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.
67
81%
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 an excellent skill description that clearly defines a narrow, specific task with concrete technical details. It includes an explicit 'Use when' clause with three well-defined trigger conditions, uses natural technical keywords that users would actually search for, and occupies a very distinct niche that minimizes conflict risk with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: migrating an MLflow ResponsesAgent, converting from Model Serving to Apps, converting predict()/predict_stream() methods to @invoke/@stream decorators. These are highly specific technical operations. | 3 / 3 |
Completeness | Clearly answers both 'what' (migrate an MLflow ResponsesAgent from Model Serving to Apps) and 'when' with an explicit 'Use when:' clause listing three specific trigger conditions. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'MLflow', 'ResponsesAgent', 'Databricks Model Serving', 'Databricks Apps', 'predict()', 'predict_stream()', '@invoke', '@stream', 'migrate'. These are the exact terms a user working on this task would use. | 3 / 3 |
Distinctiveness Conflict Risk | Extremely specific niche combining MLflow, ResponsesAgent, Databricks Model Serving, and Databricks Apps migration. This is unlikely to conflict with any other skill due to the highly specialized domain and precise trigger terms. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is highly actionable with excellent workflow clarity — every step has concrete commands, clear sequencing, and validation checkpoints. However, it is significantly over-verbose, explaining concepts Claude already knows, repeating reminders excessively, and inlining reference material that should be in separate files. The content would benefit greatly from aggressive trimming (likely 40-50% reduction possible) and splitting reference patterns into separate files.
Suggestions
Cut explanatory text Claude already knows: remove descriptions of what async/await does, what virtual environments are, basic curl usage patterns, and what PDF/MLmodel files contain. Focus only on the specific transformation rules.
Extract the 'Common Migration Patterns' and 'Resource Type Mapping' reference tables into separate files (e.g., PATTERNS.md, RESOURCES.md) and link to them from the main skill.
Remove repeated reminders (e.g., '--profile <profile>' instruction appears 5+ times; 'uv.lock must be committed' stated twice) — state each instruction once at first use.
Consolidate the task list creation section — the detailed TaskCreate table and Ctrl+T tip add ~20 lines that are operational overhead, not migration guidance. A single sentence referencing task tracking would suffice.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~600+ lines. It explains concepts Claude already knows (what async/await is, what virtual environments are, basic curl usage), repeats the same information multiple times (e.g., '--profile <profile>' reminder appears 5+ times, uv.lock importance stated twice), and includes extensive scaffolding like task list creation instructions and troubleshooting for basic auth that pad the content significantly. | 1 / 3 |
Actionability | The skill provides fully executable commands throughout — concrete bash commands with proper flags, complete Python code blocks for downloading artifacts, specific curl commands for testing, and real databricks.yml configuration examples. Code is copy-paste ready with clear placeholder conventions (<app-name>, <profile>). | 3 / 3 |
Workflow Clarity | The multi-step migration process is clearly sequenced (Steps 1-6) with explicit validation checkpoints: authenticate before proceeding, verify downloaded artifacts, test locally before deploying, verify deployment with curl. The checklist in 5.5 and the 'Only proceed to Step 6 after confirming' gate are good feedback loops. Task tracking adds additional progress visibility. | 3 / 3 |
Progressive Disclosure | The content is largely monolithic — all migration patterns, troubleshooting, reference tables, and detailed examples are inline in a single massive file. The Reference sections at the bottom could be split into separate files. There are vague references to a 'deploy skill' for troubleshooting but no clear file references. Without bundle files, the scaffold structure is described but not linked to actual navigable files. | 2 / 3 |
Total | 9 / 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 |
|---|---|---|
skill_md_line_count | SKILL.md is long (968 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- databricks/app-templates
- Commit
1c88215
- 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.