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.
83
78%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./databricks-skills/databricks-agent-bricks/SKILL.mdQuality
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 three specific agent types within the Databricks ecosystem and provides an explicit 'Use when' clause. The main weakness is that trigger term coverage could be broader — users might search for related concepts like 'RAG', 'chatbot', or 'document search' that aren't mentioned. The use of acronyms (KA, MAS) without broader natural language synonyms slightly limits discoverability.
Suggestions
Add more natural user-facing trigger terms such as 'RAG', 'chatbot', 'document search', 'data exploration', or 'agent workflow' to improve discoverability when users describe their needs in everyday language.
| 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 Databricks 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 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
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-organized skill that effectively documents three types of Agent Bricks with clear tool specifications and good cross-referencing to related skills. Its main weaknesses are some generic best practices that don't add value for Claude and a workflow section that lacks validation/error-recovery steps for the provisioning process. The multi-modal supervisor agent example is a strong concrete reference.
Suggestions
Remove or condense the 'Best Practices' section—items like 'use meaningful names' and 'provide descriptions' are generic advice Claude doesn't need.
Add explicit validation steps to the workflow: e.g., poll with get action to check endpoint_status, and specify what to do if status remains PROVISIONING or goes OFFLINE.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some unnecessary verbosity, such as the 'Best Practices' section with generic advice ('Use meaningful names', 'Provide descriptions') that Claude already knows. The prerequisites section also repeats cross-references extensively. | 2 / 3 |
Actionability | The skill provides concrete tool names, exact parameter specifications, action types with required/optional fields clearly marked, and a fully executable multi-agent example with realistic parameters. The MCP tool documentation is specific and copy-paste ready. | 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 or how to verify the endpoint is actually working before proceeding. | 2 / 3 |
Progressive Disclosure | Content is well-structured with a clear overview table, tool reference sections, and appropriate delegation to related skills (databricks-genie, detailed pattern files). References are one level deep and clearly signaled with both inline links and a 'See Also' section. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
100%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
b4071a0
- Reviewed
Table of Contents
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.