Name: loyaltylion
Rating: 59.2 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

loyaltylion

LoyaltyLion integration. Manage Members. Use when the user wants to interact with LoyaltyLion data.

Quality

69%

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/loyaltylion/SKILL.md

Quality

Content

76%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 highly actionable, with executable commands and a clear connection workflow, and is reasonably concise and well-structured. Its main gap is the absence of validation checkpoints for destructive loyalty operations, which caps workflow clarity.

Suggestions

Add an explicit validation/verification step before running destructive actions (e.g. list-customer-transactions or a dry-run to confirm the target customer) and a post-run check to confirm the points/order change applied.

Fix the step numbering: label 'Step 1'/'Step 2' consistently (currently 'Step 2' and '1b' are referenced without matching anchors) so the connection workflow is unambiguous.

Dimension	Reasoning	Score
Conciseness	The body is largely efficient — concrete commands, a flag table, and a compact actions table — with only minor trimmable prose such as the opening 'LoyaltyLion is an ecommerce loyalty and rewards platform...' background. It is not 5 because that intro and the vague 'LoyaltyLion Overview' tree add tokens without actionable value.	4 / 5
Actionability	It provides fully executable, copy-paste-ready commands covering the common cases (install, login, connection ensure/get with --wait, action list/run, request proxy) with explained placeholders and a concrete --input example. This matches anchor 5: specific examples cover the common cases.	5 / 5
Workflow Clarity	A sequence exists (install → auth → connect → poll for READY → search → run) with connection-state feedback loops, but there are no validation/verification steps around destructive actions like remove-points, add-points, or create-order. Per the rubric, missing validation for destructive/batch operations caps this at 3.	3 / 5
Progressive Disclosure	The single file is well-organized with clear section headers and no external file references (appropriate for a CLI skill), matching anchor 4. It is not 5 because the skill exceeds 50 lines with a long inline actions table and minor navigation gaps such as references to an unlabeled 'Step 2' and a '1b' with no '1'.	4 / 5
	Total	16 / 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 correctly includes an explicit 'Use when' trigger and names a distinct product, giving it solid completeness and distinctiveness. Its weaknesses are minimal specificity (only one thin action) and limited natural trigger terms, which keep it mid-range.

Suggestions

Replace the single generic 'Manage Members' with concrete actions from the skill, e.g. 'list customers, add or remove loyalty points, redeem rewards, and create orders'.

Add natural trigger phrases users actually say, such as 'loyalty points', 'rewards', 'loyalty program', or 'customers', to the 'Use when' clause.

Tighten the 'when' clause to reference concrete intents (e.g. 'Use when the user wants to manage loyalty points, rewards, or customer activities in LoyaltyLion') rather than the circular 'interact with LoyaltyLion data'.

Dimension	Reasoning	Score
Specificity	Names the domain ('LoyaltyLion integration') and one concrete action ('Manage Members'), but offers no further concrete actions and is not comprehensive. It sits above anchor 2 because 'Manage Members' names a specific entity, yet below 4 because only one thin action is given.	3 / 5
Completeness	Both 'what' ('LoyaltyLion integration. Manage Members.') and 'when' ('Use when the user wants to interact with LoyaltyLion data') are present. It is not 5 because the 'when' clause is generic and circular and the 'what' is thin, lacking concrete trigger phrases.	4 / 5
Trigger Term Quality	It includes the product name 'LoyaltyLion' and 'Members'/'LoyaltyLion data', but omits common natural phrases a user would say such as 'loyalty points', 'rewards', 'customers', or 'loyalty program'. This matches anchor 3: some relevant keywords but missing common variations.	3 / 5
Distinctiveness Conflict Risk	Naming the specific product 'LoyaltyLion' gives it a clear niche with low conflict risk. It is not 5 because the surrounding 'Manage Members'/'interact with data' phrasing is generic and could overlap with other CRM/member skills.	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/loyaltylion/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.