databricks-cost-tuning
Optimize Databricks costs with cluster policies, spot instances, and monitoring. Use when reducing cloud spend, implementing cost controls, or analyzing Databricks usage costs. Trigger with phrases like "databricks cost", "reduce databricks spend", "databricks billing", "databricks cost optimization", "cluster cost".
80
77%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/saas-packs/databricks-pack/skills/databricks-cost-tuning/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 with strong trigger term coverage and clear completeness. The explicit 'Use when' and 'Trigger with phrases' sections make it easy for Claude to select appropriately. The main weakness is that the capability actions could be more specific and concrete rather than listing broad categories like 'cluster policies' and 'monitoring'.
Suggestions
Expand the specificity of actions, e.g., 'Configure autoscaling policies, set up spot instance fallback strategies, analyze cluster utilization metrics, set billing alerts' instead of the broader categories.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Databricks costs) and some actions (cluster policies, spot instances, monitoring), but these are more like categories than concrete specific actions. It doesn't list detailed operations like 'configure autoscaling policies' or 'set up billing alerts'. | 2 / 3 |
Completeness | Clearly answers both 'what' (optimize Databricks costs with cluster policies, spot instances, and monitoring) and 'when' (explicit 'Use when' clause with triggers, plus a 'Trigger with phrases' section listing specific user phrases). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'databricks cost', 'reduce databricks spend', 'databricks billing', 'databricks cost optimization', 'cluster cost', plus broader terms like 'reducing cloud spend' and 'cost controls'. These are terms users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: Databricks cost optimization specifically. The trigger terms are specific to Databricks billing and cluster costs, making it unlikely to conflict with general cloud cost or other Databricks 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, highly actionable skill with excellent executable code examples covering the full spectrum of Databricks cost optimization. Its main weaknesses are the lack of validation/verification steps after implementing changes (e.g., confirming policy enforcement, measuring actual savings) and the monolithic structure that could benefit from splitting detailed configurations into separate reference files. Some minor verbosity in explanatory text could be trimmed.
Suggestions
Add validation checkpoints after key steps — e.g., after creating a cluster policy, show how to verify it's enforced; after enabling spot instances, show how to confirm spot usage in billing data.
Split detailed configurations (instance pools, spot config, SQL warehouse tuning) into separate reference files and keep SKILL.md as a concise overview with links.
Remove explanatory sentences Claude already knows (e.g., 'Cluster policies restrict what users can configure, preventing runaway costs') and let the code speak for itself.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with executable code and useful SQL queries, but includes some unnecessary explanations Claude would already know (e.g., explaining what cluster policies do, what spot instances are, DBU pricing context). The overview section with pricing details is useful reference data, but some inline comments are redundant. | 2 / 3 |
Actionability | Excellent actionability throughout — every step includes fully executable SQL queries, Python SDK code, or bash commands that are copy-paste ready. The SQL for cost analysis, Python for cluster policies and instance pools, and bash for auto-termination are all concrete and complete. | 3 / 3 |
Workflow Clarity | Steps are clearly sequenced from diagnosis (Step 1) through remediation (Steps 2-6), but there are no explicit validation checkpoints or feedback loops. After creating cluster policies or configuring spot instances, there's no 'verify the policy is applied' or 'confirm savings after implementation' step. For operations affecting cloud spend and cluster configurations, validation steps would be important. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and a logical flow, but at ~180 lines it's quite long for a single SKILL.md. The SQL warehouse right-sizing, instance pools, and spot instance configurations could each be separate reference files. The Resources section provides external links but no bundle files exist for deeper content. | 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.