A Databricks data-discovery workflow that routes natural-language data questions and SQL generation through Genie.
Editorial review checked 2026-10-29 against this instruction snapshot. Supporting scripts and runtime behavior remain outside this editorial review.
The source distinguishes questions about governed data from local file editing or other coding work. It uses a session label for related questions and can request the SQL behind an answer. A manual exploration path is described for cases where the preferred capability is genuinely unavailable.
Finding relevant tables or answering a bounded analytical question in an already authorized Databricks workspace.
Generated SQL and natural-language answers still need validation. Workspace permissions define the accessible data, and a missing result may reflect access limits rather than absence. Session reuse should not mix unrelated sensitive contexts or imply broader authorization.
Requires databricks CLI >= v1.9.0 for `databricks genie ask` (older CLIs fall back to the deprecated `databricks experimental genie ask` alias)
Inspect the pinned source snapshot and its supporting files first. The command selects this skill through the open-source skills CLI. Node.js and agent-specific setup may be required. Installation can download code; this catalog never runs it.
npx skills add https://github.com/databricks/databricks-agent-skills/tree/d50672205671c6d6edc847b1ddc36e7cba69bd32/skills/databricks-data-discovery --skill databricks-data-discoveryReview pinned skill folder ↗ · CLI documentation ↗
After source review, use npx skills check and npx skills update to inspect and apply upstream updates. Re-check changed instructions before running them.
Static review only. This is not a security audit or a guarantee of safety.
SKILL.md text only; scripts, dependencies and runtime behavior not audited.
Allowed tools declaration: Unknown. Runtime permissions and network behavior: Unknown.
74/100 · Metadata coverage 80% · Model 1.0
Scores summarize observable discovery signals. Popularity and repository activity apply to the whole repository. Unknown runtime safety earns no certification.
Select the intended profile and formulate a precise data question with time range and metric definitions. Preserve the generated query and inspect the referenced tables before relying on its result.
Check filters, joins, units and aggregation grain against a known example. Reconcile important totals independently, state inaccessible or ambiguous data, and avoid treating a fluent answer as proof that the business definition or underlying query is correct.
Related by category; compare scope and dependencies before choosing an alternative.
Explore 360 feedback system as a data & databases workflow from sickn33/agentic-awesome-skills. Compare its source, maintenance and review signals before choosing it for your agent.
Explore access matrix as a data & databases workflow from sickn33/agentic-awesome-skills. Compare its source, maintenance and review signals before choosing it for your agent.
Explore adhx as a data & databases workflow from sickn33/agentic-awesome-skills. Compare its source, maintenance and review signals before choosing it for your agent.
Explore databricks ai functions as a ai & machine learning workflow from databricks/databricks-agent-skills. Compare its source, maintenance and review signals before choosing it for your agent.
Explore databricks ai runtime as a ai & machine learning workflow from databricks/databricks-agent-skills. Compare its source, maintenance and review signals before choosing it for your agent.
Explore databricks aibi dashboards as a testing & qa workflow from databricks/databricks-agent-skills. Compare its source, maintenance and review signals before choosing it for your agent.