CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

databricks-execution-compute

Execute code and manage compute on Databricks: run Python/Scala/SQL/R via serverless, classic, or interactive clusters, and create/resize/delete clusters and SQL warehouses.

63

Quality

79%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/databricks/claude/skills/databricks-execution-compute/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

80%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 highly actionable and well-structured with excellent progressive disclosure, delegating per-mode detail to clearly linked reference files. Its main weakness is workflow clarity around destructive operations, which lack explicit validation or confirmation checkpoints.

Suggestions

Add an explicit validation/confirmation step before irreversible destructive commands (e.g. 'Before permanent-delete or warehouses delete, confirm the resource ID with the user and verify it is not in use via clusters get / warehouses get').

Add a feedback loop for the Serverless Job flow's FAILED/CANCELED outcome (e.g. on FAILED, fetch get-run-output error_trace, surface it, and retry only after fixing the notebook).

Tighten the CLI Command Map by linking to the relevant section instead of restating the full serverless upload/submit/wait flow inline.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence—no concept over-explanation—with useful gotchas earning their tokens, though the CLI Command Map partially restates the Serverless Job section and could be tightened slightly.

4 / 5

Actionability

Copy-paste-ready commands throughout: a complete submit.json, exact workspace import/jobs submit/get-run/get-run-output invocations, and full SQL warehouse create/edit JSON, with specific gotchas called out (client:4 required, task run_id vs parent run_id).

5 / 5

Workflow Clarity

The Serverless Job flow is clearly numbered with lifecycle polling as a validation checkpoint, but destructive irreversible operations ('permanent-delete', 'warehouses delete') appear without any validation or confirmation step, which per the rubric caps workflow clarity at 3.

3 / 5

Progressive Disclosure

A clear overview and decision matrix in SKILL.md point to three real, one-level-deep reference files (1-databricks-connect.md, 2-serverless-job.md, 3-interactive-cluster.md) that are well-signaled with links and a ⭐ marker, with content appropriately split and easy to navigate.

5 / 5

Total

17

/

20

Passed

Description

71%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 and capability-rich with strong trigger terms, but it omits any explicit 'when to use' guidance, which limits its completeness. It is mostly distinct though it shares surface area with several sibling Databricks skills.

Suggestions

Append a 'Use when...' clause naming concrete triggers, e.g. 'Use when running code on Databricks, managing clusters or SQL warehouses, or when the user mentions Databricks, PySpark, serverless jobs, or interactive clusters.'

Add common natural synonyms to the trigger terms such as 'Spark/PySpark', 'notebooks', and 'jobs' so the description matches phrasings users actually say.

Clarify the boundary against sibling skills (e.g. note that DABs-based jobs belong to databricks-dabs) to reduce conflict risk.

DimensionReasoningScore

Specificity

Lists multiple concrete actions—'run Python/Scala/SQL/R', 'create/resize/delete clusters', and 'SQL warehouses'—covering both execution and compute management comprehensively, matching the anchor for comprehensive concrete actions.

5 / 5

Completeness

The 'what' is explicit and clear, but there is no 'Use when...' clause or equivalent trigger guidance, which per the judging guidelines caps completeness at 3 even though the capability description is thorough.

3 / 5

Trigger Term Quality

Strong natural keywords ('Databricks', 'Python/Scala/SQL/R', 'clusters', 'SQL warehouses', 'serverless') but misses common variations users might say such as 'Spark/PySpark', 'notebooks', or 'jobs', so it sits just below comprehensive coverage.

4 / 5

Distinctiveness Conflict Risk

The Databricks execution/compute niche is mostly distinct, but overlap risk exists with closely related sibling skills (databricks-jobs, databricks-dbsql, databricks-dabs), several of which the body itself defers to.

4 / 5

Total

16

/

20

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.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 3 suspicious

Warning

Total

14

/

16

Passed

Repository

databricks/databricks-agent-skills

Path

plugins/databricks/claude/skills/databricks-execution-compute/SKILL.md

Revision

c570f88

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill