Name: starloop
Rating: 60 (1 reviews)
Author: membranedev

starloop

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

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

75%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 well-structured and highly actionable, with concrete CLI commands, a clear connection-state workflow, and a validation feedback loop. Its main gaps are a missing referenced "Step 2", inconsistent CLI invocation style, and inline content that could be split into reference files.

Suggestions

Add the missing "Step 2" section that the connection flow references, or relabel the steps so no jump target is undefined.

Standardize on either `membrane` or `npx @membranehq/cli` across all command examples to remove invocation ambiguity.

Move the proxy flag table and connection-state reference into a separate references file linked from the overview to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with executable code blocks and little concept re-explanation, but has minor padding (the Membrane auth-plumbing sentence and a repeated action-list command in "Popular actions"), fitting the efficient-but-trimmable score-4 anchor.	4 / 5
Actionability	Commands are concrete and copy-paste ready (install, login, connection ensure, action run/list, proxy flag table), but the inconsistent mix of `membrane` vs `npx @membranehq/cli` invocations leaves a small gap versus fully consistent score-5 guidance.	4 / 5
Workflow Clarity	The connection flow is clearly sequenced with state polling (READY/BUILDING/CLIENT_ACTION_REQUIRED) and a re-poll feedback loop after user action, but the referenced "Step 2" never appears in the body, a minor sequencing gap that keeps it at score-4 rather than score-5.	4 / 5
Progressive Disclosure	No bundle files exist and the body is a single self-contained, well-sectioned overview with clear headers; content that could be split out (full proxy flag table, state-handling detail) is inline rather than referenced, fitting score-4 with minor organization gaps rather than the fully-split score-5.	4 / 5
	Total	16 / 20 Passed

Description

66%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 includes both a what and a when clause and ties triggers to a named product, giving it strong distinctiveness. Its weaknesses are generic capability wording and missing natural synonyms (reviews, feedback) that keep specificity and trigger quality at mid-range.

Suggestions

Replace generic "Manage data, records, and automate workflows" with concrete Starloop actions such as "collect and analyze customer reviews, send feedback requests, and manage online reputation."

Add natural user keywords to the trigger clause, e.g. "Use when the user wants to interact with Starloop reviews, feedback requests, or reputation management."

Mention the API surface (e.g. "via the Starloop API") to sharpen the what-clause and reduce overlap with generic data-management skills.

Dimension	Reasoning	Score
Specificity	"Manage data, records, and automate workflows" names the Starloop domain plus a few concrete-ish actions, but the actions ("manage data, records") are generic and not comprehensive, matching the score-3 anchor rather than the more specific score-4.	3 / 5
Completeness	It states both what ("Manage data, records, and automate workflows") and when ("Use when the user wants to interact with Starloop data"), so both clauses are present with an explicit trigger, but the "what" is generic enough that it does not reach the fully concrete score-5 anchor.	4 / 5
Trigger Term Quality	The explicit "Use when the user wants to interact with Starloop data" provides a clear trigger and the product name, but "data" is generic and it omits natural user terms like "reviews," "customer feedback," or "reputation," landing at score-3 rather than score-4.	3 / 5
Distinctiveness Conflict Risk	The named product "Starloop" creates a clear niche with product-specific triggers and minimal conflict risk with other skills, matching the score-5 anchor for a distinct integration.	5 / 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/starloop/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.