databricks-docs
About databricks-docs
databricks-docs is a reference skill for consulting Databricks documentation through its llms.txt index. It is intended to supplement other skills and provide guidance on Databricks concepts, APIs, and MCP tool use rather than perform actions itself.
Key features
- 01Search the Databricks documentation index
- 02Find authoritative concept and API guidance
- 03Browse documentation by subject area
- 04Supplement workflows from other skills
Use cases
- 01Look up a Databricks feature not covered elsewhere
- 02Clarify details of Databricks APIs
- 03Find guidance before using MCP tools
- 04Consult documentation alongside a workflow skill
MCP support
This reference skill helps users find documentation that informs MCP tool use. It directs actions to MCP tools such as execute_sql and manage_pipeline rather than performing them itself.
Install
Copy the command and run it in a terminal.
npx skills add https:/ / github.com/ databricks-solutions/ ai-dev-kit --skill databricks-docsAfter installing, type/databricks-docsin Claude Code to confirm it loaded.
Details
From the project READMEDatabricks Documentation Reference
This skill provides access to the complete Databricks documentation index via llms.txt - use it as a reference resource to supplement other skills and inform your use of MCP tools.
Role of This Skill
This is a reference skill, not an action skill. Use it to:
- Look up documentation when other skills don't cover a topic
- Get authoritative guidance on Databricks concepts and APIs
- Find detailed information to inform how you use MCP tools
- Discover features and capabilities you may not know about
Always prefer using MCP tools for actions (execute_sql, manage_pipeline, etc.) and load specific skills for workflows (databricks-python-sdk, databricks-spark-declarative-pipelines, etc.). Use this skill when you need reference documentation.
How to Use
Fetch the llms.txt documentation index:
URL: https://docs.databricks.com/llms.txt
Use WebFetch to retrieve this index, then:
- Search for relevant sections/links
- Fetch specific documentation pages for detailed guidance
- Apply what you learn using the appropriate MCP tools
Documentation Structure
The llms.txt file is organized by category:
- Overview & Getting Started - Basic concepts and tutorials
- Data Engineering - Lakeflow, Spark, Delta Lake, pipelines
- SQL & Analytics - Warehouses, queries, dashboards
- AI/ML - MLflow, model serving, GenAI
- Governance - Unity Catalog, permissions, security
- Developer Tools - SDKs, CLI, APIs, Terraform
Example: Complementing Other Skills
Scenario: User wants to create a Delta Live Tables pipeline
- Load
databricks-spark-declarative-pipelinesskill for workflow patterns - Use this skill to fetch docs if you need clarification on specific DLT features
- Use
manage_pipeline(action="create_or_update")MCP tool to actually create the pipeline
Scenario: User asks about an unfamiliar Databricks feature
- Fetch llms.txt to find relevant documentation
- Read the specific docs to understand the feature
- Determine which skill/tools apply, then use them
Related Skills
- databricks-python-sdk - SDK patterns for programmatic Databricks access
- databricks-spark-declarative-pipelines - DLT / Lakeflow pipeline workflows
- databricks-unity-catalog - Governance and catalog management
- databricks-model-serving - Serving endpoints and model deployment
- databricks-mlflow-evaluation - MLflow 3 GenAI evaluation workflows