Name: databricks-model-serving
Rating: 68.8 (1 reviews)
Author: databricks

databricks-model-serving

Databricks Model Serving (ops) plus MLflow model development (dev): manage serving endpoints, train and register models to Unity Catalog with @prod aliases, batch-score via spark_udf, build custom PyFunc / ResponsesAgent models, and discover Foundation Model API endpoints.

Quality

83%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

85%

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, well-structured skill that provides actionable CLI commands with concrete examples, clear multi-step workflows with validation checkpoints, and excellent progressive disclosure to reference files. The main weakness is minor verbosity — some sections repeat guidance (CLI discovery advice) and the endpoint structure diagram, while useful, adds tokens that could be trimmed. Overall it's a high-quality skill that effectively balances comprehensiveness with navigability.

Dimension	Reasoning	Score
Conciseness	Generally efficient but has some redundancy — the CLI discovery section repeats the same advice twice (run -h before constructing commands), and some explanatory text (e.g., endpoint structure diagram, endpoint types table) could be tightened. However, it mostly avoids explaining concepts Claude already knows.	2 / 3
Actionability	Provides fully executable CLI commands with concrete JSON payloads, specific flags, and copy-paste ready examples for create, query, get, and app integration. The commands table and troubleshooting table give specific, actionable guidance for each scenario.	3 / 3
Workflow Clarity	Multi-step processes are clearly sequenced with explicit validation checkpoints — notably the create → poll for readiness → query flow with specific state checks (state.ready == 'READY' AND state.config_update == 'NOT_UPDATING'), and the app integration flow with step-by-step fallback logic. The troubleshooting table provides error recovery guidance.	3 / 3
Progressive Disclosure	Excellent structure with a clear overview in the main file and well-signaled one-level-deep references to training-and-serving.md, custom-pyfunc.md, and genai-agents.md, each with a concise description of when to read them. The reference table at the bottom clearly delineates ops vs dev concerns.	3 / 3
	Total	11 / 12 Passed

Description

82%

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 with excellent specificity and distinctive terminology that clearly carves out its niche in the Databricks/MLflow ecosystem. Its main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill over others. The technical trigger terms are well-chosen and naturally match what users working in this domain would say.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Databricks model serving, MLflow model registration, deploying models to Unity Catalog, or batch inference with spark_udf.'

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: manage serving endpoints, train and register models to Unity Catalog with @prod aliases, batch-score via spark_udf, build custom PyFunc/ResponsesAgent models, and discover Foundation Model API endpoints.	3 / 3
Completeness	The 'what' is thoroughly covered with specific capabilities, but there is no explicit 'Use when...' clause or equivalent trigger guidance telling Claude when to select this skill. Per rubric guidelines, this caps completeness at 2.	2 / 3
Trigger Term Quality	Includes strong natural keywords users would say: 'Databricks', 'Model Serving', 'MLflow', 'Unity Catalog', 'spark_udf', 'PyFunc', 'ResponsesAgent', 'Foundation Model API', 'serving endpoints', 'batch-score'. These cover both high-level concepts and specific technical terms users would naturally use.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive with a clear niche combining Databricks Model Serving and MLflow development. The specific mentions of Unity Catalog, spark_udf, PyFunc, ResponsesAgent, and Foundation Model API make it very unlikely to conflict with other skills.	3 / 3
	Total	11 / 12 Passed

Validation

90%

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 — 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: ea6452e

Reviewed: 2 days 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.