databricks-core
Databricks CLI operations: auth, profiles, data exploration, and bundles. Contains up-to-date guidelines for Databricks-related CLI tasks.
76
70%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/databricks-core/SKILL.mdQuality
Discovery
40%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description identifies a clear niche (Databricks CLI) and lists high-level capability areas, making it distinctive. However, it lacks concrete action verbs, misses some natural trigger terms, and critically omits any explicit 'Use when...' guidance, which weakens its ability to be reliably selected from a large skill set.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Databricks CLI commands, authentication setup, workspace configuration, bundle deployment, or data exploration via Databricks.'
Replace category labels with concrete actions, e.g., 'Configure Databricks authentication and profiles, explore catalog/schema/table data, deploy and manage Databricks Asset Bundles (DABs).'
Include additional natural trigger terms users might say, such as 'DABs', 'databricks workspace', 'dbx', 'databricks deploy', 'databricks jobs', or 'databricks token'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Databricks CLI) and lists some action areas (auth, profiles, data exploration, bundles), but these are categories rather than concrete actions. It doesn't specify what exactly is done within each area (e.g., 'configure authentication tokens', 'deploy bundles', 'query tables'). | 2 / 3 |
Completeness | It describes what the skill covers (Databricks CLI operations) but has no explicit 'Use when...' clause or equivalent trigger guidance. The 'when' is entirely missing, which per the rubric should cap completeness at 2, and since the 'what' is also somewhat vague, this scores a 1. | 1 / 3 |
Trigger Term Quality | Includes relevant keywords like 'Databricks', 'CLI', 'auth', 'profiles', 'bundles', and 'data exploration', which users might naturally say. However, it misses common variations like 'databricks-cli', 'dbx', 'workspace', 'deploy', 'jobs', or 'DABs' that users might use. | 2 / 3 |
Distinctiveness Conflict Risk | Databricks CLI is a clear, specific niche that is unlikely to conflict with other skills. The mention of 'Databricks' combined with 'CLI' and specific sub-areas like 'bundles' and 'profiles' makes this distinctly identifiable. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent skill file that serves as a well-organized hub for Databricks CLI operations. It excels at conciseness while packing in critical gotchas (positional arguments, shell session isolation) that would otherwise cause failures. The progressive disclosure is exemplary, with clear pointers to product-specific skills and reference guides without duplicating their content.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient throughout. It assumes Claude's competence, avoids explaining what Databricks is or how CLI tools work in general, and every section delivers actionable information without padding. The anti-pattern examples with ❌/✅ annotations are valuable and not verbose. | 3 / 3 |
Actionability | Provides fully executable, copy-paste-ready CLI commands with correct syntax. Critically highlights positional vs flag arguments with concrete correct/incorrect examples, includes troubleshooting table with specific error messages and solutions, and shows the shell session gotcha with working vs non-working patterns. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced: check CLI version → authenticate → select profile → execute commands. The prerequisites section has explicit stop conditions ('STOP. Do not proceed'), the profile selection section has a clear numbered sequence, and the shell session behavior is explicitly documented with a validation-like checkpoint (the CRITICAL note about separate sessions). | 3 / 3 |
Progressive Disclosure | Excellent progressive disclosure structure. The SKILL.md serves as a clear overview hub, pointing to dedicated product skills (databricks-jobs, databricks-pipelines, etc.) and reference files (CLI Installation, CLI Authentication, Data Exploration) with well-signaled one-level-deep references. The 'Required Reading by Task' table is an especially effective navigation aid. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- databricks/databricks-agent-skills
- Commit
f1c9cf7
- 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.