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

Blog Docs Log in Get started

hume

Hume integration. Manage data, records, and automate workflows. Use when the user wants to interact with Hume 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/hume/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 delivers executable Membrane CLI commands and a clear connection state-machine workflow with polling and feedback, scoring well on actionability and workflow clarity. It is held back by an unnecessary marketing intro and some minor organizational and conciseness issues.

Suggestions

Remove the opening marketing paragraph about what Hume AI is; Claude already knows this and it adds tokens without guidance.

Fix the step numbering inconsistency (references to 'Step 2' and '1b' without a '1a'/'1') so the connection workflow reads as one coherent sequence.

Trim the duplicated 'membrane action list' invocation (it appears in both 'Searching for actions' and 'Popular actions') to a single canonical example.

Dimension	Reasoning	Score
Conciseness	Most of the body is efficient CLI commands and tables, but it opens with marketing prose ('Hume AI provides tools for understanding human behavior...') and repeats the action-list invocation, fitting the anchor for mostly efficient content with some unnecessary explanation that could be tightened.	3 / 5
Actionability	It provides copy-paste bash commands for login, connection ensure, polling, action list/run, and proxy requests with flags explained, matching the anchor for mostly executable guidance with minor gaps (no concrete example actionId or sample output).	4 / 5
Workflow Clarity	The connection flow has an explicit state machine (READY/BUILDING/CLIENT_ACTION_REQUIRED) with a poll loop and feedback to re-poll after user action, fitting the clear-sequence anchor; minor gaps come from inconsistent step numbering ('Step 2', '1b') rather than validation.	4 / 5
Progressive Disclosure	The single SKILL.md is well-sectioned with clear headers and no nested references (no bundle files exist), matching the good-structure anchor; it is a longer single file with some inline reference-style content (the proxy flags table) that keeps it just below the ideal split.	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 includes an explicit 'Use when...' trigger and names the Hume domain, but its action language is generic and it lacks keyword synonyms or concrete capabilities. It is solid but could be sharpened with specific Hume actions.

Suggestions

Replace generic verbs like 'Manage' with concrete Hume capabilities (e.g., 'Analyze facial expressions, vocal tones, and language for emotional insight').

Add natural keyword synonyms and trigger variations users might say (e.g., 'emotion analysis', 'voice tone', 'facial expression analysis').

Tighten the 'when' clause to mention the concrete Hume use cases (customer behavior, market research, human-computer interaction) so it is more specific.

Dimension	Reasoning	Score
Specificity	Names the Hume domain and a couple of actions ("Manage data, records, and automate workflows") but the actions are generic ('manage') rather than concrete, matching the anchor that lists domain plus 1-2 actions without comprehensive coverage.	3 / 5
Completeness	It states both what it does ('Manage data, records, and automate workflows') and an explicit 'Use when the user wants to interact with Hume data' trigger, matching the anchor with both what and when where the when could be more specific.	4 / 5
Trigger Term Quality	The natural keyword 'Hume' and the phrase 'interact with Hume data' are present, but no synonyms or common variations are offered, fitting the anchor for some relevant keywords missing common variations.	3 / 5
Distinctiveness Conflict Risk	The 'Hume' niche is distinct with a clear trigger phrase, though the generic 'Manage data, records' wording leaves minor overlap risk with broad data skills, fitting the mostly-distinct anchor.	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/hume/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.