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

Blog Docs Log in Get started

medius

Medius integration. Manage data, records, and automate workflows. Use when the user wants to interact with Medius 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/medius/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 guide to driving Medius via the Membrane CLI, with real commands and a state-aware connection workflow; its main weaknesses are conciseness padding and a couple of structural/navigational loose ends.

Suggestions

Tighten conciseness: remove the filler line 'Use action names and parameters as needed.' and trim the marketing-style overview prose.

Fix the official docs URL — it points to oculus.developer.oculus.com rather than Medius documentation, which is misleading.

Define the undefined 'Step 2' reference and reconcile the inconsistent numbering (1b with no 1a/2) in the connection workflow.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with lean code blocks, but padded by the ~30-item entity bullet list, marketing-style overview prose, and filler lines like 'Use action names and parameters as needed.' that could be trimmed.	3 / 5
Actionability	Provides concrete, executable commands throughout (install, login, connection ensure/get, action list/run, request proxy with a flags table); minor gap is the 'Popular actions' section, which repeats the discovery command instead of showing real example actions.	4 / 5
Workflow Clarity	Clear install→auth→connect→search→run sequence with state-based checkpoints (READY/BUILDING/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR) and a poll-after-action feedback loop, but the referenced 'Step 2' is undefined and numbering is inconsistent (1b with no 1a/2).	4 / 5
Progressive Disclosure	Well-organized into clear section headers with no broken or deeply nested references and no bundle files to navigate; stops short of 5 because the monolithic entity list and proxy table are inlined rather than split into reference materials.	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 answers both what and when in third-person voice and is anchored to a named app, but its actions and trigger terms are generic rather than reflecting Medius's accounts-payable domain.

Suggestions

Replace generic verbs ('Manage data, records, and automate workflows') with Medius-specific actions like 'process invoices, approve payments, and manage vendor records' to sharpen specificity and trigger terms.

Add concrete trigger phrases to the 'Use when' clause, e.g. 'when the user mentions invoices, vendor records, payment approvals, or AP automation.'

Dimension	Reasoning	Score
Specificity	Names the Medius domain and a few actions ('Manage data, records, and automate workflows'), but the actions are generic rather than Medius-specific (e.g. process invoices, approve payments), so coverage is not comprehensive.	3 / 5
Completeness	Both 'what' ('Medius integration. Manage data, records, and automate workflows.') and 'when' ('Use when the user wants to interact with Medius data.') are present; the 'when' is explicit but generic, so it stops short of concrete trigger phrases.	4 / 5
Trigger Term Quality	Includes the natural keyword 'Medius' / 'Medius data' in the trigger clause, but misses common variations and synonyms a user would say such as invoices, AP automation, payments, or vendor records.	3 / 5
Distinctiveness Conflict Risk	Naming the specific app 'Medius' gives it a clear niche with minimal conflict risk, though the generic 'manage data, records, and automate workflows' wording leaves minor overlap with other integration 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/medius/SKILL.md
Commit: f484c82

Reviewed: 6 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.