deploy
Deploy agent to Databricks Apps using DAB (Databricks Asset Bundles). Use when: (1) User says 'deploy', 'push to databricks', or 'bundle deploy', (2) 'App already exists' error occurs, (3) Need to bind/unbind existing apps, (4) Debugging deployed apps, (5) Querying deployed app endpoints.
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 skill description that clearly defines its scope around Databricks Apps deployment using DAB. It excels at providing explicit trigger scenarios including user phrases, error conditions, and specific tasks. The description is concise yet comprehensive, covering both the 'what' and 'when' effectively with natural trigger terms.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: deploying agents, using DAB (Databricks Asset Bundles), binding/unbinding existing apps, debugging deployed apps, and querying deployed app endpoints. | 3 / 3 |
Completeness | Clearly answers both 'what' (deploy agent to Databricks Apps using DAB) and 'when' with an explicit 'Use when:' clause listing five specific trigger scenarios including user phrases, error conditions, and task types. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'deploy', 'push to databricks', 'bundle deploy', 'App already exists' error, 'bind/unbind', 'debugging deployed apps', 'querying deployed app endpoints'. Good coverage of both common terms and specific error scenarios. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: Databricks Apps deployment via DAB. The specific platform (Databricks), tool (DAB/Databricks Asset Bundles), and action (deploy agent) make 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, highly actionable deployment skill with excellent workflow clarity and concrete, executable commands throughout. Its main weakness is that it's somewhat long for a single SKILL.md — the FAQ and troubleshooting sections partially duplicate earlier content, and some detailed workflows could be split into referenced files. Overall, it provides exactly the kind of domain-specific, non-obvious knowledge that makes skills valuable.
Suggestions
Remove duplicate information between the main body and FAQ (e.g., OAuth vs PAT is covered in 'Query Deployed App' and again in the FAQ), or consolidate the FAQ into the troubleshooting table.
Consider splitting the 'Handling App Already Exists Error' bind workflow into a separate referenced file, as it's a detailed sub-procedure that adds significant length to the main skill.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient and covers necessary deployment-specific knowledge Claude wouldn't inherently know. However, some sections are slightly verbose — e.g., the 'Why this matters' callouts explain reasoning that could be trimmed, and the OBO section is thin enough to just be a link. The FAQ section repeats information already covered in the main body (e.g., OAuth vs PAT is mentioned twice). | 2 / 3 |
Actionability | The skill provides fully executable bash commands, concrete YAML configuration snippets, specific jq filters, and curl examples with exact payloads. Every step has copy-paste ready commands with clear parameters. The troubleshooting table maps specific errors to specific solutions. | 3 / 3 |
Workflow Clarity | The deploy workflow has a clear numbered sequence with a pre-flight check, validation step, deploy, and explicit run step. The 'App Already Exists' flow includes a decision point (ask user), then two clearly sequenced options with validation checkpoints. The bind workflow has 5 explicit steps with notes about when to skip steps. Error recovery is addressed throughout. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and logical sections, but it's quite long (~200 lines of substantive content) and could benefit from splitting detailed sections (like the bind workflow or querying guide) into separate files. References to other skills ('add-tools' skill, 'lakebase-setup' skill) and one external file are present but the main file carries a lot of inline detail. Without bundle files to confirm referenced paths, some references like `.claude/skills/add-tools/examples/lakebase-autoscaling.yaml` can't be verified. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- databricks/app-templates
- Commit
3f07ee7
- 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.