databricks-model-serving
Manage Databricks Model Serving endpoints via CLI. Use when asked to create, configure, query, or manage model serving endpoints for LLM inference, custom models, or external models.
72
88%
Does it follow best practices?
Impact
—
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 a strong, well-crafted description that clearly identifies the tool (Databricks), the domain (Model Serving endpoints), the interface (CLI), and specific actions (create, configure, query, manage). It includes an explicit 'Use when' clause with relevant trigger terms covering multiple model types. The description is concise, specific, and distinctive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'create, configure, query, or manage model serving endpoints' and specifies the domain clearly (Databricks Model Serving via CLI). | 3 / 3 |
Completeness | Clearly answers both 'what' (manage Databricks Model Serving endpoints via CLI) and 'when' (Use when asked to create, configure, query, or manage model serving endpoints for LLM inference, custom models, or external models) with an explicit 'Use when' clause. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Databricks', 'Model Serving', 'endpoints', 'CLI', 'LLM inference', 'custom models', 'external models', 'create', 'configure', 'query'. Good coverage of terms a user working with Databricks serving would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — targets a specific platform (Databricks), a specific feature (Model Serving endpoints), and a specific interface (CLI). Unlikely to conflict with generic model deployment or other cloud platform skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, actionable skill with clear workflows, executable examples, and good structural organization. Its main weakness is moderate verbosity in places—some explanatory prose and repeated CLI discovery reminders could be trimmed. The app integration section, while useful, adds significant length that could be offloaded to a referenced file.
Suggestions
Reduce repetition of the 'run -h first' guidance—state it once prominently in the CLI Discovery section and reference it briefly elsewhere instead of restating it.
Consider moving the 'Integrate with a Databricks App' section to a separate reference file to keep the main skill focused on serving endpoint management.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient and well-structured, but some sections include explanations Claude would already know (e.g., explaining what Model Serving is, what traffic config does). The endpoint structure diagram and type table are useful but the prose around them could be tighter. The repeated 'run -h first' instruction appears multiple times. | 2 / 3 |
Actionability | Provides fully executable CLI commands with concrete JSON payloads for create, query, and integration workflows. Commands are copy-paste ready with clear placeholders. The OpenAPI discovery step and the app integration YAML examples are specific and actionable. | 3 / 3 |
Workflow Clarity | Multi-step processes are clearly sequenced with explicit validation checkpoints: create → poll state.ready, query → check schema first via get-open-api, app integration has clear Step 1/Step 2 with conditional branching. The troubleshooting table provides error recovery guidance. The 'ALWAYS Do This First' CLI discovery pattern establishes a clear pre-step. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear sections and a reference table for less-common commands. However, with no bundle files, the reference to '../databricks-apps/references/appkit/model-serving.md' and the parent 'databricks-core' skill cannot be verified. The 'Other Commands' table is a good compression technique, but the app integration section is fairly lengthy and could potentially be split into a separate reference file. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- databricks/devhub
- Commit
0b6297e
- 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.