CtrlK
BlogDocsLog inGet started
Tessl Logo

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".

72

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

80%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-organized body with executable code throughout and lean prose. Its weaknesses are the absence of explicit validation/verification checkpoints for batch operations and the lack of progressive disclosure via split reference files.

Suggestions

Add explicit verification steps after batch/governance changes, e.g. re-query system.billing.usage or confirm the cluster policy/auto-termination was applied before moving on, to add a validate→fix→retry feedback loop.

Split the detailed SQL queries, the cost-savings checklist, and the error-handling table into reference files (e.g. QUERIES.md, CHECKLIST.md) referenced one level deep from SKILL.md to improve progressive disclosure.

Move the time-sensitive DBU pricing figures into a dedicated, clearly-labeled reference section or file so drift is isolated from the core instructions.

DimensionReasoningScore

Conciseness

The body is dense and code-heavy with minimal conceptual padding; prose is limited to brief, useful guidance. The DBU pricing figures are time-sensitive but provide genuinely useful domain data, not fluff.

3 / 3

Actionability

Packed with executable SQL against system.billing tables, Python SDK calls (cluster_policies, instance_pools, warehouses.list), and bash pipelines that are copy-paste ready rather than pseudocode.

3 / 3

Workflow Clarity

Steps are clearly sequenced (1 through 6) with some decision logic and an error-handling table, but batch/governance operations (applying policies to groups, bulk-editing cluster auto-termination) lack explicit verification checkpoints, capping the score per the rubric.

2 / 3

Progressive Disclosure

Well-organized into sections, but all content is inline in a single ~230-line file with no bundle reference files for deeper material; only external Databricks doc links are provided, and the under-50-line exemption does not apply.

2 / 3

Total

10

/

12

Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A well-constructed description that concretely states capabilities, includes natural trigger phrases, and explicitly answers both what and when in a clear niche. Third-person voice is maintained with no notable verbosity.

DimensionReasoningScore

Specificity

Names multiple concrete mechanisms — "cluster policies, spot instances, and monitoring" — matching the anchor for listing several specific concrete actions rather than just a domain.

3 / 3

Completeness

Clearly states what it does (optimize costs via policies/spot/monitoring) and when to use it, with an explicit "Use when..." clause plus enumerated trigger phrases.

3 / 3

Trigger Term Quality

Provides five natural phrases a user would actually say ("databricks cost", "reduce databricks spend", "databricks billing", "databricks cost optimization", "cluster cost"), giving good coverage.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear Databricks-cost niche with Databricks-specific triggers; "cluster cost" is slightly generic but the overall niche is unmistakable and unlikely to trigger the wrong skill.

3 / 3

Total

12

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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

14

/

16

Passed

Repository
jeremylongshore/claude-code-plugins-plus-skills
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.