Name: cubejs
Rating: 56.8 (1 reviews)
Author: membranedev

cubejs

Cube.js integration. Manage data, records, and automate workflows. Use when the user wants to interact with Cube.js data.

Quality

65%

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/cubejs/SKILL.md

Quality

Content

67%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 concrete commands and a clear connection workflow including state-checkpoint polling. The main weaknesses are conceptual padding in the intro and minor invocation inconsistency.

Suggestions

Trim the opening overview paragraph that explains what Cube.js is, since Claude already knows this; lead directly with the integration setup.

Standardize on a single invocation form (either `membrane` after global install or `npx @membranehq/cli`) to avoid confusing copy-paste use.

Consider moving the proxy flags table and clientAction schema detail into a reference file to slim the overview and improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient command-driven content, but it opens with conceptual explanation Claude already knows ('Cube.js is an open-source analytics framework...') and includes padded prose ('This is the fastest way to get a connection. The URL is normalized...'), fitting the 'mostly efficient but includes some unnecessary explanation' anchor.	3 / 5
Actionability	Provides copy-paste-ready commands (install, login, connection ensure, action run) and a flags table, but has minor gaps: inconsistency between `membrane` and `npx @membranehq/cli` invocation and placeholder CONNECTION_ID values.	4 / 5
Workflow Clarity	Clear sequence from install through auth, connection, polling, and action execution, with state-based checkpoints (READY/BUILDING/CLIENT_ACTION_REQUIRED) and a re-poll feedback loop; not a fully explicit validate-fix-retry checklist, so it stops at 4.	4 / 5
Progressive Disclosure	Single, well-sectioned SKILL.md with clear headers and no problematic nested references; monolithic structure with inline proxy-flags table and clientAction schema detail prevents a 5.	4 / 5
	Total	15 / 20 Passed

Description

62%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 clearly identifies the Cube.js niche and provides an explicit 'Use when' trigger, satisfying the what/when requirement. It is held back by generic action verbs and limited trigger-term variation.

Suggestions

Replace generic verbs ('Manage data, records') with specific concrete actions (e.g., 'Query data, manage pre-aggregations, run SQL, and build dashboard APIs via Cube.js').

Broaden trigger terms to include natural phrasings users say, such as 'querying Cube.js data', 'building analytics dashboards', or 'working with Cube.js data models'.

Dimension	Reasoning	Score
Specificity	Names the Cube.js domain and a few actions ('Manage data, records, and automate workflows'), but the actions are generic rather than specific concrete operations, matching the 'names domain and 1-2 concrete actions, but not comprehensive' anchor.	3 / 5
Completeness	Both a 'what' ('Manage data, records, and automate workflows') and a 'when' ('Use when the user wants to interact with Cube.js data') are present; the 'when' is explicit but the 'what' is somewhat generic, fitting the 'has both, when could be more specific' anchor.	4 / 5
Trigger Term Quality	Includes the relevant keyword 'Cube.js' and the phrase 'interact with Cube.js data', but is missing natural variations a user might say such as 'query Cube.js' or 'build dashboards with Cube.js'.	3 / 5
Distinctiveness Conflict Risk	'Cube.js integration' is a clear, specific niche with minimal overlap risk; the generic 'manage data, records' phrasing prevents a 5.	4 / 5
	Total	14 / 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/cubejs/SKILL.md
Commit: f484c82

Reviewed: ~14 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.