Tessl • The management layer for AI agent skills

SkillPublic

cardinal

Cardinal integration. Manage Organizations, Pipelines, Users, Goals, Filters. Use when the user wants to interact with Cardinal data.

Quality

70%

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

61%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.

A largely executable, well-structured integration guide whose main weaknesses are a padded marketing intro, no validation/verification steps around destructive actions, and no concrete worked example of running an action with parameters. Progressive disclosure is fine for a single-file skill of this size, though the action catalog could move to a reference file.

Suggestions

Delete the marketing-style opening paragraph ("Cardinal is a project management and collaboration tool... improve team communication") and the filler sentence "Use action names and parameters as needed.".

Add validation checkpoints before destructive operations, e.g., run get-feature and confirm with the user before delete-feature, and verify the connection works after membrane connect.

Include one concrete end-to-end example running a real action with --input (e.g., membrane action run --connectionId=... list-features --input "{ \"limit\": 10 }") to replace the generic ACTION_ID placeholder.

Move the full action catalog to a references/ file and keep a short "most common actions" list inline.

Dimension	Reasoning	Score
Conciseness	The bulk is lean commands and tables, but the marketing-style intro ("helps streamline workflows and improve team communication... typically used by project managers") and filler like "Use action names and parameters as needed" are unnecessary padding.	3 / 5
Actionability	Copy-paste-ready commands throughout (install, login with headless fallback, connect with JSON path extraction, proxy flag table), but there is no worked example running a real action key with --input, only generic ACTION_ID placeholders.	4 / 5
Workflow Clarity	The install → login → connect → discover → run sequence is clear, but there are no validation checkpoints, and the skill exposes destructive actions (delete-feature), which the rubric caps at 3.	3 / 5
Progressive Disclosure	No bundle files exist and the single-file body is well-sectioned and navigable; the 17-row action catalog is arguably reference material that could be split out, a minor organization gap.	4 / 5
	Total	14 / 20 Passed

Description

67%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 answers both what and when with a distinct product name, but leans on the generic verb "Manage" and offers only the product name as a trigger term. Its entity list also diverges from the actions the body actually documents. Voice is correctly third person.

Suggestions

Use more concrete, varied verbs per entity (e.g., "Create and update features and contacts, list companies, submit feedback") to match the actions the skill actually exposes.

Expand the "Use when..." clause with natural trigger phrases such as "projects, tasks, product backlog, feedback" to improve trigger-term coverage.

Add synonyms or context words users might say instead of relying solely on the product name "Cardinal".

Dimension	Reasoning	Score
Specificity	"Manage Organizations, Pipelines, Users, Goals, Filters" lists several concrete objects, but the single generic verb "Manage" and a mismatch with the body's actual action set (contacts, companies, feedback, features) leave minor gaps in coverage.	4 / 5
Completeness	Both a "what" ("Manage Organizations, Pipelines, Users, Goals, Filters") and an explicit "Use when the user wants to interact with Cardinal data" clause are present, but the "when" is generic and could name concrete trigger phrases.	4 / 5
Trigger Term Quality	The only natural triggers are the product name "Cardinal" and "Cardinal data"; common variations a user would say (projects, tasks, contacts, backlog, features) are missing.	3 / 5
Distinctiveness Conflict Risk	The distinct product name "Cardinal" gives a clear niche, though the generic entity words (Organizations, Users, Goals) pose minor overlap risk with other project-management or CRM skills.	4 / 5
	Total	15 / 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
Revision: f484c82

Reviewed: 16 days ago

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.

cardinal

Table of Contents

Is this your skill?