databricks-python-sdk
Databricks development guidance including Python SDK, Databricks Connect, CLI, and REST API. Use when working with databricks-sdk, databricks-connect, or Databricks APIs.
75
70%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Risky
Do not use without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./databricks-skills/databricks-python-sdk/SKILL.mdQuality
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 solid skill description with excellent trigger terms and completeness, clearly specifying both what the skill does and when to use it. Its main weakness is that the 'what' portion uses the vague word 'guidance' rather than listing specific concrete actions the skill enables (e.g., authenticate, query, manage clusters, deploy jobs). Adding more specific actions would elevate the description further.
Suggestions
Replace 'development guidance' with specific concrete actions, e.g., 'Configures Databricks clusters, runs SQL queries, manages jobs and workflows, and authenticates via Python SDK, Databricks Connect, CLI, and REST API.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Databricks development) and lists specific technologies (Python SDK, Databricks Connect, CLI, REST API), but describes the skill as 'guidance' rather than listing concrete actions like 'configure clusters', 'run queries', or 'manage jobs'. | 2 / 3 |
Completeness | Clearly answers both 'what' (Databricks development guidance including Python SDK, Databricks Connect, CLI, and REST API) and 'when' (Use when working with databricks-sdk, databricks-connect, or Databricks APIs) with an explicit 'Use when...' clause. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms that users would actually type: 'databricks-sdk', 'databricks-connect', 'Databricks APIs', 'CLI', 'REST API', and 'Python SDK'. These cover the main variations a developer would use when seeking Databricks help. | 3 / 3 |
Distinctiveness Conflict Risk | Databricks is a very specific platform, and the trigger terms (databricks-sdk, databricks-connect, Databricks APIs) are highly distinctive and unlikely to conflict with other skills. The niche is clearly defined. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is highly actionable with excellent, executable code examples covering a wide range of Databricks SDK operations, and the async patterns section adds genuine value. However, it is far too verbose—essentially duplicating SDK documentation inline rather than providing a concise overview with references to detailed materials. The content would benefit significantly from splitting the API reference into separate files and keeping only the most critical patterns (auth, async, common gotchas) in the main SKILL.md.
Suggestions
Move the detailed API reference sections (Clusters, Jobs, SQL, Catalogs, Volumes, Files, Serving, Vector Search, Pipelines, Secrets, DBUtils) into a separate REFERENCE.md file and link to it from SKILL.md, keeping only 2-3 most common examples inline.
Remove the Quick Reference Links table since the URL pattern is already documented above it—the pattern itself is sufficient for Claude to construct any URL.
Add validation/error-handling checkpoints for destructive operations like cluster deletion, file removal, and secret management (e.g., confirm existence before delete, verify after creation).
Trim explanatory text that Claude already knows (e.g., 'Use databricks-connect for running Spark code locally against a Databricks cluster') and focus on non-obvious gotchas and project-specific conventions.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | This is extremely verbose at ~500+ lines. It essentially replicates SDK documentation that Claude could look up. The extensive API reference sections (Clusters, Jobs, SQL, Volumes, Files, Serving, Vector Search, Pipelines, Secrets, DBUtils) are largely redundant with what Claude already knows or could fetch from the linked docs. The quick reference links table duplicates the URL pattern already explained above it. | 1 / 3 |
Actionability | All code examples are concrete, executable, and copy-paste ready with proper imports. The examples cover real use cases with specific method signatures, parameters, and return value handling. The async pattern section is particularly well-done with correct/incorrect examples. | 3 / 3 |
Workflow Clarity | The skill covers individual API operations well but lacks validation checkpoints for multi-step workflows. For example, cluster creation shows waiting but doesn't address error recovery. The 'When Uncertain' section provides a good lookup workflow, but destructive operations (delete, rm) lack confirmation/validation steps. | 2 / 3 |
Progressive Disclosure | The skill links to related skills and external documentation, which is good. However, the massive inline API reference (Clusters, Jobs, SQL, Catalogs, Volumes, Files, Serving, Vector Search, Pipelines, Secrets, DBUtils) should be split into separate reference files. The SKILL.md should be an overview pointing to these details, not containing all of them. | 2 / 3 |
Total | 8 / 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 (626 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- databricks-solutions/ai-dev-kit
- Commit
02aac8c
- 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.