databricks-agent-skills

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_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 → chunk → index → query).

Create Databricks AI/BI dashboards. Must use when creating, updating, or deploying Lakeview dashboards as Databricks Dashboard have a unique json structure. CRITICAL: You MUST test ALL SQL queries via CLI BEFORE deploying. Follow guidelines strictly.

Train ML models on Databricks. Use for: classification/regression/deep-learning (XGBoost, scikit-learn, LightGBM, PyTorch) with Optuna, @prod/@challenger aliases, batch scoring (spark_udf for plain models, fe.score_batch for feature-store-backed), custom PyFunc, custom ResponsesAgent (LangGraph + UC Function/Vector Search); UC feature tables + FeatureLookup + point-in-time joins + Lakebase online store; declarative Feature Views (create_feature, DeltaTableSource, RollingWindow/SlidingWindow/TumblingWindow, materialize_features, streaming Kafka features). NOT for: endpoint ops (databricks-model-serving), MLflow evaluation (databricks-mlflow-evaluation).

Comprehensive guide to Spark Structured Streaming for production workloads. Use when building streaming pipelines, working with Kafka ingestion, implementing Real-Time Mode (RTM), configuring triggers (processingTime, availableNow), handling stateful operations with watermarks, optimizing checkpoints, performing stream-stream or stream-static joins, writing to multiple sinks, or tuning streaming cost and performance.

Develop and deploy Lakeflow Jobs on Databricks via DABs, Python SDK, or the CLI. Use when creating data engineering jobs with notebooks, Python wheels, SQL, dbt, or pipelines. Invoke BEFORE starting implementation.

Python backend for Databricks Apps — FastAPI (default), Flask, Dash, Streamlit, Gradio, Reflex. **Default for a new Databricks App is `databricks-apps` (AppKit — Node/TypeScript/React) — reach for it first.** Use this skill only when the user asks for a Python backend, extends an existing Python app, or the team is Python-only. Covers OAuth auth, app resources, SQL warehouse and Lakebase connectivity, foundation-model / Vector Search / model-serving APIs (via `databricks-python-sdk`), and deployment via CLI or DABs.

Discover, explore, and query Databricks data via Genie — the CLI equivalent of the Genie One MCP. MUST be invoked whenever the user asks to find or locate data ('what tables are in X', 'where does X live', 'which catalog/schema has Y'), explore or profile a table, answer a natural-language question about the data, or write a SQL query.

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.

Unity Catalog metric views: define, create, query, and manage governed business metrics in YAML. Use when building standardized KPIs, revenue metrics, order analytics, or any reusable business metrics that need consistent definitions across teams and tools.

MLflow 3 GenAI agent evaluation. Use when writing mlflow.genai.evaluate() code, creating @scorer functions, using built-in scorers (Guidelines, Correctness, Safety, RetrievalGroundedness), building eval datasets from traces, setting up trace ingestion and production monitoring, aligning judges with MemAlign from domain expert feedback, or running optimize_prompts() with GEPA for automated prompt improvement.

Generate realistic synthetic data using Spark + Faker (strongly recommended). Supports serverless execution, multiple output formats (Parquet/JSON/CSV/Delta), and scales from thousands to millions of rows. For small datasets (<10K rows), can optionally generate locally and upload to volumes. Use when user mentions 'synthetic data', 'test data', 'generate data', 'demo dataset', 'Faker', or 'sample data'.

Unity Catalog governance, access control, and observability. Use to grant or revoke access (GRANT/REVOKE), reason about the privilege model and ownership, set up row-level security and column masks, create external locations and storage credentials, define catalogs/schemas/tables/volumes, answer "who can read this table", and query system tables (audit, lineage, billing) or work with volume files in /Volumes/.

Build Zerobus Ingest clients for near real-time data ingestion into Databricks Delta tables via gRPC. Use when creating producers that write directly to Unity Catalog tables without a message bus, working with the Zerobus Ingest SDK in Python/Java/Go/TypeScript/Rust, generating Protobuf schemas from UC tables, or implementing stream-based ingestion with ACK handling and retry logic.

Databricks AI Runtime (`air`) CLI — the command-line tool for submitting and managing GPU training workloads on Databricks serverless compute. Use for: running `air` workloads, custom Docker image setup, environment configuration, and troubleshooting `air` jobs.

Create and query Databricks Genie Spaces for natural language SQL exploration. Use when building Genie Spaces, exporting and importing Genie Spaces, migrating Genie Spaces between workspaces or environments, or asking questions via the Genie Conversation API.

Create Agent Bricks: Knowledge Assistants (KA) for document Q&A and Supervisor Agents for multi-agent orchestration (MAS).

Design the UX of custom-code Databricks Apps (AppKit/React) data screens — KPI/overview pages, reports, charts, tables, and Genie/chat data assistants — mapped to concrete AppKit components. Use when BUILDING or reviewing the UI of an AppKit/React app that displays data or answers data questions: choosing genre, layout, charts, KPIs, semantic color, required states (loading/empty/error), IBCS notation, and AI-result trust (showing generated SQL/sources for Genie/chat). A plain "create a dashboard" request means a managed AI/BI (Lakeview) dashboard → use databricks-aibi-dashboards, NOT this skill. Also NOT for non-data frontend (forms, settings, auth, marketing) or scaffolding/build/deploy (→ databricks-apps). Complements databricks-apps; use it alongside whenever a custom app has a chart, table, KPI, report, or Genie/chat/AI surface.

Build apps on Databricks Apps platform. Use when asked to create data apps, analytics tools, or custom interactive visualizations. A plain "create a dashboard" request means a managed AI/BI (Lakeview) dashboard → use databricks-aibi-dashboards, not this skill. Evaluates data access patterns (analytics vs Lakebase synced tables) before scaffolding. Invoke BEFORE starting implementation.

Databricks SQL (DBSQL) advanced features and SQL warehouse capabilities. This skill MUST be invoked when the user mentions: "DBSQL", "Databricks SQL", "SQL warehouse", "SQL scripting", "stored procedure", "CALL procedure", "materialized view", "CREATE MATERIALIZED VIEW", "pipe syntax", "|>", "geospatial", "H3", "ST_", "spatial SQL", "collation", "COLLATE", "ai_query", "ai_classify", "ai_extract", "ai_gen", "AI function", "http_request", "remote_query", "read_files", "Lakehouse Federation", "recursive CTE", "WITH RECURSIVE", "multi-statement transaction", "temp table", "temporary view", "pipe operator". SHOULD also invoke when the user asks about SQL best practices, data modeling patterns, or advanced SQL features on Databricks.

Databricks documentation reference via llms.txt index. Use when other skills do not cover a topic, looking up unfamiliar Databricks features, or needing authoritative docs on APIs, configurations, or platform capabilities.

Execute code and manage compute on Databricks: run Python/Scala/SQL/R via serverless, classic, or interactive clusters, and create/resize/delete clusters and SQL warehouses.

Apache Iceberg tables on Databricks — Managed Iceberg tables, External Iceberg Reads (fka Uniform), Compatibility Mode, Iceberg REST Catalog (IRC), Iceberg v3, Snowflake interop, PyIceberg, OSS Spark, external engine access and credential vending. Use when creating Iceberg tables, enabling External Iceberg Reads (uniform) on Delta tables (including Streaming Tables and Materialized Views via compatibility mode), configuring external engines to read Databricks tables via Unity Catalog IRC, integrating with Snowflake catalog to read Foreign Iceberg tables

Databricks Lakebase Postgres: projects, scaling, connectivity, Lakebase synced tables, and Data API. Use when asked about Lakebase databases, OLTP storage, or connecting apps to Postgres on Databricks.

Build managed ingestion pipelines into Databricks using Lakeflow Connect. Use when ingesting from SaaS apps (Salesforce, Workday Reports, ServiceNow, Google Analytics 4, HubSpot, Confluence) or databases (SQL Server cloud and on-prem; PostgreSQL/MySQL CDC in PuPr) into Unity Catalog with serverless pipelines.

Databricks Model Serving endpoint lifecycle and ops. Use when asked to: CRUD serving endpoints (CLI or MLflow Deployments client); configure traffic routing for A/B / canary deploys and zero-downtime version swaps; retrieve OpenAPI schemas; inspect logs, metrics, or permissions; manage AI Gateway rate limits; discover Foundation Model API endpoints at runtime; integrate endpoints into Databricks Apps; or stream from off-platform clients (Vercel AI SDK v6, standalone Node.js). NOT for: training, MLflow autologging, UC registration, custom PyFunc/ResponsesAgent authoring (databricks-ml-training); Knowledge Assistants/Supervisor Agents (databricks-agent-bricks); MLflow evaluation (databricks-mlflow-evaluation).

Databricks development guidance including Python SDK, Databricks Connect, CLI, and REST API. Use when working with databricks-sdk, databricks-connect, or Databricks APIs.

Build RAG / unstructured-document evaluation datasets and demo documents (e.g. for Knowledge Assistant) on Databricks: generate synthetic PDFs locally, upload to Unity Catalog volumes, and pair each document with test questions for retrieval evaluation.

Create, configure, validate, deploy, run, and manage Declarative Automation Bundles (DABs, formerly Databricks Asset Bundles). Use when working with Databricks resources via DABs including dashboards, jobs, pipelines, alerts, volumes, and apps.

Develop Lakeflow Spark Declarative Pipelines (formerly Delta Live Tables) on Databricks. Use when building batch or streaming data pipelines with Python or SQL. Invoke BEFORE starting implementation.

Migrate Databricks workloads from classic compute to serverless compute. Use when migrating notebooks, jobs, pipelines, or Scala JARs (`spark_jar_task`) from classic clusters to serverless, checking if existing code is serverless-compatible, or writing new serverless-compatible code. Provides concrete fixes for the serverless Spark Connect architecture and guides the full migration. Not for classic DBR version upgrades or cluster configuration changes within classic compute.

Databricks Vector Search endpoints and indexes for RAG and semantic search; covers index types, search modes, end-to-end RAG patterns

Build custom Python data sources for Apache Spark using the PySpark DataSource API — batch and streaming readers/writers for external systems. Use this skill whenever someone wants to connect Spark to an external system (database, API, message queue, custom protocol), build a Spark connector or plugin in Python, implement a DataSourceReader or DataSourceWriter, pull data from or push data to a system via Spark, or work with the PySpark DataSource API in any way. Even if they just say "read from X in Spark" or "write DataFrame to Y" and there's no native connector, this skill applies.