repository. AI Dev Kit skills are becoming part of the official, engineering-supported Databricks skills set, and the skill files in this repo will soon be deprecated. In the next release you'll install these skills directly from the official Databricks set — either straight from the CLI, or through the AI Dev Kit installer, which will continue to guide you through the process.
What stays: The MCP server and Builder App will remain in this repository. The Builder App will keep being developed and improved, and the MCP server will be maintained and updated on a best-effort basis as GitHub issues are filed.
What's next: AI Dev Kit will continue to guide you through setting up your AI coding environment and be a place to find experimental tools developed by Field Engineering. Beyond the skills installs, we plan to add several tutorials to help you get started using coding agents for building on Databricks, including getting started with Genie Code or Omnigent.
A few skills will be renamed or merged in the official install. Most names are unchanged; the exceptions are:
Today (AI Dev Kit) Official Databricks skills databricks-bundlesdatabricks-dabsdatabricks-spark-declarative-pipelinesdatabricks-pipelinesdatabricks-lakebase-autoscale,databricks-lakebase-provisioneddatabricks-lakebase(merged)databricks-configfolded into databricks-core
🔒 Proactive Dependency Security
As part of our commitment to supply chain integrity, we continually monitor our dependency tree against known vulnerabilities and industry advisories. In response to a recently disclosed supply chain incident affecting litellm versions 1.82.7–1.82.8, we have audited our packages and removed the litellm dependency for most usage. It is solely used in the test directory for skills evaluation and optimization, and has been pinned to a safe version.
For full third-party attribution, see NOTICE.txt.
Databricks offers two paths for AI-assisted coding. Choose the one that matches your environment.
|
Free, first-party AI coding inside Databricks Built into every Databricks workspace at no extra cost, with deep native product context — your notebooks, jobs, and Unity Catalog data are already in scope. Ideal for users who have not started using AI-driven development tools or that are comfortable in Databricks. |
Databricks expertise, in the editor you already use Curated by Databricks field experts. Brings the patterns, skills, and 75+ executable tools your AI assistant needs to build on Databricks — wherever you're already coding. + Antigravity · Windsurf · OpenCode · and more! |
|
|
|
npx claudepluginhub databricks-solutions/ai-dev-kit --plugin databricks-ai-dev-kitOpinionated workflows for agentic software development on paired Lakebase branches: a Spec-First Test-Driven Development (SFTDD) state-machine (role agents + HITL gates), an SCM branch-lifecycle workflow (claim, PR, CI, merge), and a release workflow (promotion across tiers). Every git branch is paired with a Lakebase branch.
Translate Azure Data Factory pipelines to Databricks Lakeflow Jobs via Declarative Automation Bundles. Deterministic translation for known activity types with agentic fallback.
Databricks skills for CLI, Apps, Unity Catalog, Model Serving, Declarative Automation Bundles (DABs), and more.
5 live-detection Databricks skills — cost-leak-hunter, cluster-forensics, uc-migration-pilot, streaming-guardian, bundle-medic — backed by the databricks-workspace-mcp server.
Editorial "Data Engineering" bundle for Claude Code from Antigravity Awesome Skills.
Data engineering plugin - warehouse exploration, pipeline authoring, Airflow integration
ETL pipeline construction, data warehouse design, batch processing workflows, and data-driven feature development
Operate the entire Oracle AI Data Platform (AIDP) Workbench in natural language — a 37-skill agent (not a single-engine orchestrator). Discovers your catalog into a grounding cache (FK/join hints + value dictionaries), turns plain English into accurate Spark SQL, and runs the full lakehouse SQL lifecycle (CREATE/INSERT/UPDATE/DELETE/MERGE/OPTIMIZE/VACUUM/DESCRIBE HISTORY/time-travel on the Spark/Delta lakehouse). Ingests files, profiles data and sets quality rules, authors and repairs cron pipelines, provisions clusters (Compute/AI Compute), and debugs via the Spark UI. Governs the platform (roles + per-resource permissions, credential store, Delta Sharing, audit logs, user settings; plus native Git, bundles, and MLOps/MLflow in Preview) and ships AI — Agent Flows across 13 node types with guardrails (content moderation, prompt-attack prevention, PII detection), Knowledge Base RAG, high-code LangGraph/aidputils agents, and reusable Tools. A semantic model + verified-query repository are matched before free generation for accuracy. Signature differentiators: LLM-in-SQL via ai_generate('openai.gpt-5.4', '<prompt>') and cross-source federation in one Spark session. Runs via the official Oracle aidp CLI with an oci raw-request REST fallback — under either api_key or oci-session-token auth. Additive to your Oracle stack.