CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ax-java-audio

Use when writing Java code with `dev.axllm:ax` for audio input/output, OpenAI Responses audio mapping, realtime event folding, and generated package audio examples.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./packages/java/skills/ax-java-audio/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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 a token-efficient, fact-dense API briefing that avoids teaching known concepts, and it captures exact behavioral contracts well. It falls short on execution guidance — no runnable examples for the core audio tasks — and on disclosure, since referenced files are neither bundled nor clearly linked while bulk API listings sit inline.

Suggestions

Add one short executable example each for the core tasks (a speak() call and an audio-input or realtime-event folding snippet) instead of only deferring to the examples/ directory.

Move the "Relevant API Surface" class list into a reference file (or the existing API.md) and link it with explicit see-X-for-Y pointers.

Sequence the usage guidance into an ordered workflow (start from examples, run no-key checks, then provider calls) with an explicit validation step before live provider requests.

DimensionReasoningScore

Conciseness

The body is dense with package-specific facts Claude cannot know (speak() result keys, provider defaults, precedence rules), so nearly every token earns its place; minor trimming is possible in the repeated "as in TypeScript" phrasing and the inline class-name list.

4 / 5

Actionability

The Core Pattern snippet is executable and the behavioral bullets are precise, but the main use cases (calling speak(), folding realtime events, sending audio input) lack complete executable examples and are deferred to an examples/ directory that is not present in the bundle.

3 / 5

Workflow Clarity

"When To Use" and "Guardrails" list usage contexts and directives but there is no sequenced process or validation checkpoint for the covered tasks, leaving the order of operations implicit.

3 / 5

Progressive Disclosure

Sections are well-organized, but API.md, axir-api.json, axir-capabilities.json, and examples/ are name-dropped without links or see-X-for-Y signaling, and the long "Relevant API Surface" class list is inline content that belongs in a separate reference file.

3 / 5

Total

13

/

20

Passed

Description

71%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 well-scoped and explicit about when to trigger, with a specific package and language anchor that makes conflicts unlikely. Its main weaknesses are missing natural trigger synonyms (speech, TTS, transcription, voice) and a what-that's-only-implied-through-the-when phrasing.

Suggestions

Add natural user trigger terms such as speech, text-to-speech, TTS, transcription, or voice alongside the existing jargon like "realtime event folding".

State the what as a leading action clause (e.g., "Maps speech, transcription, and realtime audio events...") before the "Use when" clause so both halves are independently explicit.

Replace or clarify "generated package audio examples" with a concrete capability statement, since it currently reads as vague padding.

DimensionReasoningScore

Specificity

Names several concrete capability areas — "audio input/output, OpenAI Responses audio mapping, realtime event folding" — which matches the several-specific-actions anchor, though "generated package audio examples" is vague and coverage of the audio domain (speech, TTS, transcription) is incomplete.

4 / 5

Completeness

The explicit "Use when writing Java code with `dev.axllm:ax` for..." clause answers when clearly, and the what is conveyed through the enumerated purposes, but the what is folded into the when-clause rather than stated as its own action statement.

4 / 5

Trigger Term Quality

Relevant keywords like "Java", "audio", and "OpenAI Responses" are present, but the most natural user triggers for this domain (speech, TTS, transcription, voice) are missing and "realtime event folding" is internal jargon users would not say.

3 / 5

Distinctiveness Conflict Risk

Scoping to "Java code with `dev.axllm:ax`" plus a specific audio/realtime niche creates a clear, distinct trigger surface with minimal overlap risk against other skills.

5 / 5

Total

16

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

ax-llm/ax

Path

packages/java/skills/ax-java-audio/SKILL.md

Reviewed

Table of Contents

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.