[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-databricks-databricks-ai-runtime":3,"mdc--j6c9xe-key":33,"related-repo-databricks-databricks-ai-runtime":342,"related-org-databricks-databricks-ai-runtime":454},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":23,"repoUrl":24,"updatedAt":25,"license":26,"forks":27,"topics":28,"repo":29,"sourceUrl":31,"mdContent":32},"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":8,"name":9,"logoUrl":10,"githubOrg":8},"databricks","Databricks","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fdatabricks.png",[12,16,17,20],{"name":13,"slug":14,"type":15},"CLI","cli","tag",{"name":9,"slug":8,"type":15},{"name":18,"slug":19,"type":15},"Engineering","engineering",{"name":21,"slug":22,"type":15},"Docker","docker",204,"https:\u002F\u002Fgithub.com\u002Fdatabricks\u002Fdatabricks-agent-skills","2026-07-12T08:04:55.843982",null,60,[],{"repoUrl":24,"stars":23,"forks":27,"topics":30,"description":26},[],"https:\u002F\u002Fgithub.com\u002Fdatabricks\u002Fdatabricks-agent-skills\u002Ftree\u002FHEAD\u002Fexperimental\u002Fdatabricks-ai-runtime","---\nname: databricks-ai-runtime\ndescription: \"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.\"\ncompatibility: Requires databricks-air CLI. See the [installation guide](https:\u002F\u002Fdocs.databricks.com\u002Faws\u002Fen\u002Fmachine-learning\u002Fai-runtime\u002Fcli\u002Finstallation) to get started.\nmetadata:\n  version: \"0.1.0\"\n---\n\n# Databricks AI Runtime (`air`) CLI\n\nDatabricks AI Runtime (`air`) is a CLI tool for submitting GPU training workloads to Databricks serverless compute. It manages environment setup, distributed training configuration, and workload lifecycle — without requiring you to manage clusters or infrastructure.\n\nA typical workload YAML looks like:\n\n```yaml\nexperiment_name: my-training-job\ncompute:\n  num_accelerators: 1\n  accelerator_type: GPU_1xA10\nenvironment:\n  dependencies:\n    - mlflow\n  version: \"AI5\"\ncommand: echo \"Hello World\"\n```\n\nSubmit with `air run --file workload.yaml -p \u003Cdatabricks_config_profile>`.\n\n## Bring your own custom Docker images\n\nUse a custom Docker image instead of `environment.version` when your workload needs specific system libraries, CUDA extensions (flash-attn, apex, custom kernels), or dependencies that don't fit `environment.dependencies`.\n\n**Read [docker-images.md](docker-images.md)** for step-by-step guidance on:\n\n- Using Databricks-provided base images\n- Dockerfile patterns\n- Pre-build compatibility checklist (CUDA\u002Fdriver, PyTorch, NCCL, EFA\u002FRDMA)\n- Registering images with `air register image`\n",{"data":34,"body":38},{"name":4,"description":6,"compatibility":35,"metadata":36},"Requires databricks-air CLI. See the [installation guide](https:\u002F\u002Fdocs.databricks.com\u002Faws\u002Fen\u002Fmachine-learning\u002Fai-runtime\u002Fcli\u002Finstallation) to get started.",{"version":37},"0.1.0",{"type":39,"children":40},"root",[41,59,71,76,248,261,268,288,305,336],{"type":42,"tag":43,"props":44,"children":46},"element","h1",{"id":45},"databricks-ai-runtime-air-cli",[47,50,57],{"type":48,"value":49},"text","Databricks AI Runtime (",{"type":42,"tag":51,"props":52,"children":54},"code",{"className":53},[],[55],{"type":48,"value":56},"air",{"type":48,"value":58},") CLI",{"type":42,"tag":60,"props":61,"children":62},"p",{},[63,64,69],{"type":48,"value":49},{"type":42,"tag":51,"props":65,"children":67},{"className":66},[],[68],{"type":48,"value":56},{"type":48,"value":70},") is a CLI tool for submitting GPU training workloads to Databricks serverless compute. It manages environment setup, distributed training configuration, and workload lifecycle — without requiring you to manage clusters or infrastructure.",{"type":42,"tag":60,"props":72,"children":73},{},[74],{"type":48,"value":75},"A typical workload YAML looks like:",{"type":42,"tag":77,"props":78,"children":83},"pre",{"className":79,"code":80,"language":81,"meta":82,"style":82},"language-yaml shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","experiment_name: my-training-job\ncompute:\n  num_accelerators: 1\n  accelerator_type: GPU_1xA10\nenvironment:\n  dependencies:\n    - mlflow\n  version: \"AI5\"\ncommand: echo \"Hello World\"\n","yaml","",[84],{"type":42,"tag":51,"props":85,"children":86},{"__ignoreMap":82},[87,111,125,144,162,175,188,202,230],{"type":42,"tag":88,"props":89,"children":92},"span",{"class":90,"line":91},"line",1,[93,99,105],{"type":42,"tag":88,"props":94,"children":96},{"style":95},"--shiki-light:#E53935;--shiki-default:#F07178;--shiki-dark:#F07178",[97],{"type":48,"value":98},"experiment_name",{"type":42,"tag":88,"props":100,"children":102},{"style":101},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[103],{"type":48,"value":104},":",{"type":42,"tag":88,"props":106,"children":108},{"style":107},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[109],{"type":48,"value":110}," my-training-job\n",{"type":42,"tag":88,"props":112,"children":114},{"class":90,"line":113},2,[115,120],{"type":42,"tag":88,"props":116,"children":117},{"style":95},[118],{"type":48,"value":119},"compute",{"type":42,"tag":88,"props":121,"children":122},{"style":101},[123],{"type":48,"value":124},":\n",{"type":42,"tag":88,"props":126,"children":128},{"class":90,"line":127},3,[129,134,138],{"type":42,"tag":88,"props":130,"children":131},{"style":95},[132],{"type":48,"value":133},"  num_accelerators",{"type":42,"tag":88,"props":135,"children":136},{"style":101},[137],{"type":48,"value":104},{"type":42,"tag":88,"props":139,"children":141},{"style":140},"--shiki-light:#F76D47;--shiki-default:#F78C6C;--shiki-dark:#F78C6C",[142],{"type":48,"value":143}," 1\n",{"type":42,"tag":88,"props":145,"children":147},{"class":90,"line":146},4,[148,153,157],{"type":42,"tag":88,"props":149,"children":150},{"style":95},[151],{"type":48,"value":152},"  accelerator_type",{"type":42,"tag":88,"props":154,"children":155},{"style":101},[156],{"type":48,"value":104},{"type":42,"tag":88,"props":158,"children":159},{"style":107},[160],{"type":48,"value":161}," GPU_1xA10\n",{"type":42,"tag":88,"props":163,"children":165},{"class":90,"line":164},5,[166,171],{"type":42,"tag":88,"props":167,"children":168},{"style":95},[169],{"type":48,"value":170},"environment",{"type":42,"tag":88,"props":172,"children":173},{"style":101},[174],{"type":48,"value":124},{"type":42,"tag":88,"props":176,"children":178},{"class":90,"line":177},6,[179,184],{"type":42,"tag":88,"props":180,"children":181},{"style":95},[182],{"type":48,"value":183},"  dependencies",{"type":42,"tag":88,"props":185,"children":186},{"style":101},[187],{"type":48,"value":124},{"type":42,"tag":88,"props":189,"children":191},{"class":90,"line":190},7,[192,197],{"type":42,"tag":88,"props":193,"children":194},{"style":101},[195],{"type":48,"value":196},"    -",{"type":42,"tag":88,"props":198,"children":199},{"style":107},[200],{"type":48,"value":201}," mlflow\n",{"type":42,"tag":88,"props":203,"children":205},{"class":90,"line":204},8,[206,211,215,220,225],{"type":42,"tag":88,"props":207,"children":208},{"style":95},[209],{"type":48,"value":210},"  version",{"type":42,"tag":88,"props":212,"children":213},{"style":101},[214],{"type":48,"value":104},{"type":42,"tag":88,"props":216,"children":217},{"style":101},[218],{"type":48,"value":219}," \"",{"type":42,"tag":88,"props":221,"children":222},{"style":107},[223],{"type":48,"value":224},"AI5",{"type":42,"tag":88,"props":226,"children":227},{"style":101},[228],{"type":48,"value":229},"\"\n",{"type":42,"tag":88,"props":231,"children":233},{"class":90,"line":232},9,[234,239,243],{"type":42,"tag":88,"props":235,"children":236},{"style":95},[237],{"type":48,"value":238},"command",{"type":42,"tag":88,"props":240,"children":241},{"style":101},[242],{"type":48,"value":104},{"type":42,"tag":88,"props":244,"children":245},{"style":107},[246],{"type":48,"value":247}," echo \"Hello World\"\n",{"type":42,"tag":60,"props":249,"children":250},{},[251,253,259],{"type":48,"value":252},"Submit with ",{"type":42,"tag":51,"props":254,"children":256},{"className":255},[],[257],{"type":48,"value":258},"air run --file workload.yaml -p \u003Cdatabricks_config_profile>",{"type":48,"value":260},".",{"type":42,"tag":262,"props":263,"children":265},"h2",{"id":264},"bring-your-own-custom-docker-images",[266],{"type":48,"value":267},"Bring your own custom Docker images",{"type":42,"tag":60,"props":269,"children":270},{},[271,273,279,281,287],{"type":48,"value":272},"Use a custom Docker image instead of ",{"type":42,"tag":51,"props":274,"children":276},{"className":275},[],[277],{"type":48,"value":278},"environment.version",{"type":48,"value":280}," when your workload needs specific system libraries, CUDA extensions (flash-attn, apex, custom kernels), or dependencies that don't fit ",{"type":42,"tag":51,"props":282,"children":284},{"className":283},[],[285],{"type":48,"value":286},"environment.dependencies",{"type":48,"value":260},{"type":42,"tag":60,"props":289,"children":290},{},[291,303],{"type":42,"tag":292,"props":293,"children":294},"strong",{},[295,297],{"type":48,"value":296},"Read ",{"type":42,"tag":298,"props":299,"children":301},"a",{"href":300},"docker-images.md",[302],{"type":48,"value":300},{"type":48,"value":304}," for step-by-step guidance on:",{"type":42,"tag":306,"props":307,"children":308},"ul",{},[309,315,320,325],{"type":42,"tag":310,"props":311,"children":312},"li",{},[313],{"type":48,"value":314},"Using Databricks-provided base images",{"type":42,"tag":310,"props":316,"children":317},{},[318],{"type":48,"value":319},"Dockerfile patterns",{"type":42,"tag":310,"props":321,"children":322},{},[323],{"type":48,"value":324},"Pre-build compatibility checklist (CUDA\u002Fdriver, PyTorch, NCCL, EFA\u002FRDMA)",{"type":42,"tag":310,"props":326,"children":327},{},[328,330],{"type":48,"value":329},"Registering images with ",{"type":42,"tag":51,"props":331,"children":333},{"className":332},[],[334],{"type":48,"value":335},"air register image",{"type":42,"tag":337,"props":338,"children":339},"style",{},[340],{"type":48,"value":341},"html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"items":343,"total":453},[344,361,375,382,399,419,430],{"slug":345,"name":345,"fn":346,"description":347,"org":348,"tags":349,"stars":23,"repoUrl":24,"updatedAt":360},"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":8,"name":9,"logoUrl":10,"githubOrg":8},[350,353,354,357],{"name":351,"slug":352,"type":15},"Agents","agents",{"name":9,"slug":8,"type":15},{"name":355,"slug":356,"type":15},"Knowledge Management","knowledge-management",{"name":358,"slug":359,"type":15},"Multi-Agent","multi-agent","2026-07-15T05:41:38.548954",{"slug":362,"name":362,"fn":363,"description":364,"org":365,"tags":366,"stars":23,"repoUrl":24,"updatedAt":374},"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":8,"name":9,"logoUrl":10,"githubOrg":8},[367,370,371],{"name":368,"slug":369,"type":15},"Data Analysis","data-analysis",{"name":9,"slug":8,"type":15},{"name":372,"slug":373,"type":15},"LLM","llm","2026-07-31T05:53:33.562077",{"slug":4,"name":4,"fn":5,"description":6,"org":376,"tags":377,"stars":23,"repoUrl":24,"updatedAt":25},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[378,379,380,381],{"name":13,"slug":14,"type":15},{"name":9,"slug":8,"type":15},{"name":21,"slug":22,"type":15},{"name":18,"slug":19,"type":15},{"slug":383,"name":383,"fn":384,"description":385,"org":386,"tags":387,"stars":23,"repoUrl":24,"updatedAt":398},"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":8,"name":9,"logoUrl":10,"githubOrg":8},[388,391,394,397],{"name":389,"slug":390,"type":15},"Analytics","analytics",{"name":392,"slug":393,"type":15},"Dashboards","dashboards",{"name":395,"slug":396,"type":15},"Data Visualization","data-visualization",{"name":9,"slug":8,"type":15},"2026-07-12T08:04:25.314591",{"slug":400,"name":400,"fn":401,"description":402,"org":403,"tags":404,"stars":23,"repoUrl":24,"updatedAt":418},"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":8,"name":9,"logoUrl":10,"githubOrg":8},[405,406,409,412,415],{"name":9,"slug":8,"type":15},{"name":407,"slug":408,"type":15},"Design","design",{"name":410,"slug":411,"type":15},"Frontend","frontend",{"name":413,"slug":414,"type":15},"React","react",{"name":416,"slug":417,"type":15},"UI Components","ui-components","2026-07-12T08:04:02.02398",{"slug":420,"name":420,"fn":421,"description":422,"org":423,"tags":424,"stars":23,"repoUrl":24,"updatedAt":429},"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":8,"name":9,"logoUrl":10,"githubOrg":8},[425,426,427,428],{"name":389,"slug":390,"type":15},{"name":392,"slug":393,"type":15},{"name":368,"slug":369,"type":15},{"name":9,"slug":8,"type":15},"2026-07-12T08:03:59.061458",{"slug":431,"name":431,"fn":432,"description":433,"org":434,"tags":435,"stars":23,"repoUrl":24,"updatedAt":452},"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":8,"name":9,"logoUrl":10,"githubOrg":8},[436,437,440,443,446,449],{"name":9,"slug":8,"type":15},{"name":438,"slug":439,"type":15},"FastAPI","fastapi",{"name":441,"slug":442,"type":15},"Flask","flask",{"name":444,"slug":445,"type":15},"Gradio","gradio",{"name":447,"slug":448,"type":15},"Python","python",{"name":450,"slug":451,"type":15},"Streamlit","streamlit","2026-07-12T08:04:10.970845",31,{"items":455,"total":453},[456,463,469,476,483,491,498,507,519,536,551,564],{"slug":345,"name":345,"fn":346,"description":347,"org":457,"tags":458,"stars":23,"repoUrl":24,"updatedAt":360},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[459,460,461,462],{"name":351,"slug":352,"type":15},{"name":9,"slug":8,"type":15},{"name":355,"slug":356,"type":15},{"name":358,"slug":359,"type":15},{"slug":362,"name":362,"fn":363,"description":364,"org":464,"tags":465,"stars":23,"repoUrl":24,"updatedAt":374},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[466,467,468],{"name":368,"slug":369,"type":15},{"name":9,"slug":8,"type":15},{"name":372,"slug":373,"type":15},{"slug":4,"name":4,"fn":5,"description":6,"org":470,"tags":471,"stars":23,"repoUrl":24,"updatedAt":25},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[472,473,474,475],{"name":13,"slug":14,"type":15},{"name":9,"slug":8,"type":15},{"name":21,"slug":22,"type":15},{"name":18,"slug":19,"type":15},{"slug":383,"name":383,"fn":384,"description":385,"org":477,"tags":478,"stars":23,"repoUrl":24,"updatedAt":398},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[479,480,481,482],{"name":389,"slug":390,"type":15},{"name":392,"slug":393,"type":15},{"name":395,"slug":396,"type":15},{"name":9,"slug":8,"type":15},{"slug":400,"name":400,"fn":401,"description":402,"org":484,"tags":485,"stars":23,"repoUrl":24,"updatedAt":418},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[486,487,488,489,490],{"name":9,"slug":8,"type":15},{"name":407,"slug":408,"type":15},{"name":410,"slug":411,"type":15},{"name":413,"slug":414,"type":15},{"name":416,"slug":417,"type":15},{"slug":420,"name":420,"fn":421,"description":422,"org":492,"tags":493,"stars":23,"repoUrl":24,"updatedAt":429},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[494,495,496,497],{"name":389,"slug":390,"type":15},{"name":392,"slug":393,"type":15},{"name":368,"slug":369,"type":15},{"name":9,"slug":8,"type":15},{"slug":431,"name":431,"fn":432,"description":433,"org":499,"tags":500,"stars":23,"repoUrl":24,"updatedAt":452},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[501,502,503,504,505,506],{"name":9,"slug":8,"type":15},{"name":438,"slug":439,"type":15},{"name":441,"slug":442,"type":15},{"name":444,"slug":445,"type":15},{"name":447,"slug":448,"type":15},{"name":450,"slug":451,"type":15},{"slug":508,"name":508,"fn":509,"description":510,"org":511,"tags":512,"stars":23,"repoUrl":24,"updatedAt":518},"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":8,"name":9,"logoUrl":10,"githubOrg":8},[513,516,517],{"name":514,"slug":515,"type":15},"Authentication","authentication",{"name":13,"slug":14,"type":15},{"name":9,"slug":8,"type":15},"2026-07-18T05:11:05.45506",{"slug":520,"name":520,"fn":521,"description":522,"org":523,"tags":524,"stars":23,"repoUrl":24,"updatedAt":535},"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":8,"name":9,"logoUrl":10,"githubOrg":8},[525,528,531,532],{"name":526,"slug":527,"type":15},"Automation","automation",{"name":529,"slug":530,"type":15},"Configuration","configuration",{"name":9,"slug":8,"type":15},{"name":533,"slug":534,"type":15},"Deployment","deployment","2026-07-15T05:41:35.930355",{"slug":537,"name":537,"fn":538,"description":539,"org":540,"tags":541,"stars":23,"repoUrl":24,"updatedAt":550},"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":8,"name":9,"logoUrl":10,"githubOrg":8},[542,543,546,547],{"name":368,"slug":369,"type":15},{"name":544,"slug":545,"type":15},"Data Engineering","data-engineering",{"name":9,"slug":8,"type":15},{"name":548,"slug":549,"type":15},"SQL","sql","2026-07-31T05:53:32.561877",{"slug":552,"name":552,"fn":553,"description":554,"org":555,"tags":556,"stars":23,"repoUrl":24,"updatedAt":563},"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":8,"name":9,"logoUrl":10,"githubOrg":8},[557,558,561,562],{"name":368,"slug":369,"type":15},{"name":559,"slug":560,"type":15},"Database","database",{"name":9,"slug":8,"type":15},{"name":548,"slug":549,"type":15},"2026-07-12T08:04:08.678282",{"slug":565,"name":565,"fn":566,"description":567,"org":568,"tags":569,"stars":23,"repoUrl":24,"updatedAt":577},"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":8,"name":9,"logoUrl":10,"githubOrg":8},[570,571,574],{"name":9,"slug":8,"type":15},{"name":572,"slug":573,"type":15},"Documentation","documentation",{"name":575,"slug":576,"type":15},"Reference","reference","2026-07-15T05:41:34.697746"]