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

liveagent

LiveAgent integration. Manage Persons, Organizations, Deals, Leads, Activities, Notes and more. Use when the user wants to interact with LiveAgent 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/liveagent/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.

The content is a well-structured, actionable guide for driving LiveAgent through the Membrane CLI, with runnable commands, a clear connect-and-poll workflow, and explicit state-based checkpoints. Its main weaknesses are an introductory paragraph of domain background Claude already knows and minor redundancy across the action-search sections.

Suggestions

Remove or trim the opening paragraph explaining what LiveAgent is and how customer service teams use it, since that is general background Claude already knows.

Consolidate the two overlapping 'Searching for actions' / 'Popular actions' sections into a single action-discovery section to reduce redundancy.

Tie the CONNECTION_ID and actionId placeholders to the prior steps (e.g., 'use the connection id returned above') so the executable flow is fully bound.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with executable commands, but includes some content Claude likely already knows (a paragraph explaining what LiveAgent is and how customer service teams use it) and mild redundancy where action-search is described in two near-duplicate sections.	3 / 5
Actionability	It provides concrete, runnable CLI commands with flags and a clear options table, covering connection, action discovery, running, and proxying; minor gaps include placeholders like CONNECTION_ID and actionId that are explained but not concretely bound.	4 / 5
Workflow Clarity	There is a clear multi-step sequence (install -> login -> connection ensure -> wait/poll until READY -> search actions -> run/proxy) with explicit state checks (READY/BUILDING/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR) serving as checkpoints, though a few transitions are only implicitly validated.	4 / 5
Progressive Disclosure	The body is well-organized into clearly signaled sections (overview, install, auth, connecting, searching, popular actions, proxy, best practices) with no bundle files to over-reference; it is a single appropriately-sized SKILL.md rather than a monolith, with only minor inline reference-table bulk.	4 / 5
	Total	15 / 20 Passed

Description

73%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 brand-specific with an explicit 'Use when' clause and a concrete entity list, giving it strong distinctiveness and reasonable completeness. It is held back from top marks by the generic 'Manage' verb and the absence of richer natural trigger phrases.

Suggestions

Replace the generic verb 'Manage' with specific concrete actions (e.g., 'Create, update, search, and delete Persons, Organizations, Deals, Leads, Activities, Notes').

Expand the trigger clause with concrete user phrases (e.g., 'Use when the user wants to search tickets, manage contacts, or interact with LiveAgent CRM data').

Dimension	Reasoning	Score
Specificity	The description names the domain and enumerates concrete entities ('Manage Persons, Organizations, Deals, Leads, Activities, Notes and more') but the verb 'Manage' is generic, leaving the specific actions performed on each entity unspecified.	3 / 5
Completeness	It has a clear 'what' (manage the listed LiveAgent entities) and an explicit 'when' clause ('Use when the user wants to interact with LiveAgent data'), but the 'when' trigger is fairly generic rather than enumerating concrete trigger phrases.	4 / 5
Trigger Term Quality	It includes natural domain terms ('LiveAgent data', entity names, 'interact with') that a user would plausibly say, though it lacks common synonyms or file-extension-style variations beyond the LiveAgent brand name.	4 / 5
Distinctiveness Conflict Risk	The LiveAgent brand name and its specific entity model create a clear niche with distinct triggers and minimal conflict risk against other skills.	5 / 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/liveagent/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.