Set up Databricks agent development environment. Use when: (1) First time setup, (2) Configuring Databricks authentication, (3) User says 'quickstart', 'set up', 'authenticate', or 'configure databricks', (4) No .env file exists.
65
77%
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 ./.claude/skills/quickstart/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 completeness, clearly specifying when Claude should select this skill. Its main weakness is that the 'what' portion is somewhat thin—it says 'set up' but doesn't enumerate the specific setup actions performed. Overall it would serve well in a multi-skill selection scenario.
Suggestions
Expand the capability description to list specific concrete actions, e.g., 'Creates .env file, installs dependencies, configures Databricks authentication tokens, and validates connection.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Databricks agent development environment) and the general action (set up), but doesn't list multiple concrete actions beyond setup—e.g., it doesn't specify what setup entails like installing packages, creating config files, or generating tokens. | 2 / 3 |
Completeness | Clearly answers both 'what' (set up Databricks agent development environment) and 'when' with an explicit 'Use when:' clause listing four specific trigger conditions including user phrases and contextual signals. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would actually say: 'quickstart', 'set up', 'authenticate', 'configure databricks', '.env file', and 'first time setup'. These cover common variations well. | 3 / 3 |
Distinctiveness Conflict Risk | Highly specific to Databricks agent development environment setup with distinct triggers like 'configure databricks', '.env file', and 'quickstart' in that context. Unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid quickstart/setup skill with strong actionability — concrete commands, multiple usage examples, and a clear fallback path. Its main weaknesses are the lack of explicit validation checkpoints after setup completion and moderate verbosity in some sections. The template placeholders ({{LAKEBASE_*}}) suggest dynamic content injection that could further bloat the file.
Suggestions
Add an explicit validation step after quickstart completes, e.g., 'Verify: check that .env exists and contains DATABRICKS_CONFIG_PROFILE, then run `databricks auth env` to confirm authentication works'.
Consider moving the Manual Authentication fallback and Existing App binding sections to separate referenced files to keep the main skill lean and focused on the happy path.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some unnecessary detail. The template placeholders ({{LAKEBASE_OPTIONS}}, etc.) add noise. The manual authentication fallback section is somewhat verbose with the full .env example, and some explanations like the idempotency section could be tighter. | 2 / 3 |
Actionability | Provides fully executable commands throughout — from checking CLI version, to running quickstart with various flags, to manual fallback with specific commands and a complete .env template. Examples cover interactive, non-interactive, and edge cases like binding to existing apps. | 3 / 3 |
Workflow Clarity | The overall flow is clear (prerequisites → quickstart → next steps) with a fallback path, but there are no explicit validation checkpoints after running quickstart. There's no 'verify quickstart succeeded' step, and the manual fallback doesn't include verification beyond 'databricks auth profiles'. For a setup/configuration workflow, a validation step confirming the environment is correctly configured would strengthen this. | 2 / 3 |
Progressive Disclosure | References to other skills (discover-tools, run-locally) in Next Steps are good, but the content is somewhat monolithic — the manual authentication fallback and existing app binding sections could potentially be separate references. The template placeholders suggest content expansion that could bloat the file. Without bundle files, the skill handles organization reasonably but not optimally. | 2 / 3 |
Total | 9 / 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.
1c88215
Table of Contents
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.