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

Blog Docs Log in Get started

helium

Helium integration. Manage Organizations. Use when the user wants to interact with Helium 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

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

57%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 actionable and reasonably structured around the Membrane CLI workflow, but it over-explains background concepts, lacks validation guidance for destructive actions, and inlines a large action catalog that should be split into a reference file.

Suggestions

Trim the intro paragraph and remove explanatory fluff (e.g., the "crypto-incentivized" analogy) so the body assumes Claude's competence.

Add an explicit validate-before-delete checkpoint or confirmation step for destructive actions (delete-device/flow/integration/label) to lift workflow clarity above the cap.

Move the popular-actions table into a references/actions.md file and link to it from the body to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete commands, but the opening explains what Helium/LoRaWAN is and includes padding ("Think of it as a crypto-incentivized way to build out wireless infrastructure") that Claude does not need.	3 / 5
Actionability	Provides copy-paste-ready CLI commands (install, login, connection ensure, action list/run, request) plus a populated actions table, with only minor placeholder gaps (CONNECTION_ID, <actionId>).	4 / 5
Workflow Clarity	The connection flow has explicit state handling and a poll-after-action feedback loop, but the popular-actions table surfaces destructive operations (delete-device, delete-flow, delete-integration, delete-label) with no validation/verification checkpoints, capping this dimension at 3.	3 / 5
Progressive Disclosure	Single-file skill over 50 lines with a 19-row inline action catalog that would be better placed in a reference file; no bundle references exist to offload the bulk.	3 / 5
	Total	13 / 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 is third-person, names a distinct platform, and includes both a what and a when clause, but the what is narrow (only Organizations) and the when trigger is generic. Expanding the action list and trigger phrases would raise completeness and specificity.

Suggestions

Add the other supported entities to the "what" clause (e.g., "Manage organizations, devices, labels, flows, and integrations in Helium").

Broaden the "when" trigger with concrete phrases users would say, such as "Use when the user wants to manage Helium IoT devices, LoRaWAN networks, or organization data."

Include natural synonyms/extensions (e.g., "IoT devices", "LoRaWAN") to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ("Helium integration") and one concrete action ("Manage Organizations"), but coverage is not comprehensive given the many other entities (devices, labels, flows, integrations) the skill supports.	3 / 5
Completeness	Both "what" ("Helium integration. Manage Organizations.") and "when" ("Use when the user wants to interact with Helium data.") are present, but the "when" clause is generic rather than listing concrete trigger phrases.	4 / 5
Trigger Term Quality	"Helium" is the core natural keyword and "interact with Helium data" is a reasonable trigger phrase, but common variations and entity-level terms (devices, labels, flows) are missing.	3 / 5
Distinctiveness Conflict Risk	"Helium" is a distinct named platform with minimal conflict risk, though the generic "Manage Organizations" framing introduces minor overlap with other org-management 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/helium/SKILL.md
Commit: f484c82

Reviewed: 5 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.