[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-databricks-databricks-data-discovery":3,"mdc-ku11ez-key":33,"related-org-databricks-databricks-data-discovery":1046,"related-repo-databricks-databricks-data-discovery":1228},{"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-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},"databricks","Databricks","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fdatabricks.png",[12,16,19,20],{"name":13,"slug":14,"type":15},"Data Engineering","data-engineering","tag",{"name":17,"slug":18,"type":15},"Data Analysis","data-analysis",{"name":9,"slug":8,"type":15},{"name":21,"slug":22,"type":15},"SQL","sql",204,"https:\u002F\u002Fgithub.com\u002Fdatabricks\u002Fdatabricks-agent-skills","2026-07-31T05:53:32.561877",null,60,[],{"repoUrl":24,"stars":23,"forks":27,"topics":30,"description":26},[],"https:\u002F\u002Fgithub.com\u002Fdatabricks\u002Fdatabricks-agent-skills\u002Ftree\u002FHEAD\u002Fplugins\u002Fdatabricks\u002Fcopilot\u002Fskills\u002Fdatabricks-data-discovery","---\nname: databricks-data-discovery\ndescription: \"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.\"\ncompatibility: Requires databricks CLI >= v1.9.0 for `databricks genie ask` (older CLIs fall back to the deprecated `databricks experimental genie ask` alias)\nmetadata:\n  version: \"0.1.0\"\nparent: databricks-core\n---\n\n# Databricks Data Discovery\n\nThis skill **routes data work** — decide first:\n- the request is about *the data* — finding it, asking questions of it, or\n  generating SQL → delegate to **Genie One**:\n  `databricks genie ask -s \u003Csession-label> \"...\"` (see Routing below).\n- writing files or anything else → use your own coding-agent tools.\n\nGenie One just needs an authenticated CLI profile (the parent `databricks-core`\nskill covers auth\u002Fprofiles if you need it) — but route the data request to Genie\nfirst; don't detour into manual catalog browsing.\n\n## Routing — Genie vs your coding agent\n\n**Route to Genie when the request is about the data:**\n- **Finding or locating data** — \"what tables are in wanderbricks?\", \"where does X\n  live?\", which catalog\u002Fschema holds something. Let Genie resolve a fuzzy or partial\n  name across all your data instead of guessing or grepping catalogs yourself.\n- **Questions about the data** — \"how many…\", \"what's the average…\", \"which … the\n  most…\", trends, breakdowns.\n- **Generating SQL from a question** — a first-cut query you can run, adapt, or drop\n  into a file.\n- **Understanding or profiling data** to inform a query, dashboard, or app.\n\n**Route to your own coding agent (do NOT use Genie) for everything else:**\n- **Writing or editing files** — a `.sql` file, notebook, dashboard, app, config.\n  Genie finds the data and produces the SQL; *you* write the file.\n- **Authoring jobs, pipelines, apps, or DABs** — use those product skills.\n- **DDL or writes** — `CREATE` \u002F `INSERT` \u002F `UPDATE` \u002F `DELETE`.\n- **General programming, git, infra, and any non-data task.**\n\n**Key principle:** data discovery, data questions, and query generation → Genie One.\nEverything else → your coding agent.\n\n## Why prefer Genie for data questions\n\nGenie runs *inside the Databricks data plane* with governed, first-hand access to\nthe org's Unity Catalog metadata, metric views, and curated semantic context —\ncontext you do **not** have when reverse-engineering schemas with ad-hoc SQL. For\ndata questions it is often higher-quality and more performant than doing the\ndiscovery yourself, and it keeps improving as a managed Databricks capability.\nDon't default to writing your own discovery SQL just because you can.\n\n## How to ask Genie\n\nAlways pass a session label with `-s`, and prefer reusing the **same** one: a\nfollow-up can only continue a conversation if the first ask set the session label,\nand reusing it lets later questions build on everything asked so far (\"summarize all\nof the above\"). Use a fresh session label only to start a deliberately separate\nsession, or distinct session labels to run several in parallel.\n\nThe command is `databricks genie ask` (CLI >= v1.9.0). On an older CLI it lives\nunder `databricks experimental genie ask` — same flags and behavior; use that\nexact fallback if `databricks genie ask` is not found.\n\n```bash\n# Always pass a session label, and reuse the SAME one so follow-ups build on each other\ndatabricks genie ask -s trips \"How many bookings were there last week?\"\ndatabricks genie ask -s trips \"Break that down by destination\"\ndatabricks genie ask -s trips \"Summarize all of the above\"\n\n# --include-sql also prints the SQL Genie ran (use it to generate a query, too)\ndatabricks genie ask -s trips \"Write SQL for the top 5 destinations by revenue\" --include-sql\n\n# --output json gives a parseable result\ndatabricks genie ask -s trips \"Top 5 destinations by revenue\" --output json\n# → {\"status\":\"completed\",\"conversation_id\":\"…\",\"text\":\"…\",\"tool_calls\":[{\"name\":\"execute_sql\",\"sql\":\"…\",\"title\":\"…\"}]}\n\n# Older CLI (\u003C v1.9.0) — same command under the deprecated experimental alias:\n#   databricks experimental genie ask -s trips \"How many bookings were there last week?\"\n```\n\nGenie searches across all the data you can see, runs SQL, and streams a grounded\nanswer — rendered with the executed SQL and, where it helps, a terminal chart. It\nauto-resolves a SQL warehouse (override with `--warehouse-id`); nothing to pick or\nset up.\n\n- **Streams live**: the answer, the agent's steps, and any SQL\u002Fresults appear as\n  they arrive. Answers usually take ~5–30s; a stalled stream (no data for ~10 min)\n  fails with a clear message, and Ctrl-C or `kill` (SIGTERM) cancels cleanly.\n- **Picking a session label**: any string works — a topic like `trips`, or `$$` for a\n  per-shell session. Default to reusing one session label so follow-ups keep full\n  context; use a fresh one only for a deliberately separate session. An expired\n  session label just starts fresh on the next ask. No id to copy around.\n- **Parallelism**: to run sessions at the same time, give each its own session label\n  (`-s q1`, `-s q2`, …) — independent session labels don't interfere. Within a single\n  session label keep calls sequential: send a follow-up after the previous turn\n  returns, and never fire two asks at once on the *same* session label (they'd split\n  into two conversations and only one mapping would survive).\n- **Structured output**: `--output json` gives `{status, conversation_id, text,\n  tool_calls[]}`, where `tool_calls` includes the SQL Genie executed; `--raw` dumps\n  the raw event stream. Note `--output json` buffers and prints once at the end (no\n  live streaming) — use it for parsing, the default text output for interactive use.\n- **Generating a query**: ask Genie to \"write SQL for …\" and read the SQL from the\n  response (it's in the answer text, and `--include-sql` also shows the query Genie\n  ran to verify it — so the SQL is known-good). Genie resolves the schema and joins\n  for you, so this beats hand-writing SQL against unfamiliar tables.\n- **For exact\u002Ffull rows**: Genie shows a preview inline; to pull the complete result\n  set locally, copy its SQL (`--include-sql` or the JSON `tool_calls`) into the\n  parent's `... aitools tools query \"\u003CSQL>\"`.\n- **A non-answer is a message, not an error**: if Genie refuses or \"couldn't find\n  relevant data,\" don't retry — use the manual fallback below.\n\n> **Naming:** \"Genie One\" is the current name for this cross-data chat — formerly\n> \"Databricks One\", then \"OneChat\" (the backend tool is still literally named\n> `onechat`). All the same thing.\n\n## If Genie One isn't available — manual fallback\n\nOnly fall back if Genie One is genuinely unavailable — first **verify** with\n`databricks genie ask --help` (or `databricks experimental genie ask --help` on a\nCLI older than v1.9.0); don't assume the command is missing. When Genie One isn't\nenabled, the CLI is too old to have either form of `genie ask`,\nor Genie can't cover the question, do the discovery yourself with the parent skill's\ncommands — see **[Manual Data Exploration](..\u002Fdatabricks-core\u002Fmanual-data-exploration.md)**\n(keyword search via `information_schema`, `discover-schema`, and `tools query`).\nRunning known SQL or profiling a known table that way is perfectly fine on its own.\nDo **not** default to `databricks tables list` or raw UC REST for data-location\nquestions — invoke this skill and ask Genie first.\n\n## Relationship to the Genie One MCP\n\nDatabricks also offers this capability as a managed **MCP** server — the *Genie One\nMCP*. This skill delivers the **same functionality** through the Databricks CLI, with\nno MCP server to configure or host. More broadly, the Databricks Agent Skills cover\nthe same ground as Databricks' managed MCP servers, so you don't need any MCP wired up\nto use this. If you already run the Genie One MCP, use whichever you prefer — they hit\nthe same Genie backend.\n\n## Related Skills\n\n- **databricks-genie-agents** — build and manage **Genie Agents**: curated\n  agents that let you or a group ask questions of specific data (create, configure,\n  import\u002Fexport).\n- **databricks-core** (parent) — CLI auth, profiles, and the manual data exploration\n  reference used as the fallback.\n",{"data":34,"body":39},{"name":4,"description":6,"compatibility":35,"metadata":36,"parent":38},"Requires databricks CLI >= v1.9.0 for `databricks genie ask` (older CLIs fall back to the deprecated `databricks experimental genie ask` alias)",{"version":37},"0.1.0","databricks-core",{"type":40,"children":41},"root",[42,50,64,103,115,122,130,173,181,267,277,283,302,308,328,356,660,673,860,882,888,973,979,1005,1011,1040],{"type":43,"tag":44,"props":45,"children":46},"element","h1",{"id":4},[47],{"type":48,"value":49},"text","Databricks Data Discovery",{"type":43,"tag":51,"props":52,"children":53},"p",{},[54,56,62],{"type":48,"value":55},"This skill ",{"type":43,"tag":57,"props":58,"children":59},"strong",{},[60],{"type":48,"value":61},"routes data work",{"type":48,"value":63}," — decide first:",{"type":43,"tag":65,"props":66,"children":67},"ul",{},[68,98],{"type":43,"tag":69,"props":70,"children":71},"li",{},[72,74,80,82,87,89,96],{"type":48,"value":73},"the request is about ",{"type":43,"tag":75,"props":76,"children":77},"em",{},[78],{"type":48,"value":79},"the data",{"type":48,"value":81}," — finding it, asking questions of it, or\ngenerating SQL → delegate to ",{"type":43,"tag":57,"props":83,"children":84},{},[85],{"type":48,"value":86},"Genie One",{"type":48,"value":88},":\n",{"type":43,"tag":90,"props":91,"children":93},"code",{"className":92},[],[94],{"type":48,"value":95},"databricks genie ask -s \u003Csession-label> \"...\"",{"type":48,"value":97}," (see Routing below).",{"type":43,"tag":69,"props":99,"children":100},{},[101],{"type":48,"value":102},"writing files or anything else → use your own coding-agent tools.",{"type":43,"tag":51,"props":104,"children":105},{},[106,108,113],{"type":48,"value":107},"Genie One just needs an authenticated CLI profile (the parent ",{"type":43,"tag":90,"props":109,"children":111},{"className":110},[],[112],{"type":48,"value":38},{"type":48,"value":114},"\nskill covers auth\u002Fprofiles if you need it) — but route the data request to Genie\nfirst; don't detour into manual catalog browsing.",{"type":43,"tag":116,"props":117,"children":119},"h2",{"id":118},"routing-genie-vs-your-coding-agent",[120],{"type":48,"value":121},"Routing — Genie vs your coding agent",{"type":43,"tag":51,"props":123,"children":124},{},[125],{"type":43,"tag":57,"props":126,"children":127},{},[128],{"type":48,"value":129},"Route to Genie when the request is about the data:",{"type":43,"tag":65,"props":131,"children":132},{},[133,143,153,163],{"type":43,"tag":69,"props":134,"children":135},{},[136,141],{"type":43,"tag":57,"props":137,"children":138},{},[139],{"type":48,"value":140},"Finding or locating data",{"type":48,"value":142}," — \"what tables are in wanderbricks?\", \"where does X\nlive?\", which catalog\u002Fschema holds something. Let Genie resolve a fuzzy or partial\nname across all your data instead of guessing or grepping catalogs yourself.",{"type":43,"tag":69,"props":144,"children":145},{},[146,151],{"type":43,"tag":57,"props":147,"children":148},{},[149],{"type":48,"value":150},"Questions about the data",{"type":48,"value":152}," — \"how many…\", \"what's the average…\", \"which … the\nmost…\", trends, breakdowns.",{"type":43,"tag":69,"props":154,"children":155},{},[156,161],{"type":43,"tag":57,"props":157,"children":158},{},[159],{"type":48,"value":160},"Generating SQL from a question",{"type":48,"value":162}," — a first-cut query you can run, adapt, or drop\ninto a file.",{"type":43,"tag":69,"props":164,"children":165},{},[166,171],{"type":43,"tag":57,"props":167,"children":168},{},[169],{"type":48,"value":170},"Understanding or profiling data",{"type":48,"value":172}," to inform a query, dashboard, or app.",{"type":43,"tag":51,"props":174,"children":175},{},[176],{"type":43,"tag":57,"props":177,"children":178},{},[179],{"type":48,"value":180},"Route to your own coding agent (do NOT use Genie) for everything else:",{"type":43,"tag":65,"props":182,"children":183},{},[184,209,219,259],{"type":43,"tag":69,"props":185,"children":186},{},[187,192,194,200,202,207],{"type":43,"tag":57,"props":188,"children":189},{},[190],{"type":48,"value":191},"Writing or editing files",{"type":48,"value":193}," — a ",{"type":43,"tag":90,"props":195,"children":197},{"className":196},[],[198],{"type":48,"value":199},".sql",{"type":48,"value":201}," file, notebook, dashboard, app, config.\nGenie finds the data and produces the SQL; ",{"type":43,"tag":75,"props":203,"children":204},{},[205],{"type":48,"value":206},"you",{"type":48,"value":208}," write the file.",{"type":43,"tag":69,"props":210,"children":211},{},[212,217],{"type":43,"tag":57,"props":213,"children":214},{},[215],{"type":48,"value":216},"Authoring jobs, pipelines, apps, or DABs",{"type":48,"value":218}," — use those product skills.",{"type":43,"tag":69,"props":220,"children":221},{},[222,227,229,235,237,243,244,250,251,257],{"type":43,"tag":57,"props":223,"children":224},{},[225],{"type":48,"value":226},"DDL or writes",{"type":48,"value":228}," — ",{"type":43,"tag":90,"props":230,"children":232},{"className":231},[],[233],{"type":48,"value":234},"CREATE",{"type":48,"value":236}," \u002F ",{"type":43,"tag":90,"props":238,"children":240},{"className":239},[],[241],{"type":48,"value":242},"INSERT",{"type":48,"value":236},{"type":43,"tag":90,"props":245,"children":247},{"className":246},[],[248],{"type":48,"value":249},"UPDATE",{"type":48,"value":236},{"type":43,"tag":90,"props":252,"children":254},{"className":253},[],[255],{"type":48,"value":256},"DELETE",{"type":48,"value":258},".",{"type":43,"tag":69,"props":260,"children":261},{},[262],{"type":43,"tag":57,"props":263,"children":264},{},[265],{"type":48,"value":266},"General programming, git, infra, and any non-data task.",{"type":43,"tag":51,"props":268,"children":269},{},[270,275],{"type":43,"tag":57,"props":271,"children":272},{},[273],{"type":48,"value":274},"Key principle:",{"type":48,"value":276}," data discovery, data questions, and query generation → Genie One.\nEverything else → your coding agent.",{"type":43,"tag":116,"props":278,"children":280},{"id":279},"why-prefer-genie-for-data-questions",[281],{"type":48,"value":282},"Why prefer Genie for data questions",{"type":43,"tag":51,"props":284,"children":285},{},[286,288,293,295,300],{"type":48,"value":287},"Genie runs ",{"type":43,"tag":75,"props":289,"children":290},{},[291],{"type":48,"value":292},"inside the Databricks data plane",{"type":48,"value":294}," with governed, first-hand access to\nthe org's Unity Catalog metadata, metric views, and curated semantic context —\ncontext you do ",{"type":43,"tag":57,"props":296,"children":297},{},[298],{"type":48,"value":299},"not",{"type":48,"value":301}," have when reverse-engineering schemas with ad-hoc SQL. For\ndata questions it is often higher-quality and more performant than doing the\ndiscovery yourself, and it keeps improving as a managed Databricks capability.\nDon't default to writing your own discovery SQL just because you can.",{"type":43,"tag":116,"props":303,"children":305},{"id":304},"how-to-ask-genie",[306],{"type":48,"value":307},"How to ask Genie",{"type":43,"tag":51,"props":309,"children":310},{},[311,313,319,321,326],{"type":48,"value":312},"Always pass a session label with ",{"type":43,"tag":90,"props":314,"children":316},{"className":315},[],[317],{"type":48,"value":318},"-s",{"type":48,"value":320},", and prefer reusing the ",{"type":43,"tag":57,"props":322,"children":323},{},[324],{"type":48,"value":325},"same",{"type":48,"value":327}," one: a\nfollow-up can only continue a conversation if the first ask set the session label,\nand reusing it lets later questions build on everything asked so far (\"summarize all\nof the above\"). Use a fresh session label only to start a deliberately separate\nsession, or distinct session labels to run several in parallel.",{"type":43,"tag":51,"props":329,"children":330},{},[331,333,339,341,347,349,354],{"type":48,"value":332},"The command is ",{"type":43,"tag":90,"props":334,"children":336},{"className":335},[],[337],{"type":48,"value":338},"databricks genie ask",{"type":48,"value":340}," (CLI >= v1.9.0). On an older CLI it lives\nunder ",{"type":43,"tag":90,"props":342,"children":344},{"className":343},[],[345],{"type":48,"value":346},"databricks experimental genie ask",{"type":48,"value":348}," — same flags and behavior; use that\nexact fallback if ",{"type":43,"tag":90,"props":350,"children":352},{"className":351},[],[353],{"type":48,"value":338},{"type":48,"value":355}," is not found.",{"type":43,"tag":357,"props":358,"children":363},"pre",{"className":359,"code":360,"language":361,"meta":362,"style":362},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","# Always pass a session label, and reuse the SAME one so follow-ups build on each other\ndatabricks genie ask -s trips \"How many bookings were there last week?\"\ndatabricks genie ask -s trips \"Break that down by destination\"\ndatabricks genie ask -s trips \"Summarize all of the above\"\n\n# --include-sql also prints the SQL Genie ran (use it to generate a query, too)\ndatabricks genie ask -s trips \"Write SQL for the top 5 destinations by revenue\" --include-sql\n\n# --output json gives a parseable result\ndatabricks genie ask -s trips \"Top 5 destinations by revenue\" --output json\n# → {\"status\":\"completed\",\"conversation_id\":\"…\",\"text\":\"…\",\"tool_calls\":[{\"name\":\"execute_sql\",\"sql\":\"…\",\"title\":\"…\"}]}\n\n# Older CLI (\u003C v1.9.0) — same command under the deprecated experimental alias:\n#   databricks experimental genie ask -s trips \"How many bookings were there last week?\"\n","bash","",[364],{"type":43,"tag":90,"props":365,"children":366},{"__ignoreMap":362},[367,379,425,462,499,509,518,561,569,578,625,634,642,651],{"type":43,"tag":368,"props":369,"children":372},"span",{"class":370,"line":371},"line",1,[373],{"type":43,"tag":368,"props":374,"children":376},{"style":375},"--shiki-light:#90A4AE;--shiki-light-font-style:italic;--shiki-default:#546E7A;--shiki-default-font-style:italic;--shiki-dark:#676E95;--shiki-dark-font-style:italic",[377],{"type":48,"value":378},"# Always pass a session label, and reuse the SAME one so follow-ups build on each other\n",{"type":43,"tag":368,"props":380,"children":382},{"class":370,"line":381},2,[383,388,394,399,404,409,415,420],{"type":43,"tag":368,"props":384,"children":386},{"style":385},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[387],{"type":48,"value":8},{"type":43,"tag":368,"props":389,"children":391},{"style":390},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[392],{"type":48,"value":393}," genie",{"type":43,"tag":368,"props":395,"children":396},{"style":390},[397],{"type":48,"value":398}," ask",{"type":43,"tag":368,"props":400,"children":401},{"style":390},[402],{"type":48,"value":403}," -s",{"type":43,"tag":368,"props":405,"children":406},{"style":390},[407],{"type":48,"value":408}," trips",{"type":43,"tag":368,"props":410,"children":412},{"style":411},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[413],{"type":48,"value":414}," \"",{"type":43,"tag":368,"props":416,"children":417},{"style":390},[418],{"type":48,"value":419},"How many bookings were there last week?",{"type":43,"tag":368,"props":421,"children":422},{"style":411},[423],{"type":48,"value":424},"\"\n",{"type":43,"tag":368,"props":426,"children":428},{"class":370,"line":427},3,[429,433,437,441,445,449,453,458],{"type":43,"tag":368,"props":430,"children":431},{"style":385},[432],{"type":48,"value":8},{"type":43,"tag":368,"props":434,"children":435},{"style":390},[436],{"type":48,"value":393},{"type":43,"tag":368,"props":438,"children":439},{"style":390},[440],{"type":48,"value":398},{"type":43,"tag":368,"props":442,"children":443},{"style":390},[444],{"type":48,"value":403},{"type":43,"tag":368,"props":446,"children":447},{"style":390},[448],{"type":48,"value":408},{"type":43,"tag":368,"props":450,"children":451},{"style":411},[452],{"type":48,"value":414},{"type":43,"tag":368,"props":454,"children":455},{"style":390},[456],{"type":48,"value":457},"Break that down by destination",{"type":43,"tag":368,"props":459,"children":460},{"style":411},[461],{"type":48,"value":424},{"type":43,"tag":368,"props":463,"children":465},{"class":370,"line":464},4,[466,470,474,478,482,486,490,495],{"type":43,"tag":368,"props":467,"children":468},{"style":385},[469],{"type":48,"value":8},{"type":43,"tag":368,"props":471,"children":472},{"style":390},[473],{"type":48,"value":393},{"type":43,"tag":368,"props":475,"children":476},{"style":390},[477],{"type":48,"value":398},{"type":43,"tag":368,"props":479,"children":480},{"style":390},[481],{"type":48,"value":403},{"type":43,"tag":368,"props":483,"children":484},{"style":390},[485],{"type":48,"value":408},{"type":43,"tag":368,"props":487,"children":488},{"style":411},[489],{"type":48,"value":414},{"type":43,"tag":368,"props":491,"children":492},{"style":390},[493],{"type":48,"value":494},"Summarize all of the above",{"type":43,"tag":368,"props":496,"children":497},{"style":411},[498],{"type":48,"value":424},{"type":43,"tag":368,"props":500,"children":502},{"class":370,"line":501},5,[503],{"type":43,"tag":368,"props":504,"children":506},{"emptyLinePlaceholder":505},true,[507],{"type":48,"value":508},"\n",{"type":43,"tag":368,"props":510,"children":512},{"class":370,"line":511},6,[513],{"type":43,"tag":368,"props":514,"children":515},{"style":375},[516],{"type":48,"value":517},"# --include-sql also prints the SQL Genie ran (use it to generate a query, too)\n",{"type":43,"tag":368,"props":519,"children":521},{"class":370,"line":520},7,[522,526,530,534,538,542,546,551,556],{"type":43,"tag":368,"props":523,"children":524},{"style":385},[525],{"type":48,"value":8},{"type":43,"tag":368,"props":527,"children":528},{"style":390},[529],{"type":48,"value":393},{"type":43,"tag":368,"props":531,"children":532},{"style":390},[533],{"type":48,"value":398},{"type":43,"tag":368,"props":535,"children":536},{"style":390},[537],{"type":48,"value":403},{"type":43,"tag":368,"props":539,"children":540},{"style":390},[541],{"type":48,"value":408},{"type":43,"tag":368,"props":543,"children":544},{"style":411},[545],{"type":48,"value":414},{"type":43,"tag":368,"props":547,"children":548},{"style":390},[549],{"type":48,"value":550},"Write SQL for the top 5 destinations by revenue",{"type":43,"tag":368,"props":552,"children":553},{"style":411},[554],{"type":48,"value":555},"\"",{"type":43,"tag":368,"props":557,"children":558},{"style":390},[559],{"type":48,"value":560}," --include-sql\n",{"type":43,"tag":368,"props":562,"children":564},{"class":370,"line":563},8,[565],{"type":43,"tag":368,"props":566,"children":567},{"emptyLinePlaceholder":505},[568],{"type":48,"value":508},{"type":43,"tag":368,"props":570,"children":572},{"class":370,"line":571},9,[573],{"type":43,"tag":368,"props":574,"children":575},{"style":375},[576],{"type":48,"value":577},"# --output json gives a parseable result\n",{"type":43,"tag":368,"props":579,"children":581},{"class":370,"line":580},10,[582,586,590,594,598,602,606,611,615,620],{"type":43,"tag":368,"props":583,"children":584},{"style":385},[585],{"type":48,"value":8},{"type":43,"tag":368,"props":587,"children":588},{"style":390},[589],{"type":48,"value":393},{"type":43,"tag":368,"props":591,"children":592},{"style":390},[593],{"type":48,"value":398},{"type":43,"tag":368,"props":595,"children":596},{"style":390},[597],{"type":48,"value":403},{"type":43,"tag":368,"props":599,"children":600},{"style":390},[601],{"type":48,"value":408},{"type":43,"tag":368,"props":603,"children":604},{"style":411},[605],{"type":48,"value":414},{"type":43,"tag":368,"props":607,"children":608},{"style":390},[609],{"type":48,"value":610},"Top 5 destinations by revenue",{"type":43,"tag":368,"props":612,"children":613},{"style":411},[614],{"type":48,"value":555},{"type":43,"tag":368,"props":616,"children":617},{"style":390},[618],{"type":48,"value":619}," --output",{"type":43,"tag":368,"props":621,"children":622},{"style":390},[623],{"type":48,"value":624}," json\n",{"type":43,"tag":368,"props":626,"children":628},{"class":370,"line":627},11,[629],{"type":43,"tag":368,"props":630,"children":631},{"style":375},[632],{"type":48,"value":633},"# → {\"status\":\"completed\",\"conversation_id\":\"…\",\"text\":\"…\",\"tool_calls\":[{\"name\":\"execute_sql\",\"sql\":\"…\",\"title\":\"…\"}]}\n",{"type":43,"tag":368,"props":635,"children":637},{"class":370,"line":636},12,[638],{"type":43,"tag":368,"props":639,"children":640},{"emptyLinePlaceholder":505},[641],{"type":48,"value":508},{"type":43,"tag":368,"props":643,"children":645},{"class":370,"line":644},13,[646],{"type":43,"tag":368,"props":647,"children":648},{"style":375},[649],{"type":48,"value":650},"# Older CLI (\u003C v1.9.0) — same command under the deprecated experimental alias:\n",{"type":43,"tag":368,"props":652,"children":654},{"class":370,"line":653},14,[655],{"type":43,"tag":368,"props":656,"children":657},{"style":375},[658],{"type":48,"value":659},"#   databricks experimental genie ask -s trips \"How many bookings were there last week?\"\n",{"type":43,"tag":51,"props":661,"children":662},{},[663,665,671],{"type":48,"value":664},"Genie searches across all the data you can see, runs SQL, and streams a grounded\nanswer — rendered with the executed SQL and, where it helps, a terminal chart. It\nauto-resolves a SQL warehouse (override with ",{"type":43,"tag":90,"props":666,"children":668},{"className":667},[],[669],{"type":48,"value":670},"--warehouse-id",{"type":48,"value":672},"); nothing to pick or\nset up.",{"type":43,"tag":65,"props":674,"children":675},{},[676,694,720,752,801,819,850],{"type":43,"tag":69,"props":677,"children":678},{},[679,684,686,692],{"type":43,"tag":57,"props":680,"children":681},{},[682],{"type":48,"value":683},"Streams live",{"type":48,"value":685},": the answer, the agent's steps, and any SQL\u002Fresults appear as\nthey arrive. Answers usually take ~5–30s; a stalled stream (no data for ~10 min)\nfails with a clear message, and Ctrl-C or ",{"type":43,"tag":90,"props":687,"children":689},{"className":688},[],[690],{"type":48,"value":691},"kill",{"type":48,"value":693}," (SIGTERM) cancels cleanly.",{"type":43,"tag":69,"props":695,"children":696},{},[697,702,704,710,712,718],{"type":43,"tag":57,"props":698,"children":699},{},[700],{"type":48,"value":701},"Picking a session label",{"type":48,"value":703},": any string works — a topic like ",{"type":43,"tag":90,"props":705,"children":707},{"className":706},[],[708],{"type":48,"value":709},"trips",{"type":48,"value":711},", or ",{"type":43,"tag":90,"props":713,"children":715},{"className":714},[],[716],{"type":48,"value":717},"$$",{"type":48,"value":719}," for a\nper-shell session. Default to reusing one session label so follow-ups keep full\ncontext; use a fresh one only for a deliberately separate session. An expired\nsession label just starts fresh on the next ask. No id to copy around.",{"type":43,"tag":69,"props":721,"children":722},{},[723,728,730,736,738,744,746,750],{"type":43,"tag":57,"props":724,"children":725},{},[726],{"type":48,"value":727},"Parallelism",{"type":48,"value":729},": to run sessions at the same time, give each its own session label\n(",{"type":43,"tag":90,"props":731,"children":733},{"className":732},[],[734],{"type":48,"value":735},"-s q1",{"type":48,"value":737},", ",{"type":43,"tag":90,"props":739,"children":741},{"className":740},[],[742],{"type":48,"value":743},"-s q2",{"type":48,"value":745},", …) — independent session labels don't interfere. Within a single\nsession label keep calls sequential: send a follow-up after the previous turn\nreturns, and never fire two asks at once on the ",{"type":43,"tag":75,"props":747,"children":748},{},[749],{"type":48,"value":325},{"type":48,"value":751}," session label (they'd split\ninto two conversations and only one mapping would survive).",{"type":43,"tag":69,"props":753,"children":754},{},[755,760,762,768,770,776,778,784,786,792,794,799],{"type":43,"tag":57,"props":756,"children":757},{},[758],{"type":48,"value":759},"Structured output",{"type":48,"value":761},": ",{"type":43,"tag":90,"props":763,"children":765},{"className":764},[],[766],{"type":48,"value":767},"--output json",{"type":48,"value":769}," gives ",{"type":43,"tag":90,"props":771,"children":773},{"className":772},[],[774],{"type":48,"value":775},"{status, conversation_id, text, tool_calls[]}",{"type":48,"value":777},", where ",{"type":43,"tag":90,"props":779,"children":781},{"className":780},[],[782],{"type":48,"value":783},"tool_calls",{"type":48,"value":785}," includes the SQL Genie executed; ",{"type":43,"tag":90,"props":787,"children":789},{"className":788},[],[790],{"type":48,"value":791},"--raw",{"type":48,"value":793}," dumps\nthe raw event stream. Note ",{"type":43,"tag":90,"props":795,"children":797},{"className":796},[],[798],{"type":48,"value":767},{"type":48,"value":800}," buffers and prints once at the end (no\nlive streaming) — use it for parsing, the default text output for interactive use.",{"type":43,"tag":69,"props":802,"children":803},{},[804,809,811,817],{"type":43,"tag":57,"props":805,"children":806},{},[807],{"type":48,"value":808},"Generating a query",{"type":48,"value":810},": ask Genie to \"write SQL for …\" and read the SQL from the\nresponse (it's in the answer text, and ",{"type":43,"tag":90,"props":812,"children":814},{"className":813},[],[815],{"type":48,"value":816},"--include-sql",{"type":48,"value":818}," also shows the query Genie\nran to verify it — so the SQL is known-good). Genie resolves the schema and joins\nfor you, so this beats hand-writing SQL against unfamiliar tables.",{"type":43,"tag":69,"props":820,"children":821},{},[822,827,829,834,836,841,843,849],{"type":43,"tag":57,"props":823,"children":824},{},[825],{"type":48,"value":826},"For exact\u002Ffull rows",{"type":48,"value":828},": Genie shows a preview inline; to pull the complete result\nset locally, copy its SQL (",{"type":43,"tag":90,"props":830,"children":832},{"className":831},[],[833],{"type":48,"value":816},{"type":48,"value":835}," or the JSON ",{"type":43,"tag":90,"props":837,"children":839},{"className":838},[],[840],{"type":48,"value":783},{"type":48,"value":842},") into the\nparent's ",{"type":43,"tag":90,"props":844,"children":846},{"className":845},[],[847],{"type":48,"value":848},"... aitools tools query \"\u003CSQL>\"",{"type":48,"value":258},{"type":43,"tag":69,"props":851,"children":852},{},[853,858],{"type":43,"tag":57,"props":854,"children":855},{},[856],{"type":48,"value":857},"A non-answer is a message, not an error",{"type":48,"value":859},": if Genie refuses or \"couldn't find\nrelevant data,\" don't retry — use the manual fallback below.",{"type":43,"tag":861,"props":862,"children":863},"blockquote",{},[864],{"type":43,"tag":51,"props":865,"children":866},{},[867,872,874,880],{"type":43,"tag":57,"props":868,"children":869},{},[870],{"type":48,"value":871},"Naming:",{"type":48,"value":873}," \"Genie One\" is the current name for this cross-data chat — formerly\n\"Databricks One\", then \"OneChat\" (the backend tool is still literally named\n",{"type":43,"tag":90,"props":875,"children":877},{"className":876},[],[878],{"type":48,"value":879},"onechat",{"type":48,"value":881},"). All the same thing.",{"type":43,"tag":116,"props":883,"children":885},{"id":884},"if-genie-one-isnt-available-manual-fallback",[886],{"type":48,"value":887},"If Genie One isn't available — manual fallback",{"type":43,"tag":51,"props":889,"children":890},{},[891,893,898,900,906,908,914,916,922,924,934,936,942,943,949,951,957,959,963,965,971],{"type":48,"value":892},"Only fall back if Genie One is genuinely unavailable — first ",{"type":43,"tag":57,"props":894,"children":895},{},[896],{"type":48,"value":897},"verify",{"type":48,"value":899}," with\n",{"type":43,"tag":90,"props":901,"children":903},{"className":902},[],[904],{"type":48,"value":905},"databricks genie ask --help",{"type":48,"value":907}," (or ",{"type":43,"tag":90,"props":909,"children":911},{"className":910},[],[912],{"type":48,"value":913},"databricks experimental genie ask --help",{"type":48,"value":915}," on a\nCLI older than v1.9.0); don't assume the command is missing. When Genie One isn't\nenabled, the CLI is too old to have either form of ",{"type":43,"tag":90,"props":917,"children":919},{"className":918},[],[920],{"type":48,"value":921},"genie ask",{"type":48,"value":923},",\nor Genie can't cover the question, do the discovery yourself with the parent skill's\ncommands — see ",{"type":43,"tag":57,"props":925,"children":926},{},[927],{"type":43,"tag":928,"props":929,"children":931},"a",{"href":930},"..\u002Fdatabricks-core\u002Fmanual-data-exploration.md",[932],{"type":48,"value":933},"Manual Data Exploration",{"type":48,"value":935},"\n(keyword search via ",{"type":43,"tag":90,"props":937,"children":939},{"className":938},[],[940],{"type":48,"value":941},"information_schema",{"type":48,"value":737},{"type":43,"tag":90,"props":944,"children":946},{"className":945},[],[947],{"type":48,"value":948},"discover-schema",{"type":48,"value":950},", and ",{"type":43,"tag":90,"props":952,"children":954},{"className":953},[],[955],{"type":48,"value":956},"tools query",{"type":48,"value":958},").\nRunning known SQL or profiling a known table that way is perfectly fine on its own.\nDo ",{"type":43,"tag":57,"props":960,"children":961},{},[962],{"type":48,"value":299},{"type":48,"value":964}," default to ",{"type":43,"tag":90,"props":966,"children":968},{"className":967},[],[969],{"type":48,"value":970},"databricks tables list",{"type":48,"value":972}," or raw UC REST for data-location\nquestions — invoke this skill and ask Genie first.",{"type":43,"tag":116,"props":974,"children":976},{"id":975},"relationship-to-the-genie-one-mcp",[977],{"type":48,"value":978},"Relationship to the Genie One MCP",{"type":43,"tag":51,"props":980,"children":981},{},[982,984,989,991,996,998,1003],{"type":48,"value":983},"Databricks also offers this capability as a managed ",{"type":43,"tag":57,"props":985,"children":986},{},[987],{"type":48,"value":988},"MCP",{"type":48,"value":990}," server — the ",{"type":43,"tag":75,"props":992,"children":993},{},[994],{"type":48,"value":995},"Genie One\nMCP",{"type":48,"value":997},". This skill delivers the ",{"type":43,"tag":57,"props":999,"children":1000},{},[1001],{"type":48,"value":1002},"same functionality",{"type":48,"value":1004}," through the Databricks CLI, with\nno MCP server to configure or host. More broadly, the Databricks Agent Skills cover\nthe same ground as Databricks' managed MCP servers, so you don't need any MCP wired up\nto use this. If you already run the Genie One MCP, use whichever you prefer — they hit\nthe same Genie backend.",{"type":43,"tag":116,"props":1006,"children":1008},{"id":1007},"related-skills",[1009],{"type":48,"value":1010},"Related Skills",{"type":43,"tag":65,"props":1012,"children":1013},{},[1014,1031],{"type":43,"tag":69,"props":1015,"children":1016},{},[1017,1022,1024,1029],{"type":43,"tag":57,"props":1018,"children":1019},{},[1020],{"type":48,"value":1021},"databricks-genie-agents",{"type":48,"value":1023}," — build and manage ",{"type":43,"tag":57,"props":1025,"children":1026},{},[1027],{"type":48,"value":1028},"Genie Agents",{"type":48,"value":1030},": curated\nagents that let you or a group ask questions of specific data (create, configure,\nimport\u002Fexport).",{"type":43,"tag":69,"props":1032,"children":1033},{},[1034,1038],{"type":43,"tag":57,"props":1035,"children":1036},{},[1037],{"type":48,"value":38},{"type":48,"value":1039}," (parent) — CLI auth, profiles, and the manual data exploration\nreference used as the fallback.",{"type":43,"tag":1041,"props":1042,"children":1043},"style",{},[1044],{"type":48,"value":1045},"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":1047,"total":1227},[1048,1065,1077,1094,1111,1131,1142,1165,1176,1193,1200,1213],{"slug":1049,"name":1049,"fn":1050,"description":1051,"org":1052,"tags":1053,"stars":23,"repoUrl":24,"updatedAt":1064},"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},[1054,1057,1058,1061],{"name":1055,"slug":1056,"type":15},"Agents","agents",{"name":9,"slug":8,"type":15},{"name":1059,"slug":1060,"type":15},"Knowledge Management","knowledge-management",{"name":1062,"slug":1063,"type":15},"Multi-Agent","multi-agent","2026-07-15T05:41:38.548954",{"slug":1066,"name":1066,"fn":1067,"description":1068,"org":1069,"tags":1070,"stars":23,"repoUrl":24,"updatedAt":1076},"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},[1071,1072,1073],{"name":17,"slug":18,"type":15},{"name":9,"slug":8,"type":15},{"name":1074,"slug":1075,"type":15},"LLM","llm","2026-07-31T05:53:33.562077",{"slug":1078,"name":1078,"fn":1079,"description":1080,"org":1081,"tags":1082,"stars":23,"repoUrl":24,"updatedAt":1093},"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},[1083,1086,1087,1090],{"name":1084,"slug":1085,"type":15},"CLI","cli",{"name":9,"slug":8,"type":15},{"name":1088,"slug":1089,"type":15},"Docker","docker",{"name":1091,"slug":1092,"type":15},"Engineering","engineering","2026-07-12T08:04:55.843982",{"slug":1095,"name":1095,"fn":1096,"description":1097,"org":1098,"tags":1099,"stars":23,"repoUrl":24,"updatedAt":1110},"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},[1100,1103,1106,1109],{"name":1101,"slug":1102,"type":15},"Analytics","analytics",{"name":1104,"slug":1105,"type":15},"Dashboards","dashboards",{"name":1107,"slug":1108,"type":15},"Data Visualization","data-visualization",{"name":9,"slug":8,"type":15},"2026-07-12T08:04:25.314591",{"slug":1112,"name":1112,"fn":1113,"description":1114,"org":1115,"tags":1116,"stars":23,"repoUrl":24,"updatedAt":1130},"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},[1117,1118,1121,1124,1127],{"name":9,"slug":8,"type":15},{"name":1119,"slug":1120,"type":15},"Design","design",{"name":1122,"slug":1123,"type":15},"Frontend","frontend",{"name":1125,"slug":1126,"type":15},"React","react",{"name":1128,"slug":1129,"type":15},"UI Components","ui-components","2026-07-12T08:04:02.02398",{"slug":1132,"name":1132,"fn":1133,"description":1134,"org":1135,"tags":1136,"stars":23,"repoUrl":24,"updatedAt":1141},"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},[1137,1138,1139,1140],{"name":1101,"slug":1102,"type":15},{"name":1104,"slug":1105,"type":15},{"name":17,"slug":18,"type":15},{"name":9,"slug":8,"type":15},"2026-07-12T08:03:59.061458",{"slug":1143,"name":1143,"fn":1144,"description":1145,"org":1146,"tags":1147,"stars":23,"repoUrl":24,"updatedAt":1164},"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},[1148,1149,1152,1155,1158,1161],{"name":9,"slug":8,"type":15},{"name":1150,"slug":1151,"type":15},"FastAPI","fastapi",{"name":1153,"slug":1154,"type":15},"Flask","flask",{"name":1156,"slug":1157,"type":15},"Gradio","gradio",{"name":1159,"slug":1160,"type":15},"Python","python",{"name":1162,"slug":1163,"type":15},"Streamlit","streamlit","2026-07-12T08:04:10.970845",{"slug":38,"name":38,"fn":1166,"description":1167,"org":1168,"tags":1169,"stars":23,"repoUrl":24,"updatedAt":1175},"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},[1170,1173,1174],{"name":1171,"slug":1172,"type":15},"Authentication","authentication",{"name":1084,"slug":1085,"type":15},{"name":9,"slug":8,"type":15},"2026-07-18T05:11:05.45506",{"slug":1177,"name":1177,"fn":1178,"description":1179,"org":1180,"tags":1181,"stars":23,"repoUrl":24,"updatedAt":1192},"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},[1182,1185,1188,1189],{"name":1183,"slug":1184,"type":15},"Automation","automation",{"name":1186,"slug":1187,"type":15},"Configuration","configuration",{"name":9,"slug":8,"type":15},{"name":1190,"slug":1191,"type":15},"Deployment","deployment","2026-07-15T05:41:35.930355",{"slug":4,"name":4,"fn":5,"description":6,"org":1194,"tags":1195,"stars":23,"repoUrl":24,"updatedAt":25},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1196,1197,1198,1199],{"name":17,"slug":18,"type":15},{"name":13,"slug":14,"type":15},{"name":9,"slug":8,"type":15},{"name":21,"slug":22,"type":15},{"slug":1201,"name":1201,"fn":1202,"description":1203,"org":1204,"tags":1205,"stars":23,"repoUrl":24,"updatedAt":1212},"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},[1206,1207,1210,1211],{"name":17,"slug":18,"type":15},{"name":1208,"slug":1209,"type":15},"Database","database",{"name":9,"slug":8,"type":15},{"name":21,"slug":22,"type":15},"2026-07-12T08:04:08.678282",{"slug":1214,"name":1214,"fn":1215,"description":1216,"org":1217,"tags":1218,"stars":23,"repoUrl":24,"updatedAt":1226},"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},[1219,1220,1223],{"name":9,"slug":8,"type":15},{"name":1221,"slug":1222,"type":15},"Documentation","documentation",{"name":1224,"slug":1225,"type":15},"Reference","reference","2026-07-15T05:41:34.697746",31,{"items":1229,"total":1227},[1230,1237,1243,1250,1257,1265,1272],{"slug":1049,"name":1049,"fn":1050,"description":1051,"org":1231,"tags":1232,"stars":23,"repoUrl":24,"updatedAt":1064},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1233,1234,1235,1236],{"name":1055,"slug":1056,"type":15},{"name":9,"slug":8,"type":15},{"name":1059,"slug":1060,"type":15},{"name":1062,"slug":1063,"type":15},{"slug":1066,"name":1066,"fn":1067,"description":1068,"org":1238,"tags":1239,"stars":23,"repoUrl":24,"updatedAt":1076},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1240,1241,1242],{"name":17,"slug":18,"type":15},{"name":9,"slug":8,"type":15},{"name":1074,"slug":1075,"type":15},{"slug":1078,"name":1078,"fn":1079,"description":1080,"org":1244,"tags":1245,"stars":23,"repoUrl":24,"updatedAt":1093},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1246,1247,1248,1249],{"name":1084,"slug":1085,"type":15},{"name":9,"slug":8,"type":15},{"name":1088,"slug":1089,"type":15},{"name":1091,"slug":1092,"type":15},{"slug":1095,"name":1095,"fn":1096,"description":1097,"org":1251,"tags":1252,"stars":23,"repoUrl":24,"updatedAt":1110},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1253,1254,1255,1256],{"name":1101,"slug":1102,"type":15},{"name":1104,"slug":1105,"type":15},{"name":1107,"slug":1108,"type":15},{"name":9,"slug":8,"type":15},{"slug":1112,"name":1112,"fn":1113,"description":1114,"org":1258,"tags":1259,"stars":23,"repoUrl":24,"updatedAt":1130},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1260,1261,1262,1263,1264],{"name":9,"slug":8,"type":15},{"name":1119,"slug":1120,"type":15},{"name":1122,"slug":1123,"type":15},{"name":1125,"slug":1126,"type":15},{"name":1128,"slug":1129,"type":15},{"slug":1132,"name":1132,"fn":1133,"description":1134,"org":1266,"tags":1267,"stars":23,"repoUrl":24,"updatedAt":1141},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1268,1269,1270,1271],{"name":1101,"slug":1102,"type":15},{"name":1104,"slug":1105,"type":15},{"name":17,"slug":18,"type":15},{"name":9,"slug":8,"type":15},{"slug":1143,"name":1143,"fn":1144,"description":1145,"org":1273,"tags":1274,"stars":23,"repoUrl":24,"updatedAt":1164},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1275,1276,1277,1278,1279,1280],{"name":9,"slug":8,"type":15},{"name":1150,"slug":1151,"type":15},{"name":1153,"slug":1154,"type":15},{"name":1156,"slug":1157,"type":15},{"name":1159,"slug":1160,"type":15},{"name":1162,"slug":1163,"type":15}]