CtrlK
BlogDocsLog inGet started
Tessl Logo

databricks-ai-runtime

Databricks AI Runtime (`air`) CLI — the command-line tool for submitting and managing GPU training workloads on Databricks serverless compute. Use for: running `air` workloads, custom Docker image setup, environment configuration, and troubleshooting `air` jobs.

68

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

78%Weight 40%Scale 1-5

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

The body is concise and actionable for the core workload-submission path, with good progressive-disclosure intent. The main weakness is the missing referenced file and the lack of inline guidance for the custom Docker workflow.

Suggestions

Add the referenced `docker-images.md` to the bundle (or correct the reference path) so the progressive-disclosure pointer resolves.

Include a brief inline sequence (e.g. build image -> `air register image` -> run with image) with a validation checkpoint for the custom Docker workflow before deferring to the reference.

Add one short verification note after the `air run` command (e.g. how to check workload status/output) to strengthen the primary workflow's feedback loop.

DimensionReasoningScore

Conciseness

Lean body with an executable YAML example and command; assumes Claude's competence and adds no padding or basic-concept explanations.

5 / 5

Actionability

The main workload path is copy-paste ready (workload YAML + `air run` command), but the custom Docker path offers only a pointer with no inline executable steps.

4 / 5

Workflow Clarity

The primary single-step flow is unambiguous, but the multi-step Docker workflow's sequence and validation are not surfaced even briefly, deferring entirely to the referenced file.

4 / 5

Progressive Disclosure

The body is well-structured with a clearly signaled one-level reference, but the referenced `docker-images.md` is not present in the bundle, so the reference does not resolve.

3 / 5

Total

16

/

20

Passed

Description

87%Weight 40%Scale 1-5

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 is specific, well-triggered, and complete, clearly answering both what the tool does and when to use it. It is slightly short of comprehensive action/trigger enumeration.

DimensionReasoningScore

Specificity

Lists several concrete actions (submitting/managing GPU training workloads, custom Docker image setup, environment configuration, troubleshooting) but does not comprehensively enumerate the breadth of `air` subcommands.

4 / 5

Completeness

Clearly states what the CLI does and gives an explicit 'Use for:' clause with concrete trigger phrases for when to invoke it.

5 / 5

Trigger Term Quality

Strong natural keyword coverage (GPU training workloads, air workloads, custom Docker image, environment configuration, troubleshooting) with a few synonyms/extensions missing.

4 / 5

Distinctiveness Conflict Risk

Narrow, specific niche (air CLI for GPU workloads on Databricks serverless) with distinct triggers and minimal overlap risk.

5 / 5

Total

18

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
databricks/databricks-agent-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.