databricks-agent-bricks

Create and manage Databricks Agent Bricks: Knowledge Assistants (KA) for document Q&A, Genie Spaces for SQL exploration, and Supervisor Agents (MAS) for multi-agent orchestration. Use when building conversational AI applications on Databricks.

Quality

75%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./databricks-skills/databricks-agent-bricks/SKILL.md

Quality

Discovery

85%

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 description that clearly identifies the specific capabilities (three types of Databricks Agent Bricks) and includes an explicit 'Use when' clause. The main weakness is that trigger terms could be broader to capture more natural user language variations beyond Databricks-specific terminology.

Suggestions

Expand trigger terms to include natural user phrases like 'RAG', 'chatbot', 'document search', 'agent framework', or 'Unity Catalog' that users might say when they need this skill.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'Create and manage Databricks Agent Bricks', with three distinct types enumerated — Knowledge Assistants for document Q&A, Genie Spaces for SQL exploration, and Supervisor Agents for multi-agent orchestration.	3 / 3
Completeness	Clearly answers both 'what' (create and manage three types of Agent Bricks with specific purposes) and 'when' ('Use when building conversational AI applications on Databricks'), providing an explicit trigger clause.	3 / 3
Trigger Term Quality	Includes some relevant keywords like 'Databricks', 'Agent Bricks', 'Knowledge Assistants', 'Genie Spaces', 'SQL exploration', 'multi-agent orchestration', and 'conversational AI'. However, it misses common user-facing variations like 'chatbot', 'RAG', 'document search', 'agent framework', or abbreviations users might naturally use.	2 / 3
Distinctiveness Conflict Risk	Highly distinctive due to the specific Databricks platform context and the named agent types (Knowledge Assistants, Genie Spaces, Supervisor Agents). Unlikely to conflict with generic AI or chatbot skills.	3 / 3
	Total	11 / 12 Passed

Implementation

64%

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

This is a solid reference skill for Databricks Agent Bricks with good actionability through concrete tool specifications and a comprehensive multi-agent example. Its main weaknesses are the lack of validation/error-handling steps in the workflow and some verbosity in parameter documentation that could be offloaded to reference files. The skill would benefit from explicit polling/verification steps after brick creation and tighter inline content with more delegation to bundle files.

Suggestions

Add explicit validation checkpoints to the workflow: after creating a brick, include a step to poll status with manage_ka(action='get') or manage_mas(action='get') and handle failure cases (e.g., if status stays PROVISIONING or goes OFFLINE).

Move detailed parameter documentation for each tool into separate reference files (e.g., 1-knowledge-assistants.md) and keep only essential parameters and a quick example in SKILL.md to reduce inline verbosity.

Remove the generic best practices section (items like 'Use meaningful names' and 'Provide descriptions') as these are obvious to Claude and don't add actionable value.

Dimension	Reasoning	Score
Conciseness	The skill is reasonably efficient but includes some unnecessary verbosity, particularly in the detailed parameter listings for each tool action and the best practices section which contains generic advice ('Use meaningful names', 'Provide descriptions') that Claude already knows. The overview table and structure are good, but the content could be tightened.	2 / 3
Actionability	The skill provides concrete, executable guidance with specific tool calls, parameter names, exact action strings, and a complete multi-agent example with real Python-style invocation. The MCP tool interfaces are fully specified with required/optional parameters and return values clearly documented.	3 / 3
Workflow Clarity	The workflow is sequenced (generate data → create brick → wait for provisioning → add examples) but lacks explicit validation checkpoints. There's no guidance on what to do if provisioning fails, no verification step after creation, and no feedback loop for error recovery. The provisioning status is mentioned but there's no instruction to poll/check status.	2 / 3
Progressive Disclosure	The skill references several related skills and supplementary files (1-knowledge-assistants.md, 2-supervisor-agents.md) but no bundle files were provided to verify these exist. The SKILL.md itself is quite long with detailed parameter documentation inline that could be split into reference files. The 'See Also' section references files that should contain the detailed patterns, but the main file still contains substantial detail.	2 / 3
	Total	9 / 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-solutions/ai-dev-kit
Commit: 93cb4e3

Reviewed: 1 day 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.