Name: create-tools
Rating: 71.2 (1 reviews)
Author: databricks

create-tools

Create Databricks resources that agents connect to as tools. Use when: (1) User needs to create a Genie space, vector search index, UC function, or UC connection, (2) User says 'create tool', 'set up genie', 'create vector search', 'register MCP server', (3) Before add-tools when the resource doesn't exist yet, (4) User asks 'what do I need to create before adding this tool'.

Quality

86%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a well-structured routing/overview skill that efficiently directs users to the right resource guide. Its main strength is the clear decision table and progressive disclosure pattern. Its weakness is the lack of any concrete, executable guidance within the skill itself — it functions purely as a navigation hub, which limits actionability, and the workflow omits validation steps.

Suggestions

Add a brief validation step in the workflow (e.g., 'Verify the resource exists: `uv run discover-tools | grep <resource-name>`') to confirm creation before proceeding to add-tools.

Include at least one minimal concrete example inline (e.g., a quick UC function creation snippet) so the skill provides some immediately actionable content rather than deferring everything to external files.

Dimension	Reasoning	Score
Conciseness	The content is lean and efficient. Every line serves a purpose — the table maps intent to resource type, the workflow is minimal, and there's no unnecessary explanation of what Databricks or these resources are.	3 / 3
Actionability	The skill provides a clear decision table and references to detailed guides, but contains no executable code, commands (beyond `uv run discover-tools`), or concrete examples of how to actually create any of the resources. It relies entirely on external files for the actionable content.	2 / 3
Workflow Clarity	The 4-step workflow is clearly sequenced and logically ordered, but lacks validation checkpoints — there's no step to verify the resource was created successfully before proceeding to add-tools, which matters for a multi-step process involving resource creation.	2 / 3
Progressive Disclosure	Excellent progressive disclosure structure: a concise overview table with one-level-deep references to specific guides for each resource type, plus clear cross-references to related skills (discover-tools, add-tools, deploy). Navigation is intuitive and well-signaled.	3 / 3
	Total	10 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is a strong skill description that clearly defines its scope (creating Databricks resources), provides explicit trigger terms and scenarios, and distinguishes itself from related skills like 'add-tools'. It uses proper third-person voice and covers both what the skill does and when to use it comprehensively.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: create Genie space, vector search index, UC function, UC connection, and register MCP server. These are clearly defined, concrete resources rather than vague abstractions.	3 / 3
Completeness	Clearly answers both 'what' (create Databricks resources that agents connect to as tools) and 'when' with an explicit 'Use when:' clause containing four distinct trigger scenarios, including relationship to other skills ('Before add-tools when the resource doesn't exist yet').	3 / 3
Trigger Term Quality	Includes natural keywords users would say: 'create tool', 'set up genie', 'create vector search', 'register MCP server', plus specific resource names like 'Genie space', 'vector search index', 'UC function', 'UC connection'. Good coverage of natural terms.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive with Databricks-specific resource types (Genie space, UC function, UC connection, vector search index) and clear differentiation from a related 'add-tools' skill. The niche is well-defined and unlikely to conflict with other skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: databricks/app-templates
Commit: 2302cd3

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.