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

Blog Docs Log in Get started

magnetic

Magnetic integration. Manage Organizations. Use when the user wants to interact with Magnetic 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

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

63%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 delivers a highly actionable, well-sequenced guide to driving Magnetic through the Membrane CLI, with a clear connection state machine and feedback loop. Its main weaknesses are some marketing/boilerplate padding and the absence of any file-based progressive disclosure for reference detail.

Suggestions

Trim the intro marketing paragraph and phrases like 'so you can focus on the integration logic rather than auth plumbing' to tighten conciseness.

Add one fully worked example with real-ish values (a concrete actionId and input JSON) so the action-run path is copy-paste-runnable end to end.

Move the proxy flag table and the clientAction field spec into a referenced reference file (e.g. references/connection-states.md) and link to it from the body to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete commands, but the marketing-style intro paragraph ('Magnetic is a CRM and marketing automation platform designed to help small businesses...') and commentary like 'so you can focus on the integration logic rather than auth plumbing' are unnecessary padding that could be trimmed, matching the score-3 anchor.	3 / 5
Actionability	It provides concrete, copy-paste-ready commands for the full workflow (install, login, connection ensure, action list/run, request proxy) with a complete flag table, but the action-run examples rely on placeholders (CONNECTION_ID, <actionId>, QUERY) and lack a fully worked end-to-end example with real values, falling just short of 5.	4 / 5
Workflow Clarity	The install → authenticate → connect → poll-until-ready → search → run sequence is clear, with an explicit connection-state machine and a poll-after-user-action feedback loop; the 'skip to Step 2' references are a minor gap since no 'Step 2' header is actually labeled, keeping it below 5.	4 / 5
Progressive Disclosure	No bundle files exist and all content is inlined in a single ~145-line document; the section structure is reasonable, but reference-style material (the proxy flag table and the detailed clientAction spec) is inlined rather than split into one-level-deep referenced files, matching the score-3 anchor.	3 / 5
	Total	14 / 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 is competent — it states what the skill does and includes an explicit Use-when trigger — but it is thin on concrete actions and natural trigger phrases. It reads more as a label than a rich, disambiguating capability statement.

Suggestions

Replace the single 'Manage Organizations' with several specific actions (e.g., 'search and update leads, manage contacts, trigger email campaigns, pull engagement reports') to lift specificity toward 5.

Expand the trigger clause with natural user phrases and synonyms, e.g. 'Use when the user wants to query Magnetic leads, update contacts, run marketing campaigns, or interact with Magnetic CRM data.'

Add file/extension or API hints where relevant to improve distinctiveness against generic CRM skills.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Magnetic integration') and one concrete action ('Manage Organizations'), but offers only a single action rather than the several specific actions the score-4 anchor requires.	3 / 5
Completeness	It provides a 'what' ('Manage Organizations') and an explicit 'Use when the user wants to interact with Magnetic data' trigger, satisfying both halves; the 'when' clause is present but could be more specific, matching the score-4 anchor rather than the concrete-trigger-phrases bar of 5.	4 / 5
Trigger Term Quality	It includes the product name 'Magnetic' and the entity 'Organizations', but the trigger phrasing 'interact with Magnetic data' is generic and misses common synonyms or natural variations a user would say.	3 / 5
Distinctiveness Conflict Risk	Tied to the named Magnetic product it occupies a clear niche with minimal conflict risk, though 'Manage Organizations' is a generic entity that could lightly overlap with related org-management skills, keeping it just below 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/magnetic/SKILL.md
Commit: f484c82

Reviewed: 6 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.