Name: gladia
Rating: 54.400000000000006 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

gladia

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

Quality

61%

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/gladia/SKILL.md

Quality

Content

82%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 highly actionable with executable Membrane CLI commands and a well-sequenced connection workflow that includes polling-based validation, held back only by a loose step reference, some trimmable prose, and no validation guidance around the listed destructive actions.

Suggestions

Fix the dangling "skip to Step 2" references by explicitly numbering the workflow steps (e.g. label the connection section Step 1 and the action-running section Step 2).

Add a validation checkpoint or confirmation step before running destructive actions (delete-live-transcription, delete-pre-recorded-transcription) listed in the Popular actions table.

Trim the opening marketing paragraph and the "focus on the integration logic rather than auth plumbing" aside to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is dominated by executable commands, flag tables, and a compact actions table, with only minor over-explanation (e.g. "so you can focus on the integration logic rather than auth plumbing" and the opening Gladia marketing paragraph), matching the score-4 anchor of efficient content with minor trimmable padding.	4 / 5
Actionability	It provides copy-paste-ready commands for install, login, connection, polling, action search/run, and proxying, plus a concrete popular-actions table with keys, fully covering the common cases per the score-5 anchor.	5 / 5
Workflow Clarity	The connection workflow is clearly sequenced with an explicit polling feedback loop and state-based branching (READY/BUILDING/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR), but references to an unlabeled "Step 2" and the absence of validation guidance around the listed destructive delete actions are minor gaps keeping it at 4 rather than 5.	4 / 5
Progressive Disclosure	Content is well-organized into clearly headed sections with most material appropriately placed inline; no external reference files exist and none are linked, so it meets the score-4 anchor of good structure with minor organization gaps rather than the score-5 bar requiring signaled one-level-deep references.	4 / 5
	Total	17 / 20 Passed

Description

41%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 names a distinct app and includes an explicit 'Use when' clause, but its action verbs are generic and it omits the natural trigger terms (transcription, speech-to-text, audio) that users would actually say.

Suggestions

Replace generic verbs with concrete Gladia capabilities, e.g. "Transcribe audio and video, run live transcription sessions, and analyze speech-to-text results."

Add natural trigger terms users actually say: "Use when the user wants to transcribe audio, generate speech-to-text, or work with live/pre-recorded transcription."

Mention file formats or input types (audio/video files) to strengthen trigger-term quality.

Dimension	Reasoning	Score
Specificity	"Manage data, records, and automate workflows" names the Gladia domain but the actions are generic verbs (manage, automate) rather than concrete Gladia capabilities like transcription or speech-to-text, matching the score-2 anchor of minimal/generic actions.	2 / 5
Completeness	Both a "what" ("Manage data, records, and automate workflows") and a "when" ("Use when the user wants to interact with Gladia data") are present, but the what is vague and the when is generic, so it sits at the score-3 level rather than 4 where both are clear and specific.	3 / 5
Trigger Term Quality	The trigger phrase "Use when the user wants to interact with Gladia data" plus "data, records, workflows" offers only generic keywords; it misses the natural terms users actually say (transcribe, transcription, speech-to-text, audio), fitting the score-2 anchor of one or two generic keywords missing natural phrases.	2 / 5
Distinctiveness Conflict Risk	Naming the specific app "Gladia" gives it a clear niche with minimal conflict risk, but the generic trigger ("interact with Gladia data") keeps it just below the score-5 bar of distinct, specific triggers.	4 / 5
	Total	11 / 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/gladia/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.