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
Advisory
Suggest reviewing before use
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 well-crafted skill description that clearly identifies the domain (Databricks Model Serving), the interface (CLI), specific actions (create, configure, query, manage), and explicit trigger conditions. It uses proper third-person voice and includes natural keywords that users would employ when needing this skill. The description is concise yet comprehensive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'create, configure, query, or manage model serving endpoints' and specifies the domain clearly as Databricks Model Serving via CLI. | 3 / 3 |
Completeness | Clearly answers both 'what' (manage Databricks Model Serving endpoints via CLI) and 'when' (explicit 'Use when asked to create, configure, query, or manage model serving endpoints for LLM inference, custom models, or external models'). | 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 variations. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: Databricks Model Serving endpoints via CLI. The combination of Databricks, model serving, and CLI makes it very unlikely to conflict with other 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 executable CLI commands, clear workflow sequencing with validation checkpoints, and a useful troubleshooting table. Its main weakness is moderate verbosity — some repeated guidance about running help commands and explanatory text that could be trimmed — and the lack of bundle files to offload detailed content like the app integration pattern or the full create JSON spec.
Suggestions
Consolidate the repeated 'run -h first' guidance into a single prominent note rather than restating it in multiple sections.
Consider extracting the 'Integrate with a Databricks App' section into a separate reference file to keep the main skill focused on serving endpoint management.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but has some unnecessary verbosity — e.g., the endpoint types table explains 'when to use' which Claude can infer, the repeated reminders to run `-h` are somewhat redundant after the first mention, and some instructions like 'Do NOT list endpoints before creating' and 'Do NOT guess command syntax' could be more concise. However, most content earns its place. | 2 / 3 |
Actionability | Provides fully executable CLI commands with concrete JSON payloads for create, query, and other operations. The examples are copy-paste ready with clear placeholders, and the troubleshooting table maps specific errors to specific solutions. | 3 / 3 |
Workflow Clarity | Multi-step processes are clearly sequenced with explicit validation checkpoints — the create workflow includes polling for readiness with specific state checks (state.ready == 'READY' AND state.config_update == 'NOT_UPDATING'), and the app integration section has a clear two-step conditional flow. The troubleshooting section provides error recovery guidance. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and tables, but it's fairly long for a single file with no bundle files to offload detail into. The app integration section and detailed JSON examples could potentially be split into reference files. The one external reference (model-serving.md) is well-signaled, but there are no bundle files provided to support progressive disclosure. | 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/databricks-agent-skills
- Commit
caf71f1
- 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.