Skills that teach Claude Code how to work effectively with Databricks - providing patterns, best practices, and code examples that work with Databricks MCP tools.
Run from your project root (the directory where you want .claude/skills created).
If you already have the repo (fork or clone), use the script on disk:
# Install all skills (Databricks + MLflow + APX) — downloads from GitHub by default
./databricks-skills/install_skills.sh
# Install Databricks skills only from this checkout (no network for those skills)
./databricks-skills/install_skills.sh --local
# Install specific skills
./databricks-skills/install_skills.sh databricks-bundles agent-evaluation
# Pin MLflow / APX versions
./databricks-skills/install_skills.sh --mlflow-version v1.0.0
# List available skills
./databricks-skills/install_skills.sh --list
# Install + upload to workspace for Genie Code (/Workspace/Users/<you>/.assistant/skills)
./databricks-skills/install_skills.sh --install-to-genie
./databricks-skills/install_skills.sh --install-to-genie --profile prod
# Local Databricks skills + Genie upload
./databricks-skills/install_skills.sh --local --install-to-geniePaths assume you are at the ai-dev-kit repo root. From another project, copy or symlink the script, or use the curl flow below.
Use this when you only want the installer and not the full repo:
# Install all skills
curl -sSL https://raw.githubusercontent.com/databricks-solutions/ai-dev-kit/main/databricks-skills/install_skills.sh | bash
# Install specific skills (pass args after bash -s --)
curl -sSL https://raw.githubusercontent.com/databricks-solutions/ai-dev-kit/main/databricks-skills/install_skills.sh | bash -s -- databricks-bundles agent-evaluation
curl -sSL https://raw.githubusercontent.com/databricks-solutions/ai-dev-kit/main/databricks-skills/install_skills.sh | bash -s -- --mlflow-version v1.0.0
curl -sSL https://raw.githubusercontent.com/databricks-solutions/ai-dev-kit/main/databricks-skills/install_skills.sh | bash -s -- --list
curl -sSL https://raw.githubusercontent.com/databricks-solutions/ai-dev-kit/main/databricks-skills/install_skills.sh | bash -s -- --install-to-genie
curl -sSL https://raw.githubusercontent.com/databricks-solutions/ai-dev-kit/main/databricks-skills/install_skills.sh | bash -s -- --install-to-genie --profile prod--install-to-genie uploads the tree under ./.claude/skills to the workspace (requires the databricks CLI).
This creates .claude/skills/ and downloads all skills. Claude Code loads them automatically.
- Databricks skills are downloaded from this repository
- MLflow skills are fetched dynamically from github.com/mlflow/skills
Manual install:
mkdir -p .claude/skills
cp -r ai-dev-kit/databricks-skills/databricks-agent-bricks .claude/skills/- databricks-ai-functions - Built-in AI Functions (ai_classify, ai_extract, ai_summarize, ai_query, ai_forecast, ai_parse_document, and more) with SQL and PySpark patterns, function selection guidance, document processing pipelines, and custom RAG (parse → chunk → index → query)
- databricks-agent-bricks - Knowledge Assistants, Genie Spaces, Supervisor Agents
- databricks-genie - Genie Spaces: create, curate, and query via Conversation API
- databricks-model-serving - Deploy MLflow models and AI agents to endpoints
- databricks-unstructured-pdf-generation - Generate synthetic PDFs for RAG
- databricks-vector-search - Vector similarity search for RAG and semantic search
📊 MLflow (from mlflow/skills)
- agent-evaluation - End-to-end agent evaluation workflow
- analyze-mlflow-chat-session - Debug multi-turn conversations
- analyze-mlflow-trace - Debug traces, spans, and assessments
- instrumenting-with-mlflow-tracing - Add MLflow tracing to Python/TypeScript
- mlflow-onboarding - MLflow setup guide for new users
- querying-mlflow-metrics - Aggregated metrics and time-series analysis
- retrieving-mlflow-traces - Trace search and filtering
- searching-mlflow-docs - Search MLflow documentation
- databricks-aibi-dashboards - Databricks AI/BI dashboards (with SQL validation workflow)
- databricks-unity-catalog - System tables for lineage, audit, billing
- databricks-iceberg - Apache Iceberg tables (Managed/Foreign), UniForm, Iceberg REST Catalog, Iceberg Clients Interoperability
- databricks-spark-declarative-pipelines - SDP (formerly DLT) in SQL/Python
- databricks-jobs - Multi-task workflows, triggers, schedules
- databricks-synthetic-data-gen - Realistic test data with Faker
- databricks-bundles - DABs for multi-environment deployments
- databricks-app-apx - Full-stack apps (FastAPI + React)
- databricks-app-python - Python web apps (Dash, Streamlit, Flask) with foundation model integration
- databricks-python-sdk - Python SDK, Connect, CLI, REST API
- databricks-config - Profile authentication setup
- databricks-lakebase-provisioned - Managed PostgreSQL for OLTP workloads
- databricks-docs - Documentation index via llms.txt
┌────────────────────────────────────────────────┐
│ .claude/skills/ + .claude/mcp.json │
│ (Knowledge) (Actions) │
│ │
│ Skills teach HOW + MCP does it │
│ ↓ ↓ │
│ Claude Code learns patterns and executes │
└────────────────────────────────────────────────┘
Example: User says "Create a sales dashboard"
- Claude loads
databricks-aibi-dashboardsskill → learns validation workflow - Calls
get_table_stats_and_schema()→ gets schemas - Calls
execute_sql()→ tests queries - Calls
manage_dashboard(action="create_or_update")→ deploys - Returns working dashboard URL
Create your own in .claude/skills/my-skill/SKILL.md:
---
name: my-skill
description: "What this teaches"
---
# My Skill
## When to Use
...
## Patterns
...Skills not loading? Check .claude/skills/ exists and each skill has SKILL.md
Install fails? Run bash install_skills.sh or check write permissions
- databricks-tools-core - Python library
- databricks-mcp-server - MCP server
- Databricks Docs - Official documentation
- MLflow Skills - Upstream MLflow skills repository