Name: efinder
Rating: 54.400000000000006 (1 reviews)
Author: membranedev

efinder

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

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/efinder/SKILL.md

Quality

Content

61%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 highly actionable, packed with executable Membrane commands and a useful actions table, and well structured for navigation. Its main weaknesses are an unnecessary introductory explainer and the absence of explicit validation checkpoints in the connection/action workflow.

Suggestions

Remove or trim the SEO explainer paragraph; it describes concepts Claude already knows and, worse, mischaracterizes a tool whose actions are email finding/verification rather than SEO.

Add an explicit validation step after connecting (e.g. verify the connection with a lightweight query like get-account) before listing or running actions.

Show how to read the action-list output and feed a returned action id into `membrane action run` to close the small gap between discovery and execution.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean CLI commands and tables, but the opening SEO explainer ('Efinder is a search engine optimization (SEO) tool...') and phrases like 'so you can focus on the integration logic rather than auth plumbing' add explanation Claude does not need.	3 / 5
Actionability	Concrete, copy-pasteable commands are given throughout (install, login, connect, action list/run, request) with placeholders like CONNECTION_ID and a complete --input JSON example, leaving only minor gaps in mapping action-list output to a run.	4 / 5
Workflow Clarity	A clear install→login→connect→list→run sequence exists with a headless-auth fallback and a 'check existing connections' guard, but there are no explicit validation checkpoints confirming a connection succeeded or an action result is usable.	3 / 5
Progressive Disclosure	The single file is well organized into clearly headed sections (Overview, setup, connecting, popular actions, running, proxy, best practices) with no nested references, though at ~115 lines with no file splits it is good rather than exemplary.	4 / 5
	Total	14 / 20 Passed

Description

62%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 covers both what the skill does and when to use it with a brand-specific trigger, but it leans on a generic verb and generic CRM entity nouns rather than the email-finding actions the tool actually exposes. Tightening the action list and trigger terms would raise it.

Suggestions

Replace the generic 'Manage ... and more' with the tool's actual concrete actions (e.g. 'Find and verify email addresses by name or domain, run domain searches, and check account credits').

Expand the trigger clause with natural user phrases such as 'find an email', 'verify an email address', 'domain search', or 'email lookup'.

Align the listed capabilities with the real tool — the body describes email finding/verification, not Leads/Deals/Projects, so the description reads as a mismatched template.

Dimension	Reasoning	Score
Specificity	The description names the domain and several concrete entities ('Leads, Persons, Organizations, Deals, Projects, Activities') but offers only the single generic verb 'Manage' plus the vague 'and more', so actions are minimal rather than comprehensive.	3 / 5
Completeness	Both a 'what' (manage Leads/Persons/Organizations/Deals/Projects/Activities) and an explicit 'Use when...' 'when' clause are present; the 'when' is generic rather than concrete trigger phrases, so it is not a 5.	4 / 5
Trigger Term Quality	'Use when the user wants to interact with Efinder data' supplies the brand keyword but misses the natural phrases a user would actually say (e.g. email, domain search, verify email, SEO), so common variations are absent.	3 / 5
Distinctiveness Conflict Risk	The brand-anchored trigger 'interact with Efinder data' is mostly distinct, though the listed generic CRM entities (Leads, Deals, Projects) create minor overlap risk with other CRM-style skills.	4 / 5
	Total	14 / 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/efinder/SKILL.md
Commit: f484c82

Reviewed: 4 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.