databricks-model-serving
Deploy and query Databricks Model Serving endpoints. Use when (1) deploying MLflow models or AI agents to endpoints, (2) creating ChatAgent/ResponsesAgent agents, (3) integrating UC Functions or Vector Search tools, (4) querying deployed endpoints, (5) checking endpoint status. Covers classical ML models, custom pyfunc, and GenAI agents.
89
86%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
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 an excellent skill description that clearly defines its scope, provides explicit trigger conditions, and uses domain-specific terminology that makes it highly distinguishable. It follows the recommended pattern with a concise capability statement followed by a numbered 'Use when' list, and covers both the breadth of actions and the types of models/agents supported.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: deploying MLflow models, creating ChatAgent/ResponsesAgent agents, integrating UC Functions or Vector Search tools, querying deployed endpoints, and checking endpoint status. Also specifies coverage of classical ML models, custom pyfunc, and GenAI agents. | 3 / 3 |
Completeness | Clearly answers both 'what' (deploy and query Databricks Model Serving endpoints, covering classical ML, custom pyfunc, and GenAI agents) and 'when' with an explicit 'Use when' clause listing five specific trigger scenarios. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Databricks', 'Model Serving', 'endpoints', 'MLflow', 'ChatAgent', 'ResponsesAgent', 'UC Functions', 'Vector Search', 'deploy', 'query', 'pyfunc', 'GenAI agents'. These cover the domain-specific terms a user working with Databricks would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche around Databricks Model Serving endpoints specifically. The combination of Databricks-specific terminology (UC Functions, Vector Search, MLflow model serving) makes it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 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 with strong progressive disclosure and actionable guidance. Its main weaknesses are the oversized Foundation Model API table that inflates token usage (could be a separate reference file) and the lack of explicit validation/error-recovery steps in the deployment workflow. The content effectively serves as a hub document pointing to detailed references while providing enough quick-start material to be immediately useful.
Suggestions
Move the Foundation Model API endpoints table to a separate reference file (e.g., `0-foundation-models.md`) and keep only the Common Defaults section inline to improve conciseness.
Add explicit validation checkpoints to the GenAI Agent quick start workflow—e.g., after Step 4, specify expected success output and what to do if the test fails before proceeding to logging.
Remove the duplicated query examples in 'Common Workflows' section since they repeat what's already shown in the MCP Tools section.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is generally well-structured but includes significant verbosity, particularly the large Foundation Model API endpoint table (~40 rows) which could be in a separate reference file. Some sections like 'Common Workflows' duplicate examples already shown in the MCP Tools section. However, it avoids explaining basic concepts Claude already knows. | 2 / 3 |
Actionability | Provides concrete, executable code examples throughout—MCP tool calls with exact parameters, Python code for classical ML, specific endpoint names, and copy-paste ready query examples. The Critical ResponsesAgent Output Format section with WRONG vs CORRECT patterns is especially actionable. | 3 / 3 |
Workflow Clarity | The GenAI Agent quick start has a clear 7-step sequence, but lacks explicit validation checkpoints—Step 4 says 'Test Agent' without specifying what success looks like or what to do if it fails. Step 6 defers entirely to another file. The deployment workflow involves destructive/batch operations but has no validate-fix-retry feedback loop, which caps this at 2. | 2 / 3 |
Progressive Disclosure | Excellent progressive disclosure with a clear overview, decision table at the top, and well-signaled one-level-deep references to 9 topic-specific files. The Reference Files table clearly indicates when to read each file. Related skills are also well-linked. | 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
02aac8c
- 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.