Name: ultramsg
Rating: 59.2 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

ultramsg

UltraMsg integration. Manage Organizations, Users. Use when the user wants to interact with UltraMsg data.

Quality

68%

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/ultramsg/SKILL.md

Quality

Content

75%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.

A strongly actionable, well-structured integration guide with copy-paste Membrane CLI commands and a clear connection workflow including state-polling feedback loops. Its main weaknesses are a padded marketing-style intro and the absence of validation steps on the outward-facing send operations.

Suggestions

Trim the opening marketing paragraph ('It allows businesses to send and receive messages, automate workflows...') to a one-line definition of what UltraMsg is.

Add a verification/dry-run note for send actions (e.g., check instance status or confirm delivery) since sending WhatsApp messages is outward-facing and irreversible.

Remove the filler line 'When to use which actions: Use action names and parameters as needed.' — it adds no concrete guidance.

Dimension	Reasoning	Score
Conciseness	The bulk is efficient executable commands, but the opening marketing paragraph ('It allows businesses to send and receive messages, automate workflows...') and filler like 'When to use which actions: Use action names and parameters as needed' are unnecessary explanation Claude does not need, fitting anchor 3.	3 / 5
Actionability	Commands are copy-paste ready and cover common cases — install, login, connection ensure/get with --wait, action list/run with --input, and the proxy options table — matching the fully-executable anchor 5.	5 / 5
Workflow Clarity	The connection sequence has explicit checkpoints (poll --wait, READY/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR handling, re-poll after user acts), but the actual message-sending operations are only a table plus a single command with no verify step, leaving a minor validation gap at anchor 4 rather than 5.	4 / 5
Progressive Disclosure	Single file with good section structure (Overview, Working with UltraMsg, Popular actions, Proxy, Best practices) and no nested references; the inline Popular-actions and proxy tables are bulk content that could be split out, so it sits at anchor 4 rather than the well-signaled-external-references anchor 5.	4 / 5
	Total	16 / 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 and when with a clear product niche, but relies on the single keyword 'UltraMsg' and generic verbs ('Manage', 'interact with data') rather than concrete WhatsApp actions and natural user phrases. Tightening triggers and listing specific actions would lift it.

Suggestions

List concrete actions users perform (e.g., 'send and receive WhatsApp messages, list chats and contacts, get instance status') instead of the generic 'Manage Organizations, Users'.

Add natural trigger terms users actually say, especially 'WhatsApp' and message/chat/contacts, since UltraMsg is a WhatsApp API.

Sharpen the 'Use when' clause with concrete triggers, e.g. 'Use when the user wants to send WhatsApp messages or query UltraMsg chats, contacts, or instance status.'

Dimension	Reasoning	Score
Specificity	Names the UltraMsg domain plus two concrete targets ('Manage Organizations, Users') but the verb 'Manage' is generic and only 1-2 actions are listed, matching anchor 3 rather than the several-specific-actions anchor 4.	3 / 5
Completeness	Both 'what' ('Manage Organizations, Users') and 'when' ('Use when the user wants to interact with UltraMsg data') are present, but the 'when' clause is generic ('interact with data') rather than concrete trigger phrases, fitting anchor 4 not 5.	4 / 5
Trigger Term Quality	The only real keyword is 'UltraMsg' (repeated as 'UltraMsg data'); it misses the natural term 'WhatsApp' that users would actually say, so coverage has relevant but incomplete keywords per anchor 3.	3 / 5
Distinctiveness Conflict Risk	Naming the specific product 'UltraMsg' gives it a clear niche, but the generic 'interact with UltraMsg data' trigger leaves minor overlap risk with other messaging/WhatsApp skills, matching anchor 4.	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/ultramsg/SKILL.md
Commit: f484c82

Reviewed: 3 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.