databricks-install-auth
Install and configure Databricks CLI and SDK authentication. Use when setting up a new Databricks integration, configuring tokens, or initializing Databricks in your project. Trigger with phrases like "install databricks", "setup databricks", "databricks auth", "configure databricks token", "databricks CLI".
80
77%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Risky
Do not use without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/saas-packs/databricks-pack/skills/databricks-install-auth/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 well-structured skill description that clearly communicates its purpose and includes explicit trigger guidance with natural user phrases. Its main weakness is that the capability listing could be more granular—specifying concrete actions beyond 'install and configure' would strengthen specificity. Overall, it performs well for skill selection purposes.
Suggestions
Add more specific concrete actions such as 'generate authentication tokens', 'configure .databrickscfg profiles', 'validate CLI connection' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Databricks CLI/SDK authentication) and some actions (install, configure, authentication), but doesn't list multiple concrete actions in detail—e.g., it doesn't specify steps like 'generate tokens', 'validate connection', 'set up profiles', etc. | 2 / 3 |
Completeness | Clearly answers both 'what' (install and configure Databricks CLI and SDK authentication) and 'when' (setting up new integration, configuring tokens, initializing Databricks) with explicit trigger phrases. | 3 / 3 |
Trigger Term Quality | Explicitly lists natural trigger phrases users would say: 'install databricks', 'setup databricks', 'databricks auth', 'configure databricks token', 'databricks CLI'. These cover common variations well. | 3 / 3 |
Distinctiveness Conflict Risk | Highly specific to Databricks CLI/SDK authentication setup, which is a clear niche unlikely to conflict with other skills. The trigger terms are all Databricks-specific. | 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, highly actionable skill with concrete executable examples covering multiple auth methods, profiles, and SDK usage. Its main weaknesses are moderate verbosity (some explanatory text Claude doesn't need) and a lack of inline validation/feedback loops in the workflow steps — the error table exists but is disconnected from the step-by-step flow. The content would benefit from being split into a concise overview with references to detailed files for advanced scenarios.
Suggestions
Add inline validation checkpoints within the workflow steps, e.g., after Step 2 auth configuration: 'Run `databricks current-user me` — if you see INVALID_TOKEN, regenerate the PAT and retry'
Move the error handling table, account-level client example, and Azure AD managed identity example into separate bundle files (e.g., TROUBLESHOOTING.md, EXAMPLES.md) and reference them from the main skill
Remove explanatory phrases Claude already knows (e.g., 'Uses client credentials flow. No browser required.', 'Opens browser for OAuth consent.') to improve token efficiency
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient with executable examples, but includes some unnecessary explanation (e.g., 'Opens browser for OAuth consent. Token auto-refreshes (1-hour lifetime)' and 'Uses client credentials flow. No browser required.') and could be tightened. The error handling table and multiple examples add length but most earn their place. Some comments in code are redundant for Claude. | 2 / 3 |
Actionability | Excellent actionability — every step has fully executable, copy-paste-ready bash commands and Python code. Environment variable names, config file formats, CLI commands, and SDK usage are all concrete and specific with realistic placeholder values. | 3 / 3 |
Workflow Clarity | Steps are clearly numbered and sequenced (install → configure → verify), and verification commands are included (e.g., `databricks current-user me`, SDK smoke test). However, there's no explicit feedback loop for error recovery — the error handling table is separate and disconnected from the workflow steps. For auth configuration which can easily fail, inline validation checkpoints with 'if this fails, do X' would improve clarity. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and sections, but it's a fairly long monolithic document (~150 lines of content). The error handling table, account-level client example, and Azure AD example could be split into separate reference files. The Resources section links to external docs which is good, but there are no bundle files to offload advanced content to. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Commit
3a2d27d
- 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.