databricks-deploy-integration
Deploy Databricks jobs and pipelines with Declarative Automation Bundles. Use when deploying jobs to different environments, managing deployments, or setting up deployment automation. Trigger with phrases like "databricks deploy", "asset bundles", "databricks deployment", "deploy to production", "bundle deploy".
85
83%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%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-structured skill description that clearly identifies its niche (Databricks deployment with bundles), provides explicit trigger phrases, and answers both what and when. The main weakness is that the specificity of concrete actions could be expanded beyond just 'deploy jobs and pipelines' to include more granular capabilities like environment configuration or bundle validation.
Suggestions
Add more specific concrete actions beyond deploying, such as 'configure environment-specific settings, validate bundle configurations, promote bundles across stages' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Databricks) and some actions (deploy jobs and pipelines, Declarative Automation Bundles), but doesn't list multiple concrete actions beyond deploying. It could specify more granular capabilities like configuring environments, managing bundle configurations, or rollback. | 2 / 3 |
Completeness | Clearly answers both 'what' (deploy Databricks jobs and pipelines with Declarative Automation Bundles) and 'when' (deploying jobs to different environments, managing deployments, setting up deployment automation), with explicit trigger phrases listed. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'databricks deploy', 'asset bundles', 'databricks deployment', 'deploy to production', 'bundle deploy'. These cover common variations a user would naturally say when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with the Databricks + deployment + bundles niche. The specific trigger terms like 'databricks deploy', 'asset bundles', and 'bundle deploy' are unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 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 skill with excellent workflow clarity and realistic, executable examples covering the full Databricks bundle deployment lifecycle. Its main weakness is length — the comprehensive YAML examples and inline resource definitions make it token-heavy, and the content could benefit from splitting detailed resource configurations into separate reference files. The error handling table and promotion workflow are particularly well done.
Suggestions
Move the detailed resources/jobs.yml and resources/pipelines.yml examples into separate bundle reference files, keeping only a minimal example inline with pointers to the full configs.
Remove the 'Output' section which merely restates what the skill already demonstrates through its examples.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient with good YAML/bash examples, but includes some unnecessary sections like the 'Output' summary which restates what was already shown, and the 'Overview' paragraph explains what bundles are which Claude likely knows. The error handling table and examples are useful but the overall document is quite long (~180 lines) and could be tightened. | 2 / 3 |
Actionability | Excellent actionability with fully executable bash commands, complete YAML configurations, and copy-paste ready examples. The databricks.yml, resources/jobs.yml, and CLI commands are all concrete and specific with realistic values and proper syntax. | 3 / 3 |
Workflow Clarity | Clear 6-step sequential workflow with explicit validation checkpoints (validate before deploy, test staging before promoting to prod). Step 5 includes a proper feedback loop: validate → deploy → run → check result state → then promote. The destroy command is properly flagged as dev-only with warnings about production mode protection. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and logical sections, but it's a monolithic document with ~180 lines of inline content. The resources YAML examples (jobs.yml, pipelines.yml) could be split into separate reference files. External links are provided but no bundle files exist to offload detailed configurations. The 'Next Steps' reference to 'databricks-multi-env-setup' is good but the main content is heavy. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Commit
3a2d27d
- 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.