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

curated

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

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/curated/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 content is a strong, executable integration guide with a real polling feedback loop and a concrete command catalog. Its main weakness is conciseness: a marketing-style intro and internal-mechanics asides add tokens Claude does not need, and an end-to-end worked example with a real action input would lift actionability.

Suggestions

Cut the marketing intro and internals asides (e.g. the 'bloggers, content creators, and businesses' sentence and the 'fastest way... connector is built automatically' explanation); lead with what Claude must do.

Add one end-to-end worked example tying an action key to a real command, e.g. `membrane action run list-email-subscribers --connectionId=CONN --input '{"publicationId": "123"}' --json`, so the run path is concrete instead of a placeholder.

Consider moving the Popular actions and proxy-flag reference tables into a reference bundle file (e.g. references/actions.md) referenced from SKILL.md, so the main file stays an overview.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete commands, but the marketing intro ('helps users easily create and send curated newsletters... used by bloggers, content creators, and businesses') and asides about internals ('This is the fastest way to get a connection... a connector is built automatically') are unnecessary explanation Claude does not need, matching 'mostly efficient but includes some unnecessary explanation'.	3 / 5
Actionability	It provides a full catalog of concrete, copy-paste-ready commands (install, login, connection ensure/get, action list/run, request) plus a real actions table, but the run examples use generic placeholders ('{"key": "value"}', 'QUERY') rather than a concrete worked example with a real action input, leaving a minor gap.	4 / 5
Workflow Clarity	The connect-and-poll flow has an explicit feedback loop (poll --wait, then handle CLIENT_ACTION_REQUIRED and re-poll until READY) and covers error states (CONFIGURATION_ERROR/SETUP_FAILED), but the step numbering is loose ('Step 2' is referenced without a labeled Step 1/2, and the search/run sections are not framed as numbered steps), matching 'clear sequence with most checkpoints present; minor validation gaps'.	4 / 5
Progressive Disclosure	No bundle files exist and the body references no external files; the single SKILL.md is well-organized into clear ## sections and is easy to navigate, but at over 150 lines with the Popular actions and proxy-flag reference tables inlined, content that could be split out is kept inline, so it is good structure with minor organization gaps rather than ideal disclosure.	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 answers both what and when with an explicit trigger clause and is anchored to a distinct product name, but it relies on a single generic verb ('Manage') and trigger phrasing that is too generic to surface the real user vocabulary. It is solid but not sharp.

Suggestions

Replace the generic 'Manage' with concrete verbs that match the skill's actual actions, e.g. 'List and add email subscribers, create and list draft issues, and list publications and categories'.

Make the trigger phrase concrete by naming what users actually ask for: 'Use when the user wants to manage Curated newsletters, subscribers, issues, or publications'.

Reconcile the listed entities (Organizations, Users, Goals, Filters) with the skill's real capabilities (subscribers, issues, publications, categories, links), since the current entities do not appear in the documented actions.

Dimension	Reasoning	Score
Specificity	The phrase 'Manage Organizations, Users, Goals, Filters' names the domain and several concrete entities, but the only action verb is the generic 'Manage', so actions are minimal rather than comprehensive; this sits at the 2/3 boundary and the multiple named entities pull it to 3.	3 / 5
Completeness	It states both the 'what' ('Manage Organizations, Users, Goals, Filters') and an explicit 'Use when...' clause for the 'when', matching the anchor where both are present but the 'when' could be more specific; not a 5 because the trigger is not concrete.	4 / 5
Trigger Term Quality	It includes 'Curated' and the entity nouns plus an explicit trigger ('Use when the user wants to interact with Curated data'), but 'interact with Curated data' is generic and it omits the natural user-facing terms (newsletter, subscribers, issues, publications) that a user would actually say.	3 / 5
Distinctiveness Conflict Risk	Tying it to the named product 'Curated' / 'Curated data' gives it a clear niche, but the generic entities ('Organizations, Users') create minor overlap risk with sibling Membrane integration skills, matching 'mostly distinct; minor overlap risk'.	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/curated/SKILL.md
Commit: f484c82

Reviewed: ~16 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.