CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ax-go-audio

Use when writing Go code with `github.com/ax-llm/ax/packages/go` for audio input/output, OpenAI Responses audio mapping, realtime event folding, and generated package audio examples.

Quality

75%

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/go/skills/ax-go-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 factually dense and efficient, clearly written for a competent agent, but it reads more like an API fact sheet than an actionable skill: the core tasks lack executable examples, and heavy reference material is inlined instead of split out. Referenced files are not part of the bundle, weakening navigation.

Suggestions

Add complete, executable examples for the headline tasks — a speak() call with renderAudio, and a minimal realtime event-folding loop — instead of describing their behavior in prose bullets.

Move the 'Relevant API Surface' symbol list into a separate reference file (e.g. references/api-surface.md), keeping only the audio-relevant symbols inline in SKILL.md.

Resolve the dangling references: either ship API.md, axir-api.json, and examples/ in the skill bundle or state explicitly that they live in the generated package repository, so the agent knows where to find them.

DimensionReasoningScore

Conciseness

The body is dense and assumes Go competence with no basic-concept padding, but the 'Relevant API Surface' section inlines dozens of symbols largely unrelated to audio (balancers, tracers, meters, rate limiters), which is trimmable bulk — fitting the 'efficient with minor instances that could be trimmed' anchor rather than score 5's 'every token earns its place'.

4 / 5

Actionability

There is one small executable snippet (`ax.NewAI(...)`), but the headline tasks the skill promises — speak() rendering, realtime event folding, audio input mapping — are covered only by descriptive bullets with no complete runnable code, leaving key execution details missing (anchor 3) rather than 'mostly executable with minor gaps' (anchor 4).

3 / 5

Workflow Clarity

'When To Use' and 'Guardrails' provide directional guidance (start from examples, no-key for local checks), but there is no sequenced flow for actually accomplishing the promised tasks and no checkpoints; the steps-present-but-gaps anchor 3 fits better than anchor 4's 'clear sequence with most checkpoints'.

3 / 5

Progressive Disclosure

Sections are well-organized, but the large API symbol list is content that belongs in a separate reference file, and the paths the body cites (`API.md`, `axir-api.json`, `examples/`, 'the gen skill') are not present in the skill bundle (no references/, scripts/, or assets/ directories exist), leaving navigation unresolved — matching anchor 3 rather than anchor 4.

3 / 5

Total

13

/

20

Passed

Description

83%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 description: specific, third-person, correctly sized, with an explicit 'Use when' clause anchored to a unique package path. Its main weakness is trigger-term breadth — users asking about speech, TTS, voice, or transcription in Go would not naturally match the current wording.

DimensionReasoningScore

Specificity

The description lists multiple concrete capabilities — "audio input/output, OpenAI Responses audio mapping, realtime event folding, and generated package audio examples" — giving comprehensive coverage of the skill's audio niche, matching the top anchor rather than the 'minor gaps' anchor below it.

5 / 5

Completeness

Both parts are present: the 'what' (audio I/O, mapping, folding, examples for the generated Go package) and an explicit "Use when writing Go code with `github.com/ax-llm/ax/packages/go`" trigger. The 'when' clause is concrete via the package path but offers no additional user-facing trigger phrases, so it matches anchor 4 ('could be more explicit or specific') rather than anchor 5.

4 / 5

Trigger Term Quality

Natural terms like "Go code", "audio input/output", and "realtime" are present, but common user phrasings such as "speech", "TTS", "voice", or "transcription" (which the body demonstrates the skill handles) are missing, fitting the 'good coverage, a few natural terms missing' anchor rather than the comprehensive one.

4 / 5

Distinctiveness Conflict Risk

The exact import path `github.com/ax-llm/ax/packages/go` combined with the audio/realtime focus creates a clear niche with distinct triggers and minimal overlap risk with generic Go or audio skills.

5 / 5

Total

18

/

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/go/skills/ax-go-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.