Name: lusha
Rating: 57.599999999999994 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

lusha

Lusha integration. Manage Persons, Organizations. Use when the user wants to interact with Lusha data.

Quality

66%

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/lusha/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 body is a well-structured, actionable guide to driving Lusha through the Membrane CLI, with concrete commands, a clear connect-and-poll workflow, and error-state handling. Its main weakness is mild verbosity (marketing overview and a few padded explanations) and a large inline action-reference table that could be split out.

Suggestions

Trim the marketing-style Lusha overview paragraph and padded rationales ('burn less tokens', 'rather than auth plumbing') to keep only what Claude cannot infer.

Move the 13-row Popular actions table into a separate reference file (e.g. references/actions.md) and keep only the 3-4 most common actions inline, signaling the rest with a one-level-deep link.

Add an explicit validation/verification checkpoint after running actions (e.g., check the response `output` field and handle empty results or error states) to strengthen the workflow's feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with executable commands and tables, but includes unnecessary explanatory prose ('so you can focus on the integration logic rather than auth plumbing', 'This will burn less tokens and make communication more secure') and a marketing-style Lusha overview that could be trimmed, matching the 'mostly efficient but includes some unnecessary explanation' anchor.	3 / 5
Actionability	Concrete executable commands appear throughout (npm install, membrane login, connection ensure, action run/list, request) with flag tables and JSON examples, matching 'mostly executable guidance with minor gaps' since some placeholders (CONNECTION_ID, <actionId>) and output-handling detail are lightly specified.	4 / 5
Workflow Clarity	A clear sequence (install -> authenticate -> connect -> search -> run/proxy) with an explicit feedback loop ('After the user completes the action... poll again to check if state moved to READY') and error-state branching matches 'clear sequence with most checkpoints present; minor validation gaps'.	4 / 5
Progressive Disclosure	No bundle files exist; the single SKILL.md is well-organized with clear section headers and a popular-actions table. The simple-skill note allows a high score, but a sizeable inline actions reference that could be a separate file keeps it at 'good structure with minor organization gaps' rather than 5.	4 / 5
	Total	15 / 20 Passed

Description

66%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 identifies a specific niche (Lusha) with explicit what/when guidance, but its action list and trigger keywords are generic and miss the natural terms (contacts, leads, enrichment) that would distinguish it. It is solid but leaves specificity and trigger-term coverage underdeveloped.

Suggestions

Replace the generic 'Manage Persons, Organizations' with concrete actions a user would request, e.g. 'Search and enrich B2B contacts and companies, find emails and phone numbers, get lookalike recommendations and signals.'

Add natural trigger terms users actually say, such as 'contacts', 'leads', 'prospect lists', 'enrichment', 'B2B contact data', or 'phone numbers and emails'.

Tighten the 'Use when...' clause to specific scenarios, e.g. 'Use when the user wants to find, enrich, or search B2B contacts and companies via Lusha.'

Dimension	Reasoning	Score
Specificity	Quotes 'Manage Persons, Organizations' name the Lusha domain plus two concrete actions, matching the anchor for naming a domain with 1-2 concrete actions but not comprehensive coverage.	3 / 5
Completeness	It has both a clear 'what' ('Lusha integration. Manage Persons, Organizations.') and an explicit 'when' ('Use when the user wants to interact with Lusha data.'), but the 'when' trigger is somewhat generic, matching the 'both what and when; when could be more explicit' anchor.	4 / 5
Trigger Term Quality	'Persons, Organizations', 'interact with Lusha data' provide some relevant keywords, but natural synonyms users would say (contacts, leads, enrichment, B2B data) are missing, fitting the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	'Lusha integration' names a specific B2B contact-data product with a clear niche and distinct triggers, minimal conflict risk with other skills.	5 / 5
	Total	15 / 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/lusha/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.