Name: liondesk
Rating: 53.6 (1 reviews)
Author: membranedev

liondesk

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

Quality

60%

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/liondesk/SKILL.md

Quality

Content

66%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 concise, command-first integration guide with good structure and no padding beyond a short intro paragraph, and it is appropriately self-contained for a single-CLI skill. Its main weakness is workflow clarity: the connect-then-run sequence lacks any validation or error-recovery checkpoints for operations that can mutate CRM data.

Suggestions

Add explicit validation checkpoints after `membrane connect` (confirm the connection id is present) and after `membrane action run`/`membrane request` (inspect the JSON output for errors before proceeding), especially for write/POST operations.

Include a brief feedback loop for the discovery workflow: if `membrane action list --intent=...` returns no matches, fall back to `membrane request` via the proxy, and vice versa.

Trim or relocate the introductory paragraph explaining what LionDesk is so the body stays lean and assumes Claude's existing knowledge.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient, leading with executable CLI commands and a clean flag table; the only padding is the opening paragraph explaining what LionDesk is ('a CRM platform designed for real estate professionals...'), which is background Claude does not strictly need, keeping it just below 'lean and efficient' at 4.	4 / 5
Actionability	It provides concrete, copy-pasteable commands throughout (install, login, search, connect, action list/run, request) with parameter examples and a flag table, which is mostly executable; the minor gap is that the discovery commands return IDs whose parsing is only loosely described ('Take the connector ID from output.items[0]...'), so it is not fully copy-paste-ready for every common case.	4 / 5
Workflow Clarity	The connect/action/request flow is sequenced but validation is essentially absent: there is no checkpoint after `membrane connect` or `action run`, and the cap for batch/destructive operations without validation applies since `action run` and `membrane request` can mutate Liondesk data; this fits 'rough sequence present but many gaps; validation absent' better than 3.	2 / 5
Progressive Disclosure	The SKILL.md is a concise overview of the single integration surface with well-organized sections (Overview, Working with, Popular actions, Best practices) and no external bundle files to split off; per the simple-skill scoring note, a short well-structured body with no need for separate references earns a 5.	5 / 5
	Total	15 / 20 Passed

Description

53%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 answers both 'what' and 'when' and is well-scoped to the Liondesk CRM, but it relies on the single generic verb 'Manage' and a broad 'and more', leaving the concrete actions and natural trigger phrases under-specified. It is functional but reads closer to the mid-anchors than the top.

Suggestions

Replace the generic 'Manage ... and more' with concrete verbs per entity (e.g., 'Create, update, and search Leads; move Deals across Pipelines; log Activities').

Broaden the trigger clause beyond 'interact with Liondesk data' to natural user phrases such as 'manage real estate leads', 'update a Deal in Liondesk', or 'pull a contact report'.

Drop the vague 'and more' or enumerate the remaining entity types so the capability list is comprehensive rather than open-ended.

Dimension	Reasoning	Score
Specificity	Names the domain and enumerates entities ('Manage Leads, Persons, Organizations, Deals, Pipelines, Activities and more') but the actions are all collapsed into the generic verb 'Manage', so no concrete per-entity actions are listed; this matches the 'names domain and 1-2 concrete actions, but not comprehensive' anchor better than 4 since coverage is generic rather than specific.	3 / 5
Completeness	It has a clear 'what' ('Manage Leads, Persons, Organizations, Deals, Pipelines, Activities and more') and an explicit 'Use when the user wants to interact with Liondesk data' trigger, which should earn a 4, but the trigger clause is broad and not tied to concrete scenarios; the vague 'and more' plus generic 'when' keeps it at the 'clear what but when is only weakly implied/explicit' boundary of 3-4, settling at 3.	3 / 5
Trigger Term Quality	The only natural trigger is 'interact with Liondesk data'; entity names (Leads, Deals, Pipelines) are domain nouns rather than the natural phrases a user would say, and common synonyms/file extensions are absent, so it sits at 'some relevant keywords but missing common variations'.	3 / 5
Distinctiveness Conflict Risk	The product name 'Liondesk' plus the real-estate CRM entity list makes it clearly niche with minimal overlap against other skills; minor risk only because 'Manage ... data' is generic phrasing, fitting 'mostly distinct; minor overlap risk'.	4 / 5
	Total	13 / 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/liondesk/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.