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.
72
66%
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 description with excellent trigger terms and clear 'when' guidance targeting a distinct technology niche. Its main weakness is that the 'what' portion uses the vague word 'guidance' instead of listing concrete actions the skill enables (e.g., configuring clusters, running notebooks, managing jobs). Adding specific actions would make it more informative for skill selection.
Suggestions
Replace 'development guidance' with specific concrete actions, e.g., 'Configures Databricks clusters, runs notebooks, manages jobs, and queries data using 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' (explicit 'Use when working with databricks-sdk, databricks-connect, or Databricks APIs'). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms that users would actually type: 'databricks-sdk', 'databricks-connect', 'Databricks APIs', 'CLI', 'Python SDK', and 'REST API'. These cover the main ways users would reference Databricks development work. | 3 / 3 |
Distinctiveness Conflict Risk | Databricks is a very specific platform, and the description names specific packages (databricks-sdk, databricks-connect) that create a clear niche unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill excels at actionability with excellent, executable code examples covering a wide range of Databricks SDK operations. However, it is far too verbose—essentially serving as a full API reference document rather than a concise skill guide. The content desperately needs progressive disclosure, splitting the detailed API examples into separate reference files while keeping SKILL.md as a lean overview with navigation pointers.
Suggestions
Extract the detailed API reference sections (Clusters, Jobs, SQL, Volumes, Files, Serving, Vector Search, Pipelines, Secrets, DBUtils) into a separate REFERENCE.md or individual per-service files, keeping only the most essential patterns (auth, Databricks Connect, async, error handling) in SKILL.md.
Remove the Quick Reference Links table since the same URLs are already provided inline next to each API section—or keep only the table and remove inline URLs.
Add validation/verification steps for destructive or long-running operations, e.g., confirming cluster state after creation, verifying file upload success, or checking job run output for errors.
Consolidate content that overlaps with related skills (databricks-unity-catalog, databricks-model-serving, databricks-vector-search) by replacing those sections with cross-references rather than duplicating the material.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | This is extremely verbose at ~400+ lines. It includes extensive API reference material (Clusters, Jobs, SQL, Volumes, Files, Serving, Vector Search, Pipelines, Secrets, DBUtils) that essentially duplicates SDK documentation. The quick reference links table at the end repeats the same URLs already provided inline. Much of this could be offloaded to separate reference files or simply linked to the official docs. | 1 / 3 |
Actionability | All code examples are concrete, executable, and copy-paste ready with proper imports. The examples cover real patterns including authentication variants, async wrapping, error handling, pagination, and long-running operations with specific method signatures and parameters. | 3 / 3 |
Workflow Clarity | The async pattern section clearly shows wrong vs. correct approaches, and the wait patterns are well-sequenced. However, there are no validation checkpoints for potentially destructive operations (e.g., cluster creation, secret management, file uploads) and no error recovery workflows beyond a basic try/except example. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of content with no separation of concerns. The entire API reference for 15+ services is inlined rather than split into separate files. The 'Related Skills' section at the end suggests a modular structure exists, but this file doesn't leverage it—it duplicates content that likely belongs in those related skills (e.g., serving endpoints, vector search, Unity Catalog). | 1 / 3 |
Total | 7 / 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
b4071a0
- 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.