AI tools for “data”

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…

Python backend for Databricks Apps — FastAPI (default), Flask, Dash, Streamlit, Gradio, Reflex. **Default for a new Databricks App is `databricks-apps` (AppKit — Node/TypeScript/React) — reach for it first.** Use this…

Design the UX of custom-code Databricks Apps (AppKit/React) data screens — KPI/overview pages, reports, charts, tables, and Genie/chat data assistants — mapped to concrete AppKit components. Use when BUILDING or…

Databricks AI Runtime, the `databricks air` CLI commands for submitting and managing GPU training workloads on Databricks serverless compute. Use for: writing and submitting `databricks air` workload YAML, choosing an…

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

Use Databricks built-in AI Functions (ai_classify, ai_decide, 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,…

Build custom Python data sources for Apache Spark using the PySpark DataSource API — batch and streaming readers/writers for external systems. Use this skill whenever someone wants to connect Spark to an external system…

高度自动化的 IDMP 数据建模与加载工具。支持基于调研文档设计（industry_research.md）或自然语言描述，进行分层资产建模、超级表设计、时序数据模拟及端到端自动化加载与执行。

Create, manage, and query Databricks Genie Agents (formerly Genie Spaces): curated agents over Unity Catalog tables, Metric Views, and documents in UC volumes. Use when building, migrating, tuning, or asking a specific…

IDMP data import and export workflow. Separate package import or export from datasource CSV import, read first, write carefully, and reread records after every write.

IDMP datasource diagnosis workflow. Read the connection, probe connectivity, inspect databases and metadata, compare model mappings, and reread after every probe or write.

IDMP datasource skill. Use it to list and inspect connections, verify connectivity before deeper metadata reads, and diagnose database or table visibility issues instead of stopping at the connection list.

IDMP data import/export skill. Use it to inspect exportable root elements, review import/export records, download artifacts, and distinguish package export, artifact download, and import flows.

Serverless compute for Databricks jobs, Lakeflow pipelines and Declarative Automation Bundles (DABs), with STANDARD or PERFORMANCE_OPTIMIZED and classic only where serverless cannot run the workload. Use when creating,…

…bus to run. Use to stream events, telemetry, logs, IoT data, CDC, or columnar batches into Databricks in near real time; connect existing collectors and log shippers (OpenTelemetry, Debezium, Vector, Telegraf,…

…explicitly asks to create, scaffold, or initialize a new Datadog App project — they must use action words like "create", "scaffold", "new", or "build" together with "Datadog App" or "@datadog/apps" or "npm create…

Build RAG / unstructured-document evaluation datasets and demo documents (e.g. for a Genie Agent with an attached volume) on Databricks: generate synthetic PDFs locally, upload to Unity Catalog volumes, and pair each…

Databricks AI Search (formerly Vector Search) endpoints and indexes for RAG and semantic search. Use when asked to: create Standard or Storage-Optimized endpoints and Delta Sync or Direct Access indexes with…

Generate realistic synthetic data using Spark + Faker (strongly recommended). Supports serverless execution, multiple output formats (Parquet/JSON/CSV/Delta), and scales from thousands to millions of rows. For small…

…legacy AI Gateway on Model Serving endpoints; use databricks-model-serving for…