databrickslabs

This skill should be used when the user asks to "write Gherkin", "create feature files", "generate BDD scenarios", "write acceptance tests in Gherkin", "create Behave features", "write Given When Then tests", "BDD test cases for my pipeline", "Gherkin for Unity Catalog", or wants to translate requirements into Gherkin feature files for Databricks.

This skill should be used when the user asks to "run BDD tests", "execute Behave", "run Gherkin tests", "run my feature files", "behave test results", "run smoke tests", "BDD test report", or needs to execute Behave test suites with specific options like tag filtering, parallel execution, or CI reporting.

This skill should be used when the user asks to "set up BDD", "create a Behave project", "scaffold BDD tests", "initialize Behave", "add BDD to my project", "set up Gherkin testing", "create test structure for Behave", or mentions setting up behavior-driven development testing. Generates a complete Behave project structure wired to Databricks SDK.

This skill should be used when the user asks to "write step definitions", "implement BDD steps", "generate step code", "create Behave steps", "implement Given When Then", "write Python steps for Gherkin", "step definitions for Databricks", or needs to create Python step implementations for existing Gherkin feature files.

Deploy and query Databricks Model Serving endpoints. Use when (1) deploying MLflow models or AI agents to endpoints, (2) creating ChatAgent/ResponsesAgent agents, (3) integrating UC Functions or Vector Search tools, (4) querying deployed endpoints, (5) checking endpoint status. Covers classical ML models, custom pyfunc, and GenAI agents.

Create and manage Databricks Agent Bricks: Knowledge Assistants (KA) for document Q&A, Genie Spaces for SQL exploration, and Supervisor Agents (MAS) for multi-agent orchestration. Use when building conversational AI applications on Databricks.

Create Databricks AI/BI dashboards. CRITICAL: You MUST test ALL SQL queries via execute_sql BEFORE deploying. Follow guidelines strictly.

Build full-stack Databricks applications using APX framework (FastAPI + React).

Generate public-facing documentation for a connector targeted at end users.

Set up authentication for a source connector — generate connector spec, collect credentials interactively, and validate auth.

Run the authenticate script to collect credentials from the user via a browser form.

Guide the user through creating or updating a pipeline for a source connector — read the docs, build a pipeline spec interactively, and run create_pipeline or update_pipeline.

Generate the connector spec YAML file defining connection parameters and external options allowlist.

Single step only: audit a completed connector — implementation, testing & simulator validation, artifacts, security smells, cross-doc consistency — and produce a scored markdown review report. Read-mostly; does not modify connector code.

Generate and run an auth verification test to confirm that collected credentials are valid.

Single step only: implement the connector in Python when the API doc already exists. Do NOT use for full connector creation — use the create-connector agent instead.

Use when the user asks to deploy, ship, release, or push OntoBricks to Databricks. Wraps the Databricks Asset Bundle deploy for the FastAPI app and the MCP server, with the bootstrap-perms safety net described in README.md.

Use after any code change (feature, fix, refactor, review fixup) to update /changelogs/YYYY-MM-DD.log and run the test suite. Mandatory post-change routine — see .cursorrules.

Use when the user asks for a code review, asks to "review the code", or requests review of a feature/PR/branch. Runs the OntoBricks review checklist defined in .cursorrules.

Use when the user adds, changes, or refactors an LLM agent under src/agents/ — or anything that goes through Foundation Model API or an MLflow-traced LLM call. Mandatory under CNS §3.5 and .cursor/12-ai-feature-lifecycle.mdc. Walks the SPEC → dataset → eval-harness → impl → re-eval sequence.

Use when adding a new subpackage under back/core/, back/objects/, or agents/ — e.g. a new graph DB engine, W3C parser, industry importer, reasoning module, or domain class. Enforces the checklist defined in .cursor/07-project-conventions.mdc.

Use when the user asks to "refactor", restructure, clean up, simplify, deduplicate, extract, or reorganize code. Enforces the Martin Fowler discipline defined in src/.coding_rules.md and .cursor/08-testing-and-deployment.mdc.

Run DQX validation end-to-end — read an input table or path, apply checks, and write valid and quarantined rows to output locations — in a single call. Use when the user asks for "apply and save", "quality-check a table and split the output", "DQX on a whole table", "save valid and invalid rows", or wants to drop DQX into a Lakeflow / workflow that runs on a table or path. Covers apply_checks_and_save_in_table, the by_metadata variant, InputConfig / OutputConfig, and incremental streaming mode.

Validate a PySpark DataFrame or Delta table against a set of DQX quality rules using DQEngine. Use when the user asks to "run data quality checks", "apply DQX rules to a DataFrame/table", "split valid and invalid rows", "quarantine bad records", or "integrate DQX into a streaming pipeline". Covers apply_checks, apply_checks_and_split, the by_metadata variants, and the shape of the result columns.

Create DQX quality rules (checks) for a PySpark DataFrame or Delta table. Use when the user asks to "add a DQX check", "define a data quality rule", "validate that column X is not null / unique / in a set", or wants checks expressed in YAML/JSON for storage. Covers DQRowRule, DQDatasetRule, DQForEachColRule, built-in check_funcs, filters, user_metadata, custom SQL/Python checks, and the declarative metadata form.

Profile a DataFrame or table and generate DQX quality rule candidates with summary statistics. Use when the user asks to "profile a table", "generate DQX rules from data", "suggest data quality checks", "bootstrap a checks.yml", or "generate DLT expectations". Covers DQProfiler, DQGenerator, DQDltGenerator, the profiler workflow, sampling / filter options, and AI-assisted variants.

Load and save DQX checks (quality rules) to a file, workspace path, Unity Catalog volume, Delta table, Lakebase, or the DQX installation folder. Use when the user asks to "load DQX checks from YAML", "save checks to a Delta table", "read checks from a volume", "share checks across notebooks", or "use the DQX workspace install's default checks location". Covers every *ChecksStorageConfig and the matching load/save calls.