Name: golioth
Rating: 56.8 (1 reviews)
Author: membranedev

golioth

Golioth integration. Manage data, records, and automate workflows. Use when the user wants to interact with Golioth data.

Quality

65%

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/golioth/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 CLI guide with a solid connection state-machine and feedback loop, but it carries some introductory fluff and slightly inconsistent step numbering. Trimming the definitional prose and fixing the step labels would push conciseness and workflow_clarity higher.

Suggestions

Cut the opening definitional paragraph and the filler line 'Use action names and parameters as needed.'; assume Claude knows what an IoT platform is.

Fix the step numbering: label the connection setup as 'Step 1' with '1a/1b' sub-steps and explicitly number 'Searching for actions' as 'Step 2' so the 'skip to Step 2' reference resolves.

Add a brief verification note after `membrane action run` (e.g. check the `output` field for errors) to close the action-running workflow loop.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with copy-paste commands and a flags table, but it opens with a definitional paragraph ('Golioth is a cloud platform for connecting and managing IoT devices...') and filler like 'Use action names and parameters as needed.' that could be trimmed.	3 / 5
Actionability	Provides concrete, executable CLI commands (membrane login, connection ensure, action run, request) with a full flags table and --json usage; minor gaps are placeholder tokens (CONNECTION_ID, <actionId>) the agent must substitute.	4 / 5
Workflow Clarity	The connection flow has an explicit state-machine with a polling feedback loop (READY/BUILDING/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR), but the section references an unlabeled 'Step 2' and '1b' without a matching '1a', and action-running lacks result verification.	4 / 5
Progressive Disclosure	Single cohesive SKILL.md with well-organized section headers and no nested external references; no bundle files exist to verify, and the inline content is appropriately sized for one file with only minor organization redundancy.	4 / 5
	Total	15 / 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 correctly pairs a 'what' with an explicit 'Use when' trigger tied to a distinct named platform, but its actions are generic and its trigger language is narrow. Tightening the action list and broadening the trigger phrases would lift specificity and trigger_term_quality.

Suggestions

Replace generic verbs with concrete Golioth capabilities, e.g. 'Manage IoT devices, LightDB state/stream data, settings, logs, and firmware releases'.

Broaden the trigger to cover natural phrasings: 'Use when the user wants to manage Golioth IoT devices, query LightDB data, or deploy firmware releases.'

Mention key Golioth nouns (devices, LightDB, firmware) so the trigger matches how users actually describe the task.

Dimension	Reasoning	Score
Specificity	Names the domain ('Golioth integration') and a few actions ('Manage data, records, and automate workflows'), but the actions are generic and overlapping rather than concrete and comprehensive.	3 / 5
Completeness	Both a 'what' ('Manage data, records, and automate workflows') and an explicit 'when' ('Use when the user wants to interact with Golioth data') are present, but the 'when' could be more specific with concrete trigger phrases.	4 / 5
Trigger Term Quality	The natural keyword 'Golioth' appears, but the trigger phrase 'interact with Golioth data' is narrow and omits common variations users might say (devices, LightDB, firmware, IoT).	3 / 5
Distinctiveness Conflict Risk	'Golioth' is a uniquely named IoT platform giving it a clear distinct niche with low conflict risk, though the thin trigger phrasing leaves minor overlap ambiguity versus generic data 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/golioth/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.