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

cardinal

Cardinal integration. Manage Organizations, Pipelines, Users, Goals, Filters. Use when the user wants to interact with Cardinal 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/cardinal/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 concrete, executable CLI commands and a clear connection-to-execution sequence, but it carries some generic introductory padding and lacks validation checkpoints around its destructive operations.

Suggestions

Add explicit validation checkpoints before destructive/batch actions, e.g. verify the target entity with a get-* call and confirm with the user before running delete-feature or update-* actions.

Trim the generic opening paragraph about what Cardinal is and remove the filler line 'Use action names and parameters as needed.' to improve token efficiency.

Consider moving the Popular actions table into a separate references file (e.g. ACTIONS.md) with a one-line pointer from SKILL.md to deepen progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient command-driven guidance, but the opening 'Cardinal is a project management and collaboration tool used by teams to organize tasks, track progress, and manage resources...' and the filler line 'Use action names and parameters as needed.' are unnecessary explanation that could be trimmed, matching the 'mostly efficient but includes some unnecessary explanation' anchor.	3 / 5
Actionability	Copy-paste-ready executable commands cover the common cases throughout — 'npm install -g @membranehq/cli', 'membrane search cardinal --elementType=connector --json', 'membrane action run --connectionId=CONNECTION_ID ACTION_ID --json', plus specific JSON paths like 'output.items[0].element?.id' and a concrete --input example, matching the fully executable anchor.	5 / 5
Workflow Clarity	A clear install→login→connect→discover→run sequence is present as numbered steps, but the skill exposes destructive and batch operations (e.g. 'Delete Feature', 'Update Feature', 'Update Company') with no explicit validation or verification checkpoints before or after them, which caps workflow clarity at 3 per the destructive-operation rule.	3 / 5
Progressive Disclosure	The body is well-organized with clearly labeled sections (## Working with Cardinal, ### Connecting to Cardinal, ## Popular actions, ### Proxy requests, ## Best practices) and no nested references, but the sizable Popular actions table is bulk inline content that could reasonably live in a separate reference file, leaving it just below the cleanly-split anchor.	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 cleanly answers both what and when and ties to a specific product niche, but it relies on a single generic action verb and offers limited natural trigger variations beyond the product name.

Suggestions

Replace the single generic verb 'Manage' with several distinct concrete actions (e.g., 'Create and update Pipelines, assign Users to Goals, apply Filters') to lift specificity.

Broaden the 'when' trigger with concrete natural phrases users would say, e.g. 'Use when the user wants to manage Cardinal projects, pipelines, goals, or team members.'

Add a disambiguating qualifier to 'Cardinal' to reduce conflict risk with other products sharing the name.

Dimension	Reasoning	Score
Specificity	Quotes 'Manage Organizations, Pipelines, Users, Goals, Filters' list five concrete entity types, but the single generic verb 'Manage' is the only action rather than multiple distinct concrete actions, matching the anchor that names the domain with limited action coverage.	3 / 5
Completeness	Both parts are present: 'Cardinal integration. Manage Organizations, Pipelines, Users, Goals, Filters' answers what, and 'Use when the user wants to interact with Cardinal data' answers when, though the 'when' clause is somewhat generic rather than listing concrete trigger phrases, matching the 'has both what and when; when could be more explicit' anchor.	4 / 5
Trigger Term Quality	The phrase 'Use when the user wants to interact with Cardinal data' names the product 'Cardinal' as a keyword, but offers no synonyms or natural variations a user might say, fitting the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	'Cardinal integration' tied to a specific named product with its own entity types is mostly distinct with minimal overlap risk, though 'Cardinal' is a common English word that could ambiguously match other contexts, placing it just below the clear-niche anchor.	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/cardinal/SKILL.md
Commit: f484c82

Reviewed: 4 days 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.