Name: migrate-from-model-serving
Rating: 72 (1 reviews)
Author: databricks

migrate-from-model-serving

Migrate an MLflow ResponsesAgent from Databricks Model Serving to Databricks Apps. Use when: (1) User wants to migrate from Model Serving to Apps, (2) User has a ResponsesAgent with predict()/predict_stream() methods, (3) User wants to convert to @invoke/@stream decorators.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with a clearly sequenced, validated workflow, but it is weighed down by repetition and a monolithic structure that would benefit from trimming redundant notes and offloading reference material into separate files.

Suggestions

Remove the duplicated reminders (the uv.lock-must-commit note appears three times; the --profile reminder repeats) and trim obvious-context notes like 'This helps the user follow along' to tighten conciseness.

Split the Reference sections (Common Migration Patterns, Useful Resources, and the detailed MLmodel→databricks.yml resource mapping) into separate one-level-deep reference files linked from the main body, to improve progressive disclosure.

Consolidate the two deliverables/file-structure tree explanations (the Overview tree and the Reference: App File Structure tree) into a single authoritative location to reduce redundancy.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete commands and code, but carries redundant padding: the uv.lock-must-commit reminder repeats three times, the --profile reminder recurs, and several notes restate obvious context ("This helps the user follow along", "This helps catch configuration issues early") that could be trimmed without losing clarity.	2 / 3
Actionability	Provides fully executable bash/uv commands, complete Python blocks with real imports, copy-paste-ready curl test payloads, and a concrete MLmodel→databricks.yml resource-mapping table — matching the copy-paste-ready anchor.	3 / 3
Workflow Clarity	A clear six-step sequence with task-status checkpoints at each step, explicit validation (`databricks bundle validate` before deploy), a pre-deploy verification checklist (5.5), and feedback loops (re-authenticate on auth error, fix imports after copy) — matching the explicit-validation/checklist anchor.	3 / 3
Progressive Disclosure	The skill is a single ~960-line monolithic SKILL.md with no bundle files in references/scripts/assets; content that could be offloaded (the migration pattern catalog, full troubleshooting, and the detailed resource-mapping reference) is inline rather than split into clearly signaled one-level-deep reference files, though internal section organization is good.	2 / 3
	Total	10 / 12 Passed

Description

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.

The description is specific, complete, and distinctive: it names the exact source/target artifacts, provides explicit "Use when" triggers, and occupies a clear niche unlikely to conflict with other skills. It is concise and avoids fluff.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions and objects — "Migrate an MLflow ResponsesAgent from Databricks Model Serving to Databricks Apps", "predict()/predict_stream() methods", "convert to @invoke/@stream decorators" — matching the highest anchor that lists several specific concrete actions.	3 / 3
Completeness	Explicitly answers both what (migrate an MLflow ResponsesAgent from Model Serving to Apps) and when, via the "Use when:" clause with three numbered trigger conditions — matching the anchor requiring explicit triggers for both.	3 / 3
Trigger Term Quality	Covers natural terms a user would say — "migrate from Model Serving to Apps", "ResponsesAgent", "predict()/predict_stream()", "convert to @invoke/@stream" — giving good coverage of the domain vocabulary rather than generic jargon.	3 / 3
Distinctiveness Conflict Risk	Targets a narrow, well-defined niche (ResponsesAgent Model Serving→Apps migration) with distinct triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (968 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: databricks/app-templates
Commit: 2a4c792

Reviewed: 5 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.