Name: azure-speech-to-text-rest-py
Rating: 60 (1 reviews)
Author: administrakt0r

azure-speech-to-text-rest-py

Azure Speech to Text REST API for short audio (Python). Use for simple speech recognition of audio files up to 60 seconds without the Speech SDK.

Quality

70%

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 ./plugins/AI-Agents-Safe-Coding-Skills/skills/azure-speech-to-text-rest-py/SKILL.md

The canonical home for this skill is azure-speech-to-text-rest-py in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

71%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 comprehensive executable examples and clear boundary guidance, but it pays for breadth in conciseness (repeated boilerplate, a vague closing line) and lacks genuine progressive disclosure since its only referenced file is missing and most reference material is inlined.

Suggestions

Remove the vague closing 'When to Use' line ('applicable to execute the workflow or actions described in the overview') and replace it with a concrete, specific trigger sentence.

Factor the shared request boilerplate (URL construction, headers, params) into a single canonical snippet and have the chunked, bearer, async, and error-handling variants show only what differs, to cut repeated Content-Type/header blocks.

Create references/pronunciation-assessment.md (the file the Reference Files table points to) or remove the broken reference row, and move the supported-languages table and detailed response-format examples into reference files linked from a concise overview.

Dimension	Reasoning	Score
Conciseness	The body is mostly code and tables with little conceptual padding, but header/Content-Type boilerplate is repeated verbatim across five code variants and the closing 'When to Use' line ('applicable to execute the workflow or actions described in the overview') is vague filler, so it could be tightened beyond the 4 anchor.	3 / 5
Actionability	Quick Start gives copy-paste-ready executable Python, and the chunked-transfer, bearer-token, error-handling, and async variants plus parameter/status tables cover the common cases fully, matching the fully-executable anchor.	5 / 5
Workflow Clarity	The single transcription action is unambiguous in Quick Start and the error-handling example validates RecognitionStatus, but the body is organized as a reference of variants rather than a sequenced workflow with explicit checkpoints, leaving minor gaps versus the 5 anchor.	4 / 5
Progressive Disclosure	Section headers give reasonable structure, but the file is a long monolithic wall with content (supported-languages list, full API reference) that could live in separate files inlined, and the one declared reference (references/pronunciation-assessment.md) does not exist on disk, so it is not well-signaled one-level-deep disclosure.	3 / 5
	Total	15 / 20 Passed

Description

70%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 concrete, third-person, and covers both what the skill does and when to use it with a reasonable trigger phrase. It is held back from the top band by single-action specificity, a single trigger context, and minor overlap risk with broader transcription skills.

Dimension	Reasoning	Score
Specificity	Names the domain ('Azure Speech to Text REST API for short audio') and one concrete action ('speech recognition of audio files up to 60 seconds'), but does not enumerate multiple specific actions, matching the 1-2-action anchor rather than the several-actions anchor at 4.	3 / 5
Completeness	Explicitly answers both what ('Azure Speech to Text REST API for short audio (Python)') and when ('Use for simple speech recognition of audio files up to 60 seconds without the Speech SDK'), but the trigger is a single context rather than the comprehensive, multi-phrase coverage of the 5 anchor.	4 / 5
Trigger Term Quality	Includes natural terms users say ('speech recognition', 'speech to text', 'audio files', 'Python') with good synonym coverage, though common variations like 'transcribe'/'transcription' are missing, fitting the good-coverage-with-gaps anchor.	4 / 5
Distinctiveness Conflict Risk	The Azure + REST + short-audio + Python + without-SDK niche is mostly distinct with only minor overlap risk against general transcription skills, fitting the mostly-distinct anchor rather than the clear-niche-minimal-conflict anchor at 5.	4 / 5
	Total	15 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills/skills/azure-speech-to-text-rest-py/SKILL.md
Commit: 57c135b

Reviewed: 21 hours 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.