skills.rest
bcheng004
bcheng004COMMUNITY
Explore all skills by this author →
WebsiteGitHub

create-tools

Create Databricks tool resources including Genie spaces, Vector Search indexes, and Unity Catalog functions.

2|Updated Apr 6, 2026
Search Tags:#permissions#mcp#vector search#databricks#unity catalog#genie space#tool setup
One-click install
npx skills add https://github.com/bcheng004/agent-langgraph-advanced-workshop --skill create-tools-bcheng004
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: create-tools
Source: https://github.com/bcheng004/agent-langgraph-advanced-workshop/tree/main/.claude/skills/create-tools
Command: npx skills add https://github.com/bcheng004/agent-langgraph-advanced-workshop --skill create-tools-bcheng004

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It eliminates the manual, error-prone setup work required before an agent can use Databricks-backed tools like Genie, Vector Search, Unity Catalog functions, and UC connections.

Core Features & Use Cases

  • Guides resource creation: Covers Genie space, Vector Search index, UC function, UC connection, and local Python tools selection.
  • Fits into an end-to-end workflow: Emphasizes discovering existing resources first, then creating what’s missing, then wiring with permissions via the add-tools skill.
  • Prepares agent-ready tool endpoints: Produces the next-step knowledge needed to connect the created resources to your agent (including MCP URL patterns).

Quick Start

Ask the AI to create the Databricks tools you need by telling it what capability you want your agent to have (for example, “Create the vector search index resources my agent needs to search my document corpus”).

Frequently Asked Questions about create-tools

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I set up Databricks tool resources like Genie spaces and Vector Search indexes for an agent?▼

To set up Databricks tool resources, you can use a create-before-wire workflow that discovers existing resources first, then creates missing Genie spaces, Vector Search indexes, and Unity Catalog functions required for your agent.

What is the best way to prepare Databricks-backed tools before wiring them to an agent?▼

The best way to prepare Databricks-backed tools is following a discovery-first creation process that builds Genie spaces, Vector Search indexes, and local Python tools, producing the endpoint knowledge needed to connect resources to your agent.

Do I need existing Unity Catalog permissions to create tool resources for an agent?▼

You need proper Unity Catalog permissions to create tool resources, as the workflow aligns created resources with subsequent wiring steps using required permissions to ensure the agent can access Genie, Vector Search, and UC functions.

Can I create Unity Catalog HTTP connections for external MCP servers using this approach?▼

Yes, you can create Unity Catalog HTTP connections for external MCP servers, which aligns the resulting resources with subsequent deployment steps using the documented MCP URL patterns and required permissions.

Why does my agent deployment fail when Databricks tool resources do not exist yet?▼

Agent deployment fails when Databricks tool resources do not exist because tool-backed capabilities must be set up first; this workflow applies specifically when resources like Genie spaces or Vector Search indexes are missing before adding tools.

Related Skills

Explore More Software Engineering Skills→
sumitsaxena-gitsumitsaxena-git

add-tools

Add tools to a Databricks agent and grant permissions in databricks.yml.

Community
Intermediate
keqingli1129keqingli1129

create-tools

Create Databricks tool resources for agents to execute MCP-backed operations.

Community
Intermediate
AnanyaDBJAnanyaDBJ
6

create-tools

Automate creation of Databricks Genie spaces, vector search indexes, UC functions, and connections.

Community
Intermediate
victorlouvictorlou
4

create-tools

Create Databricks Genie spaces, Vector Search indexes, UC functions, and HTTP connections.

Community
Intermediate