[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"org-databricks":3,"repo-skills-v-0-3-0":60},{"org":4,"repos":44},{"slug":5,"name":6,"logoUrl":7,"githubOrg":5,"website":8,"skillCount":9,"repoCount":10,"topRepos":11,"topTags":14,"lastUpdatedAt":43},"databricks","Databricks","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fdatabricks.png","https:\u002F\u002Fwww.databricks.com",31,1,[12],{"name":13,"skillCount":9},"databricks\u002Fdatabricks-agent-skills",[15,16,19,22,25,28,31,34,37,40],{"slug":5,"name":6},{"slug":17,"name":18},"data-engineering","Data Engineering",{"slug":20,"name":21},"data-analysis","Data Analysis",{"slug":23,"name":24},"data-pipeline","Data Pipeline",{"slug":26,"name":27},"python","Python",{"slug":29,"name":30},"analytics","Analytics",{"slug":32,"name":33},"api-development","API Development",{"slug":35,"name":36},"cli","CLI",{"slug":38,"name":39},"deployment","Deployment",{"slug":41,"name":42},"engineering","Engineering","2026-07-31T05:53:34.774642",[45],{"name":46,"fullName":13,"repoUrl":47,"skillCount":9,"stars":48,"forks":49,"description":50,"topics":51,"topTags":52,"topTagCount":59,"lastUpdatedAt":43},"databricks-agent-skills","https:\u002F\u002Fgithub.com\u002Fdatabricks\u002Fdatabricks-agent-skills",204,60,null,[],[53,54,55,56,57,58],{"slug":5,"name":6},{"slug":17,"name":18},{"slug":20,"name":21},{"slug":23,"name":24},{"slug":26,"name":27},{"slug":29,"name":30},52,{"items":61,"total":9},[62,80,92,105,120,140,151,172,184,199,212,225,239,248,263,274,287,300,313,328,344,357,368,379],{"slug":63,"name":63,"fn":64,"description":65,"org":66,"tags":67,"stars":48,"repoUrl":47,"updatedAt":79},"databricks-agent-bricks","create Databricks Agent Bricks","Create Agent Bricks: Knowledge Assistants (KA) for document Q&A and Supervisor Agents for multi-agent orchestration (MAS).",{"slug":5,"name":6,"logoUrl":7,"githubOrg":5},[68,72,73,76],{"name":69,"slug":70,"type":71},"Agents","agents","tag",{"name":6,"slug":5,"type":71},{"name":74,"slug":75,"type":71},"Knowledge Management","knowledge-management",{"name":77,"slug":78,"type":71},"Multi-Agent","multi-agent","2026-07-15T05:41:38.548954",{"slug":81,"name":81,"fn":82,"description":83,"org":84,"tags":85,"stars":48,"repoUrl":47,"updatedAt":91},"databricks-ai-functions","use Databricks built-in AI functions","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).",{"slug":5,"name":6,"logoUrl":7,"githubOrg":5},[86,87,88],{"name":21,"slug":20,"type":71},{"name":6,"slug":5,"type":71},{"name":89,"slug":90,"type":71},"LLM","llm","2026-07-31T05:53:33.562077",{"slug":93,"name":93,"fn":94,"description":95,"org":96,"tags":97,"stars":48,"repoUrl":47,"updatedAt":104},"databricks-ai-runtime","submit and manage Databricks GPU workloads","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.",{"slug":5,"name":6,"logoUrl":7,"githubOrg":5},[98,99,100,103],{"name":36,"slug":35,"type":71},{"name":6,"slug":5,"type":71},{"name":101,"slug":102,"type":71},"Docker","docker",{"name":42,"slug":41,"type":71},"2026-07-12T08:04:55.843982",{"slug":106,"name":106,"fn":107,"description":108,"org":109,"tags":110,"stars":48,"repoUrl":47,"updatedAt":119},"databricks-aibi-dashboards","create Databricks AI\u002FBI dashboards","Create Databricks AI\u002FBI 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.",{"slug":5,"name":6,"logoUrl":7,"githubOrg":5},[111,112,115,118],{"name":30,"slug":29,"type":71},{"name":113,"slug":114,"type":71},"Dashboards","dashboards",{"name":116,"slug":117,"type":71},"Data Visualization","data-visualization",{"name":6,"slug":5,"type":71},"2026-07-12T08:04:25.314591",{"slug":121,"name":121,"fn":122,"description":123,"org":124,"tags":125,"stars":48,"repoUrl":47,"updatedAt":139},"databricks-app-design","design UX for Databricks AppKit applications","Design the UX of custom-code Databricks Apps (AppKit\u002FReact) data screens — KPI\u002Foverview pages, reports, charts, tables, and Genie\u002Fchat data assistants — mapped to concrete AppKit components. Use when BUILDING or reviewing the UI of an AppKit\u002FReact app that displays data or answers data questions: choosing genre, layout, charts, KPIs, semantic color, required states (loading\u002Fempty\u002Ferror), IBCS notation, and AI-result trust (showing generated SQL\u002Fsources for Genie\u002Fchat). A plain \"create a dashboard\" request means a managed AI\u002FBI (Lakeview) dashboard → use databricks-aibi-dashboards, NOT this skill. Also NOT for non-data frontend (forms, settings, auth, marketing) or scaffolding\u002Fbuild\u002Fdeploy (→ databricks-apps). Complements databricks-apps; use it alongside whenever a custom app has a chart, table, KPI, report, or Genie\u002Fchat\u002FAI surface.",{"slug":5,"name":6,"logoUrl":7,"githubOrg":5},[126,127,130,133,136],{"name":6,"slug":5,"type":71},{"name":128,"slug":129,"type":71},"Design","design",{"name":131,"slug":132,"type":71},"Frontend","frontend",{"name":134,"slug":135,"type":71},"React","react",{"name":137,"slug":138,"type":71},"UI Components","ui-components","2026-07-12T08:04:02.02398",{"slug":141,"name":141,"fn":142,"description":143,"org":144,"tags":145,"stars":48,"repoUrl":47,"updatedAt":150},"databricks-apps","build applications on Databricks Apps","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\u002FBI (Lakeview) dashboard → use databricks-aibi-dashboards, not this skill. Evaluates data access patterns (analytics vs Lakebase synced tables) before scaffolding. Invoke BEFORE starting implementation.",{"slug":5,"name":6,"logoUrl":7,"githubOrg":5},[146,147,148,149],{"name":30,"slug":29,"type":71},{"name":113,"slug":114,"type":71},{"name":21,"slug":20,"type":71},{"name":6,"slug":5,"type":71},"2026-07-12T08:03:59.061458",{"slug":152,"name":152,"fn":153,"description":154,"org":155,"tags":156,"stars":48,"repoUrl":47,"updatedAt":171},"databricks-apps-python","build Python backends for Databricks Apps","Python backend for Databricks Apps — FastAPI (default), Flask, Dash, Streamlit, Gradio, Reflex. **Default for a new Databricks App is `databricks-apps` (AppKit — Node\u002FTypeScript\u002FReact) — 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 \u002F Vector Search \u002F model-serving APIs (via `databricks-python-sdk`), and deployment via CLI or DABs.",{"slug":5,"name":6,"logoUrl":7,"githubOrg":5},[157,158,161,164,167,168],{"name":6,"slug":5,"type":71},{"name":159,"slug":160,"type":71},"FastAPI","fastapi",{"name":162,"slug":163,"type":71},"Flask","flask",{"name":165,"slug":166,"type":71},"Gradio","gradio",{"name":27,"slug":26,"type":71},{"name":169,"slug":170,"type":71},"Streamlit","streamlit","2026-07-12T08:04:10.970845",{"slug":173,"name":173,"fn":174,"description":175,"org":176,"tags":177,"stars":48,"repoUrl":47,"updatedAt":183},"databricks-core","configure Databricks CLI and authentication","Databricks CLI operations and the parent\u002Fentry-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.",{"slug":5,"name":6,"logoUrl":7,"githubOrg":5},[178,181,182],{"name":179,"slug":180,"type":71},"Authentication","authentication",{"name":36,"slug":35,"type":71},{"name":6,"slug":5,"type":71},"2026-07-18T05:11:05.45506",{"slug":185,"name":185,"fn":186,"description":187,"org":188,"tags":189,"stars":48,"repoUrl":47,"updatedAt":198},"databricks-dabs","manage Databricks Declarative Automation Bundles","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.",{"slug":5,"name":6,"logoUrl":7,"githubOrg":5},[190,193,196,197],{"name":191,"slug":192,"type":71},"Automation","automation",{"name":194,"slug":195,"type":71},"Configuration","configuration",{"name":6,"slug":5,"type":71},{"name":39,"slug":38,"type":71},"2026-07-15T05:41:35.930355",{"slug":200,"name":200,"fn":201,"description":202,"org":203,"tags":204,"stars":48,"repoUrl":47,"updatedAt":211},"databricks-data-discovery","discover and query Databricks data","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\u002Fschema has Y'), answer a natural-language question about the data, or write a SQL query.",{"slug":5,"name":6,"logoUrl":7,"githubOrg":5},[205,206,207,208],{"name":21,"slug":20,"type":71},{"name":18,"slug":17,"type":71},{"name":6,"slug":5,"type":71},{"name":209,"slug":210,"type":71},"SQL","sql","2026-07-31T05:53:32.561877",{"slug":213,"name":213,"fn":214,"description":215,"org":216,"tags":217,"stars":48,"repoUrl":47,"updatedAt":224},"databricks-dbsql","query and script Databricks SQL warehouses","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.",{"slug":5,"name":6,"logoUrl":7,"githubOrg":5},[218,219,222,223],{"name":21,"slug":20,"type":71},{"name":220,"slug":221,"type":71},"Database","database",{"name":6,"slug":5,"type":71},{"name":209,"slug":210,"type":71},"2026-07-12T08:04:08.678282",{"slug":226,"name":226,"fn":227,"description":228,"org":229,"tags":230,"stars":48,"repoUrl":47,"updatedAt":238},"databricks-docs","search Databricks documentation","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.",{"slug":5,"name":6,"logoUrl":7,"githubOrg":5},[231,232,235],{"name":6,"slug":5,"type":71},{"name":233,"slug":234,"type":71},"Documentation","documentation",{"name":236,"slug":237,"type":71},"Reference","reference","2026-07-15T05:41:34.697746",{"slug":240,"name":240,"fn":241,"description":242,"org":243,"tags":244,"stars":48,"repoUrl":47,"updatedAt":247},"databricks-execution-compute","execute code and manage Databricks compute","Execute code and manage compute on Databricks: run Python\u002FScala\u002FSQL\u002FR via serverless, classic, or interactive clusters, and create\u002Fresize\u002Fdelete clusters and SQL warehouses.",{"slug":5,"name":6,"logoUrl":7,"githubOrg":5},[245,246],{"name":18,"slug":17,"type":71},{"name":6,"slug":5,"type":71},"2026-07-12T08:04:22.587562",{"slug":249,"name":249,"fn":250,"description":251,"org":252,"tags":253,"stars":48,"repoUrl":47,"updatedAt":262},"databricks-iceberg","manage Apache Iceberg tables on Databricks","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",{"slug":5,"name":6,"logoUrl":7,"githubOrg":5},[254,255,258,259],{"name":18,"slug":17,"type":71},{"name":256,"slug":257,"type":71},"Data Warehouse","data-warehouse",{"name":6,"slug":5,"type":71},{"name":260,"slug":261,"type":71},"Spark","spark","2026-07-12T08:04:29.563212",{"slug":264,"name":264,"fn":265,"description":266,"org":267,"tags":268,"stars":48,"repoUrl":47,"updatedAt":273},"databricks-jobs","develop and deploy Databricks Lakeflow jobs","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.",{"slug":5,"name":6,"logoUrl":7,"githubOrg":5},[269,270,271,272],{"name":18,"slug":17,"type":71},{"name":24,"slug":23,"type":71},{"name":6,"slug":5,"type":71},{"name":39,"slug":38,"type":71},"2026-07-15T05:41:33.465258",{"slug":275,"name":275,"fn":276,"description":277,"org":278,"tags":279,"stars":48,"repoUrl":47,"updatedAt":286},"databricks-lakebase","manage Databricks Lakebase Postgres databases","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.",{"slug":5,"name":6,"logoUrl":7,"githubOrg":5},[280,281,282,283],{"name":33,"slug":32,"type":71},{"name":220,"slug":221,"type":71},{"name":6,"slug":5,"type":71},{"name":284,"slug":285,"type":71},"PostgreSQL","postgresql","2026-07-12T08:04:52.513565",{"slug":288,"name":288,"fn":289,"description":290,"org":291,"tags":292,"stars":48,"repoUrl":47,"updatedAt":299},"databricks-lakeflow-connect","build managed ingestion pipelines into 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\u002FMySQL CDC in PuPr) into Unity Catalog with serverless pipelines.",{"slug":5,"name":6,"logoUrl":7,"githubOrg":5},[293,294,295,296],{"name":18,"slug":17,"type":71},{"name":24,"slug":23,"type":71},{"name":6,"slug":5,"type":71},{"name":297,"slug":298,"type":71},"ETL","etl","2026-07-12T08:04:21.243004",{"slug":301,"name":301,"fn":302,"description":303,"org":304,"tags":305,"stars":48,"repoUrl":47,"updatedAt":312},"databricks-metric-views","manage Databricks Unity Catalog metric views","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.",{"slug":5,"name":6,"logoUrl":7,"githubOrg":5},[306,307,308,309],{"name":30,"slug":29,"type":71},{"name":18,"slug":17,"type":71},{"name":6,"slug":5,"type":71},{"name":310,"slug":311,"type":71},"KPI","kpi","2026-07-12T08:04:12.237759",{"slug":314,"name":314,"fn":315,"description":316,"org":317,"tags":318,"stars":48,"repoUrl":47,"updatedAt":327},"databricks-ml-training","train machine learning models on Databricks","Train ML models on Databricks. Use for: classification\u002Fregression\u002Fdeep-learning (XGBoost, scikit-learn, LightGBM, PyTorch) with Optuna, @prod\u002F@challenger aliases, batch scoring (spark_udf for plain models, fe.score_batch for feature-store-backed), custom PyFunc, custom ResponsesAgent (LangGraph + UC Function\u002FVector Search); UC feature tables + FeatureLookup + point-in-time joins + Lakebase online store; declarative Feature Views (create_feature, DeltaTableSource, RollingWindow\u002FSlidingWindow\u002FTumblingWindow, materialize_features, streaming Kafka features). NOT for: endpoint ops (databricks-model-serving), MLflow evaluation (databricks-mlflow-evaluation).",{"slug":5,"name":6,"logoUrl":7,"githubOrg":5},[319,320,321,324],{"name":18,"slug":17,"type":71},{"name":6,"slug":5,"type":71},{"name":322,"slug":323,"type":71},"Deep Learning","deep-learning",{"name":325,"slug":326,"type":71},"Machine Learning","machine-learning","2026-07-12T08:04:42.666956",{"slug":329,"name":329,"fn":330,"description":331,"org":332,"tags":333,"stars":48,"repoUrl":47,"updatedAt":343},"databricks-mlflow-evaluation","evaluate GenAI agents with MLflow","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.",{"slug":5,"name":6,"logoUrl":7,"githubOrg":5},[334,335,336,339,340],{"name":69,"slug":70,"type":71},{"name":6,"slug":5,"type":71},{"name":337,"slug":338,"type":71},"Evals","evals",{"name":89,"slug":90,"type":71},{"name":341,"slug":342,"type":71},"MLflow","mlflow","2026-07-12T08:04:07.451169",{"slug":345,"name":345,"fn":346,"description":347,"org":348,"tags":349,"stars":48,"repoUrl":47,"updatedAt":356},"databricks-model-serving","manage Databricks model serving endpoints","Databricks Model Serving endpoint lifecycle and ops. Use when asked to: CRUD serving endpoints (CLI or MLflow Deployments client); configure traffic routing for A\u002FB \u002F 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\u002FResponsesAgent authoring (databricks-ml-training); Knowledge Assistants\u002FSupervisor Agents (databricks-agent-bricks); MLflow evaluation (databricks-mlflow-evaluation).",{"slug":5,"name":6,"logoUrl":7,"githubOrg":5},[350,351,352,353],{"name":6,"slug":5,"type":71},{"name":39,"slug":38,"type":71},{"name":325,"slug":326,"type":71},{"name":354,"slug":355,"type":71},"MLOps","mlops","2026-07-12T08:04:35.810649",{"slug":358,"name":358,"fn":359,"description":360,"org":361,"tags":362,"stars":48,"repoUrl":47,"updatedAt":43},"databricks-pipelines","develop Databricks Lakeflow Spark pipelines","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.",{"slug":5,"name":6,"logoUrl":7,"githubOrg":5},[363,364,365,366,367],{"name":18,"slug":17,"type":71},{"name":24,"slug":23,"type":71},{"name":6,"slug":5,"type":71},{"name":27,"slug":26,"type":71},{"name":209,"slug":210,"type":71},{"slug":369,"name":369,"fn":370,"description":371,"org":372,"tags":373,"stars":48,"repoUrl":47,"updatedAt":378},"databricks-python-sdk","develop with Databricks Python SDK","Databricks development guidance including Python SDK, Databricks Connect, CLI, and REST API. Use when working with databricks-sdk, databricks-connect, or Databricks APIs.",{"slug":5,"name":6,"logoUrl":7,"githubOrg":5},[374,375,376,377],{"name":33,"slug":32,"type":71},{"name":36,"slug":35,"type":71},{"name":6,"slug":5,"type":71},{"name":27,"slug":26,"type":71},"2026-07-12T08:04:04.552795",{"slug":380,"name":380,"fn":381,"description":382,"org":383,"tags":384,"stars":48,"repoUrl":47,"updatedAt":393},"databricks-serverless-migration","migrate Databricks workloads to serverless compute","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.",{"slug":5,"name":6,"logoUrl":7,"githubOrg":5},[385,388,389,390],{"name":386,"slug":387,"type":71},"Cloud","cloud",{"name":6,"slug":5,"type":71},{"name":42,"slug":41,"type":71},{"name":391,"slug":392,"type":71},"Migration","migration","2026-07-15T05:41:37.214848"]