Name: lmnt
Rating: 60.8 (1 reviews)
Author: membranedev

lmnt

LMNT integration. Manage Leads, Persons, Organizations, Deals, Projects, Pipelines and more. Use when the user wants to interact with LMNT data.

Quality

71%

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/lmnt/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.

A highly actionable, well-structured CLI integration guide with a real validation feedback loop for connection setup. Its main weaknesses are an irrelevant opening paragraph about LMNT as a beverage, duplicated action-list examples, and broken step numbering that leaves "Step 2" undefined.

Suggestions

Delete the "LMNT is an electrolyte drink mix..." paragraph; it explains an unrelated product fact and wastes context tokens.

Fix the step numbering: define a labeled "Step 2" (or rephrase to "skip to Searching for actions") and reconcile the lone "1b" with the surrounding steps.

De-duplicate the action-list example (it appears in both "Searching for actions" and "Popular actions") into a single canonical command.

Dimension	Reasoning	Score
Conciseness	Mostly efficient operational guidance, but the opening "LMNT is an electrolyte drink mix formulated with a salty taste..." paragraph is irrelevant padding, and phrases like "so you can focus on the integration logic rather than auth plumbing" could be trimmed.	3 / 5
Actionability	Provides concrete, copy-paste-ready CLI commands across install, login, connection, action discovery, action execution, and proxying, with a flags table; minor gaps come from the duplicated action-list example and placeholder CONNECTION_ID/actionId usage.	4 / 5
Workflow Clarity	The connection flow is a clear sequence with an explicit validation/polling feedback loop (poll state, handle CLIENT_ACTION_REQUIRED, re-poll until READY), but the broken step numbering ("skip to Step 2" with no Step 2 heading; a "1b" with no "1a") is a clarity gap that prevents a 5.	4 / 5
Progressive Disclosure	Well-organized into clear sections (Overview, Working with LMNT, Authentication, Connecting, Searching, Popular actions, Best practices) in a self-contained single file; the longer clientAction detail and flags table could arguably move to a reference file, but placement is reasonable.	4 / 5
	Total	15 / 20 Passed

Description

75%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.

A solid, third-person description that pairs a concrete entity list with an explicit use-when clause. It is held back from the top band by a single generic verb, the vague "and more" hedge, and a when-clause that is not tied to specific trigger phrases.

Suggestions

Replace the single verb "Manage" with distinct concrete actions (e.g., "Create, update, and query Leads, Persons, Organizations...") to raise specificity.

Tighten the when-clause with concrete triggers (e.g., "Use when the user wants to create or update LMNT leads, deals, or projects, or query LMNT data").

Drop the "and more" hedge or replace it with the remaining entity types so coverage is explicit rather than implied.

Dimension	Reasoning	Score
Specificity	Names the LMNT domain and lists several concrete manageables ("Leads, Persons, Organizations, Deals, Projects, Pipelines"), but a single generic verb "Manage" plus the open-ended "and more" leaves minor coverage gaps rather than distinct action verbs.	4 / 5
Completeness	Explicitly answers both what ("Manage Leads, Persons, Organizations, Deals, Projects, Pipelines") and when ("Use when the user wants to interact with LMNT data"), but the when-clause is less explicit than concrete trigger phrases, so it stops short of a 5.	4 / 5
Trigger Term Quality	Includes the natural entity terms users would say (Leads, Persons, Organizations, Deals, Projects, Pipelines, LMNT), giving good keyword coverage, though it lacks synonyms or file extensions and the "interact with LMNT data" phrasing is fairly generic.	4 / 5
Distinctiveness Conflict Risk	The "LMNT integration" framing and LMNT-pinned when-clause give it a clear niche, but the generic CRM entity list (Leals, Deals, Pipelines) carries minor overlap risk with other CRM-integration skills.	4 / 5
	Total	16 / 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/lmnt/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.