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

levity

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

Quality

68%

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/levity/SKILL.md

Quality

Content

68%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 well-structured, actionable integration guide with concrete CLI commands and a useful proxy fallback. Its chief gap is the absence of validation checkpoints in a workflow that can perform destructive administrative operations.

Suggestions

Add explicit validation checkpoints after connect and action-run steps, e.g. verify the connectionId is returned and confirm action output before proceeding.

Populate the 'Popular actions' section with concrete example action IDs or a sample intent query so Claude can act without first discovering them.

For destructive operations on Users/Organizations, add a confirm-before-acting or dry-run step and an error-recovery feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean concrete commands with a brief, justified Levity intro, but phrases like 'so you can focus on the integration logic rather than auth plumbing' could be trimmed, fitting anchor 4 rather than 5.	4 / 5
Actionability	Provides copy-paste-ready npx commands with real flags and a proxy option table, but the 'Popular actions' section lists no concrete action IDs, leaving a minor gap that fits anchor 4 rather than 5.	4 / 5
Workflow Clarity	A clear setup->connect->discover->run sequence is present, but there are no validation or verification checkpoints, and managing Users/Organizations is potentially destructive, capping workflow_clarity at 3 per the rubric guidelines.	3 / 5
Progressive Disclosure	A single self-contained file (~110 lines) with well-organized section headers and clear navigation; no bundle files exist and no external references are needed, but it exceeds the 50-line simple-skill threshold so anchor 4 applies rather than 5.	4 / 5
	Total	15 / 20 Passed

Description

67%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 clearly scopes a Levity integration with both capability and trigger guidance, and its named-product niche keeps conflict risk low. Its main weaknesses are a single generic action verb and incomplete trigger-term coverage that omits several core Levity concepts present in the body.

Suggestions

Replace the generic verb 'Manage' with concrete operations, e.g. 'Create, list, update, and delete Organizations, Pipelines, Users, Goals, and Filters'.

Expand the 'Use when' clause to name the specific entities and synonyms users would say, e.g. 'Use when the user wants to manage Levity workflows, models, datasets, pipelines, or users'.

Align trigger terms with the body's overview so core concepts like Workflow, Model, and Dataset appear in the description.

Dimension	Reasoning	Score
Specificity	Names five concrete Levity entities ('Manage Organizations, Pipelines, Users, Goals, Filters'), giving broad coverage, but the single generic verb 'Manage' leaves the specific CRUD actions unspecified, fitting anchor 4 rather than 5.	4 / 5
Completeness	Provides both a 'what' (manage the listed entities) and a 'when' ('Use when the user wants to interact with Levity data'), but the trigger could be more entity-specific, fitting anchor 4 rather than 5.	4 / 5
Trigger Term Quality	Includes relevant keywords ('Levity', 'Organizations', 'Pipelines', 'Users', 'Goals', 'Filters') but omits prominent body concepts like Workflow, Model, Dataset, Queue and common synonyms, matching anchor 3.	3 / 5
Distinctiveness Conflict Risk	Levity is a named SaaS product giving a clear niche with low conflict risk, though generic terms like 'Users' and 'Organizations' carry minor overlap with adjacent admin skills, matching anchor 4.	4 / 5
	Total	15 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: membranedev/application-skills
Path: skills/levity/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.