databricks-core
Databricks CLI operations: auth, profiles, data exploration, and bundles. Contains up-to-date guidelines for Databricks-related CLI tasks.
60
70%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
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, giving it good distinctiveness. However, it lacks concrete action verbs describing what the skill actually does within each area, and critically omits any explicit trigger guidance ('Use when...') that would help Claude know when to select this skill. The phrase 'Contains up-to-date guidelines' is filler that doesn't aid skill selection.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Databricks CLI commands, configuring Databricks authentication, deploying Databricks bundles, or exploring Databricks data from the terminal.'
Replace high-level category names with concrete actions, e.g., 'Configure Databricks authentication and profiles, explore workspace data (tables, schemas, catalogs), and deploy/manage Databricks Asset Bundles via CLI.'
Remove the vague phrase 'Contains up-to-date guidelines for Databricks-related CLI tasks' and replace with specific trigger terms users might say, such as 'databricks configure', 'bundle deploy', 'databricks workspace', or 'list catalogs'.
| 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 falls to 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', 'databricks connect', or specific commands users might reference. | 2 / 3 |
Distinctiveness Conflict Risk | Databricks CLI is a very specific niche tool, making this unlikely to conflict with other skills. The mention of 'Databricks' combined with 'CLI', 'bundles', and 'profiles' creates a distinct identity that wouldn't easily overlap with general data or CLI skills. | 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 concise, well-structured hub for Databricks CLI operations. Its greatest strengths are the highly actionable command examples with explicit anti-patterns showing common mistakes, the clear prerequisite workflow with decision points, and the well-organized progressive disclosure to specialized reference files. The content respects Claude's intelligence throughout while adding genuine value with CLI-specific gotchas like positional arguments and shell session isolation.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient throughout. It avoids explaining what Databricks is, what CLI tools are, or other concepts Claude already knows. Every section delivers actionable information without padding, and the anti-patterns section (showing wrong commands) earns its tokens by preventing common errors. | 3 / 3 |
Actionability | The skill provides fully executable, copy-paste-ready CLI commands with correct syntax, including positional vs flag argument distinctions. The explicit wrong-command examples with explanations of what to use instead are highly actionable and prevent real failure modes. | 3 / 3 |
Workflow Clarity | The prerequisites section establishes a clear sequence (check CLI → authenticate → select profile) with explicit decision points and fallback paths (e.g., sandboxed environments falling back to REST API). The profile selection workflow has explicit steps, and the troubleshooting table provides clear error-recovery guidance. The Claude Code section clearly explains shell session isolation with working vs non-working examples. | 3 / 3 |
Progressive Disclosure | The skill serves as a well-organized hub, with concise overview content inline and clear one-level-deep references to dedicated skill files (databricks-cli-install.md, databricks-cli-auth.md, data-exploration.md) and product-specific skills. The 'Required Reading by Task' table provides excellent navigation, and the structure makes it easy to find the right reference for any task. | 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
caf71f1
- 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.