azure-speech-to-text

Transcribe audio to text using Azure AI Speech (Fast Transcription REST API). Use when converting audio/video to text, generating subtitles, or processing spoken content in OpenMontage. Optional cloud STT provider — preferred when AZURE_SPEECH_KEY is configured; the local faster-whisper `transcriber` is the default offline path.

Quality

85%

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

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.

A tight, actionable single-tool skill doc with concrete code, a useful comparison table, and a verification tip. Could nudge toward leaner prose and an explicit numbered verification step.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with useful non-obvious content (the three-surface comparison table, schema mapping); a few sections like the rationale narrative could be trimmed slightly, so it does not reach fully lean.	4 / 5
Actionability	Provides a copy-paste-ready registry example with realistic parameters, an explicit env-var setup block, and the exact output JSON schema, covering the common case fully.	5 / 5
Workflow Clarity	Setup → call → fallback sequence is clear and includes a verification checkpoint ("Spot-check the first and last cues"), but the validation is advisory rather than an explicit step in a numbered workflow.	4 / 5
Progressive Disclosure	Well-organized into clearly headed sections with no nested references and no bundle files to mis-route; at ~107 lines some reference-shape detail could move to a separate file, keeping it just below the top anchor.	4 / 5
	Total	17 / 20 Passed

Description

87%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.

A strong, specific description with an explicit trigger clause and clear provider niche. Minor room to broaden trigger synonyms and separate true capabilities from use-cases.

Dimension	Reasoning	Score
Specificity	Names the domain (Azure AI Speech, Fast Transcription REST API) and several concrete applications — "converting audio/video to text, generating subtitles, or processing spoken content" — though they are use-cases of one core capability rather than distinct actions, so it sits just below comprehensive.	4 / 5
Completeness	Clearly states what it does ("Transcribe audio to text using Azure AI Speech") and an explicit "Use when..." clause with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Good natural-term coverage ("audio/video to text", "subtitles", "spoken content") with the provider tied to AZURE_SPEECH_KEY, but misses common synonyms like "transcription" or "speech-to-text" in the description itself.	4 / 5
Distinctiveness Conflict Risk	Tied to a specific provider (Azure AI Speech, Fast Transcription) and explicitly contrasted with the local faster-whisper transcriber default, giving it a clear niche with minimal conflict risk.	5 / 5
	Total	18 / 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
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: calesthio/OpenMontage
Path: .agents/skills/azure-speech-to-text/SKILL.md
Commit: cd9f3c1

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.