Name: databricks
Rating: 55.2 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

databricks

Databricks integration. Manage Workspaces. Use when the user wants to interact with Databricks data.

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/databricks/SKILL.md

Quality

Content

68%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 with executable CLI commands and a clear connection-state workflow, but it is padded by an unnecessary Databricks explainer and a no-description action table, and it lacks validation steps around destructive action execution.

Suggestions

Remove or condense the introductory "Databricks is a unified data analytics platform..." paragraph and the all-"No description" Popular actions table to reclaim context budget.

Add an explicit validation/verification checkpoint before and after destructive or batch actions (e.g. get-job to confirm state before delete-job, and verify the resulting state after).

Move the bulk action catalog and the proxy flag reference into a separate reference file (e.g. ACTIONS.md) and link to it from the body to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The opening paragraph explains what Databricks is (which Claude already knows) and the 20-row "Popular actions" table reads "No description" for every row, adding bulk without value; the core CLI guidance is otherwise efficient.	3 / 5
Actionability	Concrete, copy-paste-ready commands cover the common path end-to-end — install/login, connection ensure, poll for READY, action list/run with --input JSON, and request proxying — plus a flag reference table.	5 / 5
Workflow Clarity	The connect→poll→handle-state→search→run sequence is clear with a polling feedback loop, but running destructive/batch actions (delete-job, create-job, update-git-repo) has no validation or verification checkpoint, which caps this dimension at 3.	3 / 5
Progressive Disclosure	Sections are well-organized and clearly signaled with no nested references, but the ~175-line body inlines bulk content (the action catalog and proxy flag reference) that could live in a separate reference file.	4 / 5
	Total	15 / 20 Passed

Description

57%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 third-person, names the domain, and includes an explicit Use-when clause, so it answers both what and when. Its weaknesses are a generic action verb ("Manage") and thin trigger vocabulary that omits concrete Databricks objects.

Suggestions

Replace the generic "Manage Workspaces" with concrete actions, e.g. "Start/stop clusters, run jobs, query SQL warehouses, and execute notebooks."

Expand the Use-when clause with natural trigger terms users actually say: clusters, jobs, notebooks, SQL warehouses, Spark, tables, and .dbc files.

Tighten the trigger to be more specific than "interact with Databricks data" to further reduce overlap with general data-analysis skills.

Dimension	Reasoning	Score
Specificity	"Manage Workspaces" names the domain but the only action is the generic verb "manage"; no concrete operations (start/stop clusters, run jobs, query tables) are listed in the description.	2 / 5
Completeness	Both a "what" ("Databricks integration. Manage Workspaces.") and an explicit "when" ("Use when the user wants to interact with Databricks data") are present, though the trigger phrase is generic rather than concrete.	4 / 5
Trigger Term Quality	"Databricks" and "Databricks data" are relevant terms, but common synonyms and concrete nouns users say (clusters, jobs, notebooks, SQL warehouses, Spark, tables) are missing.	3 / 5
Distinctiveness Conflict Risk	"Databricks" carves a clear, distinct niche with minimal overlap risk, but the broad trigger "interact with Databricks data" leaves minor ambiguity versus general data skills.	4 / 5
	Total	13 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: membranedev/application-skills
Path: skills/databricks/SKILL.md
Commit: f484c82

Reviewed: ~17 hours ago

Table of Contents

Discovery Implementation Validation

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.