Name: ax-audio
Rating: 68 (1 reviews)
Author: ax-llm

ax-audio

This skill helps an LLM generate correct audio code with @ax-llm/ax. Use when the user asks about ai.transcribe(), ai.speak(), signature audio inputs or outputs, agent audio behavior, .chat() conversational audio, OpenAI audio or realtime models, Gemini Live native audio, Grok Voice Agent models, voices, formats, transcripts, or how audio fits with structured outputs.

Quality

82%

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

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A dense, highly actionable codegen reference with complete executable examples and clear per-API sections. Its main weaknesses are inline time-sensitive model/version strings, the absence of validation/error-recovery checkpoints in the workflow, and a monolithic structure that could offload provider-default reference material to separate files.

Suggestions

Move time-sensitive model/version strings (e.g. gemini-2.5-flash-native-audio-preview-12-2025, grok-voice-think-fast-1.0, gpt-realtime-2) into an 'old patterns' or provider-defaults reference, or note that they may drift, so they don't bloat the main body.

Add a brief validation/error-recovery note for batch audio calls (e.g. catch AxMediaNotSupportedError and fall back to a supported provider/format) to give the workflow explicit checkpoints.

Extract the OpenAI/Gemini/Grok default-config reference blocks into a separate PROVIDERS.md (one level deep) and link to it from the main body to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean, code-forward reference material that assumes Claude's competence, but it embeds time-sensitive model/version strings inline (e.g. 'gemini-2.5-flash-native-audio-preview-12-2025', 'grok-voice-think-fast-1.0', 'gpt-realtime-2') outside any 'old patterns'/'deprecated' section and repeats lengthy per-provider default blocks, so it could be tightened.	2 / 3
Actionability	Provides complete, executable TypeScript examples with real imports and full API calls (transcribe, speak, signature forward, agent forward, .chat, streaming, structured outputs) that are copy-paste ready.	3 / 3
Workflow Clarity	The opening 'Pick the smallest audio surface that matches the job' bullets give a clear selection sequence, but there are no validation checkpoints or error-recovery feedback loops for the batch audio operations, which caps clarity at 2.	2 / 3
Progressive Disclosure	Sections are well-organized with clear headers and easy navigation, but the skill is a monolithic single file (over 50 lines) with large inline provider-default reference blocks that could be split into separate reference files, and no external references are used.	2 / 3
	Total	9 / 12 Passed

Description

100%

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, well-constructed description that concisely states the skill's purpose and gives an explicit, comprehensive 'Use when' trigger list covering the relevant APIs, providers, and natural audio terms. It is distinctive and unlikely to conflict with other skills.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions and APIs ('generate correct audio code with @ax-llm/ax', 'ai.transcribe()', 'ai.speak()', 'signature audio inputs or outputs', '.chat() conversational audio') rather than vague language, matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly states what it does ('helps an LLM generate correct audio code with @ax-llm/ax') and when to use it via an explicit 'Use when the user asks about...' clause, satisfying both what and when.	3 / 3
Trigger Term Quality	Covers natural terms users of this library would say — 'voices, formats, transcripts', 'OpenAI audio or realtime models', 'Gemini Live native audio', 'Grok Voice Agent models' — giving good coverage rather than just jargon.	3 / 3
Distinctiveness Conflict Risk	The niche is clearly Ax audio codegen with distinctive triggers tied to specific Ax APIs and provider audio models, making it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 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: ax-llm/ax
Path: website/static/typescript/.well-known/agent-skills/ax-audio/SKILL.md
Commit: 7911e27

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.