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.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Risky

Do not use without reviewing

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A thorough, highly actionable API reference with strong executable examples, weakened by its monolithic single-file structure and minor redundancy between its link tables.

Suggestions

Move the per-API code references (Clusters, Jobs, SQL, Catalog, etc.) into a bundled reference file (e.g. references/api_reference.md) and keep SKILL.md as a concise overview with one-level-deep links, improving progressive_disclosure.

Consolidate the "Workspace API Categories" table and "Quick Reference Links" table, which duplicate much of the same URL information, to improve conciseness.

Add explicit validation or verification checkpoints around destructive/batch operations (e.g. verify a cluster is stopped before delete, confirm job run state) to lift workflow_clarity.

Dimension	Reasoning	Score
Conciseness	The code blocks are lean and assume competence, but the two URL tables ("Workspace API Categories" and "Quick Reference Links") overlap and the "When Uncertain" section repeats the already-stated URL pattern, so it could be tightened.	2 / 3
Actionability	Nearly every section ships executable, copy-paste-ready code with concrete method calls and parameters, matching the fully-executable level-3 anchor.	3 / 3
Workflow Clarity	Useful patterns exist (async wrapping with wrong/correct examples, wait/polling options), but destructive and batch operations like cluster delete lack explicit validation or verification checkpoints, capping this at 2.	2 / 3
Progressive Disclosure	Well-organized into sections, but ~620 lines of API reference live inline in SKILL.md with no bundle files split out, matching the level-2 example of API reference that should be in a separate file.	2 / 3
	Total	9 / 12 Passed

Description

90%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A focused, well-constructed description with explicit trigger guidance and specific package names; the only weakness is that it names tools rather than concrete actions, slightly limiting specificity.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete tools ("Python SDK, Databricks Connect, CLI, and REST API"), but "development guidance" is abstract rather than listing concrete actions, so it falls short of the level-3 anchor.	2 / 3
Completeness	Explicitly states what it does ("Databricks development guidance including...") and when to use it ("Use when working with databricks-sdk, databricks-connect, or Databricks APIs."), satisfying both what and when.	3 / 3
Trigger Term Quality	Includes natural package-name triggers a user would actually say ("databricks-sdk", "databricks-connect", "Databricks APIs"), giving good coverage of likely phrasings.	3 / 3
Distinctiveness Conflict Risk	The Databricks niche and specific package-name triggers make it unlikely to fire for unrelated skills, matching the clear-niche level-3 anchor.	3 / 3
	Total	11 / 12 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 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
relative_links	Relative link issues: 7 suspicious	Warning

	Total	14 / 16 Passed

Repository: databricks-solutions/ai-dev-kit
Commit: 1c43c21

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.