Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →microsoftdocs/azure-databricks
Expert knowledge for Azure Databricks development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment.
Passed 26 of 26 test cases with the skill, and 11 of 26 without it.
and 13 more in the full report
15 fixed11 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
One of 15 test cases the skill fixed. Same model, same prompt, with and without the skill.
What line range in the Category Index covers decision-making topics, such as choosing subscription tiers, runtimes, compute options, and Unity Catalog migrations?
| Checked | Without skill | With skill |
|---|---|---|
| L384-L492 | Missed | Passed |
The instructions your model reads when the skill loads.
This skill provides expert guidance for Azure Databricks. Covers troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. It combines local quick-reference content with remote documentation fetching capabilities.
IMPORTANT for Agent: Use the Category Index below to locate relevant sections. For categories with line ranges (e.g.,
L35-L120), useread_filewith the specified lines. For categories with file links (e.g.,[security.md](security.md)), useread_fileon the linked reference file
IMPORTANT for Agent: If
metadata.generated_atis more than 3 months old, suggest the user pull the latest version from the repository. Ifmcp_microsoftdocstools are not available, suggest the user install it: Installation Guide
This skill requires network access to fetch documentation content:
mcp_microsoftdocs:microsoft_docs_fetch with query string from=learn-agent-skill. Returns Markdown.fetch_webpage with query string from=learn-agent-skill&accept=text/markdown. Returns Markdown.| Category | Location | Description |
|---|---|---|
| Troubleshooting | L37-L183 | Diagnosing and fixing Databricks issues: Spark and SQL errors, connectors and Lakeflow pipelines, model serving and AI Runtime, CLI/IDE/Git problems, and monitoring/debugging tools. |
| Best Practices | L184-L398 | End-to-end Databricks best practices for cost, governance, security, performance, streaming, AI/ML/RAG, connectors, and Lakehouse design, plus tuning, testing, and operating production workloads. |
| Decision Making | decision-making.md | Guides for architectural and cost decisions in Azure Databricks: choosing compute, runtimes, AI/BI tools, connectors, and migration paths for workspaces, pipelines, models, and Unity Catalog. |
| Architecture & Design Patterns | architecture-patterns.md | Architectural blueprints and patterns for Databricks: DR/HA, networking, storage, Lakehouse/medallion, Lakeflow/CDC, Lakebase, multi-agent/AI pipelines, MLOps, feature stores, and streaming. |
| Limits & Quotas | limits-quotas.md | Limits, quotas, and constraints for Databricks compute, AI/model serving, Lakeflow pipelines, connectors, Unity Catalog, Free Edition, and related resource usage and throttling behavior. |
| Security | security.md | Identity, access control, encryption, networking, compliance, and secret management for Azure Databricks, Unity Catalog, AI/Apps, Lakeflow, Lakebase, and external data/model connections. |
| Configuration | configuration.md | Configuring and governing Azure Databricks: accounts, workspaces, compute, networking, storage, AI/ML, Lakeflow, Unity Catalog, SQL, connectors, CLI, and monitoring/cost/observability settings. |
| Integrations & Coding Patterns | integrations.md | Patterns and examples for integrating Databricks with apps, agents, AI/ML, external databases/BI tools, Lakehouse Federation, Lakeflow, AI Runtime, and SQL/PySpark APIs and UDFs. |
| Deployment | deployment.md | Deploying and managing Azure Databricks workspaces, apps, models, pipelines, and Lakebase using ARM/Bicep/Terraform/Bundles/CI-CD, plus Unity Catalog, AI Runtime, and model serving deployment patterns. |
test cases passed, vs 11 / 26 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.