Name: maestra
Rating: 55.2 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

maestra

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

Quality

63%

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/maestra/SKILL.md

Quality

Content

68%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 well-structured with concrete Membrane CLI commands throughout. Its main weakness is workflow sequencing — undefined 'Step 2' references and a missing connection-step-1 anchor make the flow confusing, and there is no validation feedback loop for action failures.

Suggestions

Fix the broken step references: define 'Step 1' and 'Step 2' explicitly and remove the orphaned 'Step 1b' / 'Step 2' callouts so the connection flow reads top to bottom.

Add a validation/recovery checkpoint after running actions (e.g. how to interpret a non-READY state or an error response and retry).

Replace the placeholder 'QUERY' intent with a Maestra-specific example (e.g. 'transcribe a file' or 'list transcripts') and explain where CONNECTION_ID comes from.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with executable command blocks and a tight options table, though the overview intro ('used by content creators, educators, and businesses') is mild padding Claude does not need.	4 / 5
Actionability	Provides concrete, copy-pasteable `membrane` commands with flags and a parameter-passing example; minor gaps include the undefined CONNECTION_ID source and placeholder intent 'QUERY'.	4 / 5
Workflow Clarity	Steps are roughly sequenced but checkpoints are inconsistent: it references 'Step 2' that is never defined, mixes 'Step 1b' before 'Step 1', and lacks a validation/recovery loop for failed actions.	3 / 5
Progressive Disclosure	Well-organized into clear sections (install, auth, connecting, searching, actions, proxy, best practices) with no external bundle files needed; everything is inline and one level deep.	4 / 5
	Total	15 / 20 Passed

Description

57%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 short and branded with an explicit 'Use when' trigger, but the capability statement is sparse — 'Manage Organizations, Users' uses generic verbs and omits the actual Maestra use case (transcription/captioning) that the body reveals.

Suggestions

Replace the generic verb 'Manage' with concrete Maestra actions such as 'transcribe audio and video, generate captions, and manage Organizations and Users'.

Mirror the body's core capability so the description reflects transcription/captioning, not just generic data interaction.

Add common trigger phrasings users would say, e.g. 'transcribe', 'caption', or 'subtitle' media files.

Dimension	Reasoning	Score
Specificity	Names the domain ('Maestra integration') and two entities ('Manage Organizations, Users') but the actions are generic ('Manage') with no concrete operations listed.	2 / 5
Completeness	Has both a 'what' ('Manage Organizations, Users') and an explicit 'when' ('Use when the user wants to interact with Maestra data'), though both are somewhat sparse.	4 / 5
Trigger Term Quality	Includes the natural term 'Maestra' and the phrase 'interact with Maestra data', but lacks common synonyms or variations users might say.	3 / 5
Distinctiveness Conflict Risk	The Maestra brand name makes it fairly distinct and unlikely to trigger for the wrong skill, though 'Manage Organizations, Users' could overlap with generic admin skills.	4 / 5
	Total	13 / 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/maestra/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.