Name: loop-returns
Rating: 51.2 (1 reviews)
Author: membranedev

loop-returns

Loop Returns integration. Manage Returns, Merchants, Customers, Integrations. Use when the user wants to interact with Loop Returns data.

Quality

56%

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/loop-returns/SKILL.md

Quality

Content

46%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 skill delivers executable, well-structured CLI guidance for connecting to and calling Loop Returns, but it is undermined by a large block of nonsensical padded overview entries and a lack of any external reference files. Destructive proxy operations also lack validation guidance.

Suggestions

Delete the ~120 irrelevant 'Package *' overview entries (NFT, Metaverse, Fonts, Haptics, etc.) or move a curated entity list into a separate reference file.

Add a validation/verification checkpoint before running destructive proxy requests (POST/PUT/PATCH/DELETE), e.g., confirm the target endpoint and dry-run where possible.

Move the bulk entity/action catalog into a references file (e.g., references/entities.md) and link to it from SKILL.md so the overview stays lean.

Dimension	Reasoning	Score
Conciseness	The 'Loop Returns Overview' inflates the body with ~120 'Package *' entries (e.g., 'Package NFT', 'Package Metaverse', 'Package Fonts', 'Package Haptics') that are irrelevant padding, wasting significant context despite otherwise reasonable working sections.	2 / 5
Actionability	Provides concrete, copy-paste-ready commands for the core flow (membrane login, connection ensure, action list/run, request) with flag tables and JSON examples, with only minor gaps around parameter construction.	4 / 5
Workflow Clarity	Sequencing from install → authenticate → connect → poll for READY → search → run is clear, but the proxy-request section enables arbitrary POST/PUT/PATCH/DELETE calls with no validation checkpoint, capping destructive/batch workflow clarity at 3.	3 / 5
Progressive Disclosure	There are no bundle files and all content is inlined into SKILL.md, including the huge overview list that clearly belongs in a separate reference file; structure is minimal and references are absent.	2 / 5
	Total	11 / 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 is well-structured with both a 'what' and an explicit 'Use when' clause, and it occupies a distinct niche. Its weaknesses are the generic 'Manage' verb and limited trigger-term variety.

Suggestions

Replace the generic verb 'Manage' with concrete actions (e.g., 'Search, retrieve, create, and update Returns, Merchants, Customers, and Integrations').

Broaden the trigger clause with natural user phrases (e.g., 'Use when the user wants to query or modify Loop Returns data, manage RMAs, or handle returns/exchanges').

Mention key concrete nouns users would say, such as 'RMAs', 'returns', 'exchanges', or 'store credit'.

Dimension	Reasoning	Score
Specificity	Names the domain ('Loop Returns integration') and lists several entities to 'Manage' (Returns, Merchants, Customers, Integrations), but the verb 'Manage' is generic and the action coverage is shallow rather than comprehensive.	3 / 5
Completeness	Explicitly answers both 'what' (Loop Returns integration managing Returns, Merchants, Customers, Integrations) and 'when' ('Use when the user wants to interact with Loop Returns data'), though the 'when' could be more specific.	4 / 5
Trigger Term Quality	Includes the core keyword 'Loop Returns' and a 'Use when...' trigger ('interact with Loop Returns data'), but lacks common variations, synonyms, or concrete task phrases users would naturally say.	3 / 5
Distinctiveness Conflict Risk	Targets a clearly named third-party app ('Loop Returns') with a distinct niche, making it unlikely to trigger for unrelated skills.	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/loop-returns/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.