Name: sellix
Rating: 64.8 (1 reviews)
Author: membranedev

sellix

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

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

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

Quality

Content

76%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 highly actionable and well-structured, dominated by concrete CLI commands that cover the full integration workflow. Its main weakness is the absence of validation/verification checkpoints and error-feedback loops around potentially destructive action runs and proxy requests.

Suggestions

Add explicit validation checkpoints after risky steps, e.g. verify a connection succeeded (and capture its connectionId) before running actions, and inspect action/proxy responses for errors before proceeding.

Include a feedback loop for destructive operations: show how to read an error response from `membrane action run` / `membrane request`, fix the input, and retry, especially for POST/PUT/DELETE proxy calls.

Remove the redundant `membrane action list ...` command in the "Popular actions" section (it duplicates "Searching for actions") and replace it with a short curated list of commonly used Sellix action IDs or intents.

Dimension	Reasoning	Score
Conciseness	Largely efficient, built from copy-paste commands and a flags table, but the opening Sellix paragraph and the "Popular actions" section (which repeats the action-list command already shown under "Searching for actions") are minor padding that could be trimmed.	4 / 5
Actionability	Fully executable, copy-paste-ready commands cover the common workflow (install, login, connect, list connections, discover actions, run actions, proxy), with a thorough proxy-flags table and concrete guidance on extracting the connector ID from JSON output.	5 / 5
Workflow Clarity	The install→login→connect→discover→run sequence is clear, but there are no validation or verification checkpoints, and because proxy requests and action runs can be destructive (POST/PUT/DELETE), the missing feedback loops cap this dimension at 3.	3 / 5
Progressive Disclosure	Well-organized into clearly headed sections in a single file with no bundle references; structure is good, though the entity overview and proxy reference table sit fully inline with minor redundancy rather than split into one-level-deep reference files.	4 / 5
	Total	16 / 20 Passed

Description

78%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 third-person, concise, and answers both what and when with an explicit Use-when clause tied to a distinct brand niche. It is held back from the top band by a generic verb ("Manage"), a vague "and more" tail, and a trigger clause that is not scenario-specific.

Dimension	Reasoning	Score
Specificity	Names the Sellix domain and lists six concrete entity types ("Deals, Persons, Organizations, Leads, Projects, Activities"), but the single generic verb "Manage" and the trailing "and more" keep it just short of comprehensive, distinct-action coverage.	4 / 5
Completeness	Explicitly states both what ("Sellix integration. Manage Deals, Persons, Organizations, Leads, Projects, Activities and more.") and when ("Use when the user wants to interact with Sellix data."), but the trigger clause is somewhat generic rather than scenario-specific.	4 / 5
Trigger Term Quality	Includes the natural brand keyword "Sellix" (repeated) plus several entity names a user would actually say, giving good keyword coverage, though domain terms like orders, payments, or digital products are absent.	4 / 5
Distinctiveness Conflict Risk	"Sellix integration" carves out a clear, brand-specific niche with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	17 / 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/sellix/SKILL.md
Commit: f484c82

Reviewed: ~22 hours 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.