databricks/databricks-agent-skills
10 skills5.9k installs2.4k starsGitHub
Install
npx skills add https://github.com/databricks/databricks-agent-skillsSkills in this repo
1Databricks CoreThe databricks-core skill is the parent entry point for all Databricks agent work covering CLI authentication, profile selection, bundle deployments, data exploration, and Genie natural-language data Q&A. It requires databricks CLI version 0.292.0 or newer and routes agents to specialized child skills after establishing credentials and workspace context. Agents load databricks-core first before SQL, jobs, or ML workflows to avoid auth and profile misconfiguration. The skill standardizes how Claude agents interact with Databricks workspaces safely. Parent entry skill for all Databricks agent operations. CLI auth, profiles, bundles, and data exploration. Genie natural-language data Q&A routing. Requires databricks CLI >= v0.292.0. Load first before specialized Databricks child skills. Entry-point Databricks CLI skill for auth, profiles, bundles, data exploration, and Genie Q&A.1.2kinstalls2Databricks AppsDatabricks Apps Development guides agents through building apps on the Databricks Apps platform using databricks-core for auth plus mandatory data access and state storage decision gates before scaffolding. It requires databricks apps manifest before init, derives --features and --set from plugin resources, and enforces typegen-before-UI for analytics apps with SQL files in config/queries/. Lakebase versus analytics tradeoffs cover sub-second synced tables versus warehouse queries for dashboards, with explicit user choice and smoke test selector updates to avoid validate failures. AppKit API calls must use npx @databricks/appkit docs for authoritative signatures, and lint forbids double type assertions. Genie apps follow a table-discovery workflow before asking for space IDs, and post-deploy verification uses databricks apps get and logs commands.811installs3Databricks PipelinesThe databricks-pipelines skill guides agents building and operating Databricks Lakeflow pipelines via workspace APIs and SDK patterns. Covers pipeline definition, scheduling, dependency management, monitoring failed runs, and aligning notebook or wheel tasks with production data engineering standards. Agents validate cluster policies, identity permissions, and incremental processing requirements before deploying changes. Use when automating ETL or ML feature pipelines on Databricks with agent assistance.694installs4Databricks JobsThe databricks-jobs skill helps agents configure Databricks jobs for notebook, Python wheel, and pipeline tasks. Workflow covers job JSON or UI-equivalent definitions, cluster selection, schedules and triggers, retry policies, email or webhook notifications, and run-level troubleshooting from event logs. Validates permissions and cost-aware cluster policies before enabling production schedules. Use when automating recurring data processing or ML training jobs on Databricks.665installs5Databricks LakebaseDatabricks 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. **FIRST**: Use the parent `databricks-core` skill for CLI basics, authentication, and profile selection.623installs6Databricks DabsCreate, 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. Use this skill for any bundle-related request including creating, configuring, validating, deploying, running, and managing Databricks resources through DABs.614installs7Databricks Model ServingDatabricks 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). **FIRST**: Use the parent `databricks-core` skill for CLI basics, authentication, and profile selection.511installs8Databricks Serverless MigrationMigrate 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. **FIRST**: Use the parent `databricks-core` skill for CLI basics, authentication, and profile selection.431installs9DatabricksDatabricks CLI operations: auth, profiles, data exploration, and bundles. Contains up-to-date guidelines for Databricks-related CLI tasks. Core skill for Databricks CLI, authentication, and data exploration.212installs10Databricks Vector SearchDatabricks Vector Search endpoints and indexes for RAG and semantic search covers index types search modes end-to-end RAG patterns name databricks-vector-search description Databricks Vector Search endpoints and indexes for RAG and semantic search covers index types search modes end-to-end RAG patterns metadata version 0 1 0 parent databricks-core Databricks Vector Search FIRST Use the parent databricks-core skill for CLI basics authentication and profile selection Patterns for creating managing and querying vector search indexes for RAG and semantic search applications When to Use Use this skill when Building RAG Retrieval-Augmented Generation applications Implementing semantic search or similarity matching Creating vector indexes from Delta tables Choosing between storage-optimized and standard endpoints Querying vector indexes with filters Overview Databricks Vector Search provides managed vector similarity search with automatic embedding generation and Delta Lake integration Component Description Endpoint Compute resource hosting indexes Standard or Storage-Optimized Index Vector data structure for similarity search Delta Sync Auto-syncs with source Delta table Direct Access M.190installs