yao-audio

Audio expert. ALWAYS invoke this skill when the user asks to transcribe, recognize, or convert speech/audio to text.

Quality

96%

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

Quality

Content

100%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 clean, executable, well-structured reference for two audio tools that respects token budget and gives copy-paste-ready guidance. No meaningful gaps for a skill of this scope.

Dimension	Reasoning	Score
Conciseness	The body is lean — minimal prose, two CLI examples per tool, and parameter tables — and assumes Claude's competence without explaining what audio or STT is.	5 / 5
Actionability	It provides copy-paste-ready executable `tai tool` commands with real flags, plus parameter tables giving types, required flags, and descriptions covering the common cases.	5 / 5
Workflow Clarity	This is a simple single-purpose skill (~40 lines) with an unambiguous action; the simple-skill exception applies and the Constraints section flags that unsupported parameters cause errors.	5 / 5
Progressive Disclosure	The content is well-organized into clear per-tool sections with examples and tables; under 50 lines with no need for external references, satisfying the simple-skill path.	5 / 5
	Total	20 / 20 Passed

Description

92%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, concise description that clearly states capabilities and provides explicit invocation triggers. The only minor gap is coverage of additional natural synonyms a user might say.

Suggestions

Add common synonyms a user might naturally say, such as 'dictation', 'captions', or 'subtitles', to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description lists three concrete actions — 'transcribe', 'recognize', and 'convert speech/audio to text' — giving comprehensive coverage of the audio-to-text task.	5 / 5
Completeness	It explicitly answers both 'what' ('Audio expert') and 'when' ('ALWAYS invoke this skill when the user asks to transcribe, recognize, or convert speech/audio to text') with concrete trigger phrases.	5 / 5
Trigger Term Quality	It includes natural user phrases ('transcribe', 'recognize', 'speech/audio to text') but misses common synonyms like 'dictation' or 'captions/subtitles' and file extensions.	4 / 5
Distinctiveness Conflict Risk	The audio-to-text niche is distinct, and its triggers are unlikely to collide with other skills, giving minimal conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: YaoApp/yao
Path: tools/skills/yao-audio/SKILL.md
Commit: d90d41d

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.