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.
62
73%
Does it follow best practices?
Impact
—
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 clear trigger terms and an explicit 'Use when' clause that makes it easy for Claude to select appropriately. Its main weakness is that the 'what' portion uses the vague term 'guidance' rather than listing specific concrete actions (e.g., configure clusters, submit jobs, manage notebooks). The distinctiveness is excellent due to the Databricks-specific terminology.
Suggestions
Replace 'development guidance' with specific concrete actions like 'configure clusters, submit jobs, query data, manage notebooks, authenticate connections' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Databricks development) and lists specific technologies (Python SDK, Databricks Connect, CLI, REST API), but describes the capability as 'guidance' rather than listing concrete actions like 'configure clusters, run jobs, query tables'. | 2 / 3 |
Completeness | Clearly answers both 'what' (Databricks development guidance including specific tools) and 'when' (explicit 'Use when working with databricks-sdk, databricks-connect, or Databricks APIs' clause). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms that users would actually type: 'databricks-sdk', 'databricks-connect', 'Databricks APIs', 'Python SDK', 'CLI', 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 trigger terms (databricks-sdk, databricks-connect, Databricks APIs) are highly distinctive and unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill excels at actionability with comprehensive, executable code examples covering the full Databricks SDK surface area. However, it suffers from being a monolithic reference document that tries to be both a quick-start guide and a complete API reference in a single file. The lack of progressive disclosure (no bundle files to offload detailed API sections) and missing validation workflows for long-running/destructive operations are its main weaknesses.
Suggestions
Split the detailed API reference sections (Clusters, Jobs, SQL, Catalog, Files, Serving, Vector Search, Pipelines, Secrets, DBUtils) into separate bundle files (e.g., `apis/clusters.md`, `apis/jobs.md`) and keep SKILL.md as a concise overview with links to each.
Add validation/verification steps for long-running operations — e.g., after creating a cluster, check its state; after running a job, verify the result state before proceeding; after file upload, confirm the file exists.
Remove the duplicate Quick Reference Links table since every API section already includes its documentation URL inline, or keep only the table and remove inline URLs to reduce redundancy.
Add a brief 'Common Errors & Recovery' section covering typical failure modes (token expiry, cluster timeout, warehouse not started) with concrete recovery steps.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is quite long (~400+ lines) and includes extensive API reference material that could be split into separate files. The quick reference links table at the end duplicates URLs already provided inline. However, the code examples themselves are lean and don't over-explain concepts Claude already knows. | 2 / 3 |
Actionability | Excellent executable code examples throughout — every API section includes copy-paste ready Python code with proper imports, method calls, and realistic parameters. The async pattern section is particularly well done with clear WRONG vs CORRECT examples. | 3 / 3 |
Workflow Clarity | The skill covers many APIs but lacks explicit multi-step workflows with validation checkpoints. The 'When Uncertain' section provides a reasonable lookup workflow, and the async section clearly sequences correct usage, but there are no validation/verification steps for operations like cluster creation, job execution, or file uploads that could fail. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of content — the entire API reference is inline in a single file with no bundle files to offload detailed sections. The related skills links at the bottom suggest a broader ecosystem exists, but the core content (~400+ lines of API examples) should be split into separate reference files with the SKILL.md serving as an overview. | 1 / 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
93cb4e3
- 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.